Anything not like your other LLM Stack with Custom Wrapper Layer & Multi-nodes – Part 4

Today, I’ll be sharing the fourth & final installment of the Colibri LLM framework with a bit of custom twists to get a stunning result at the end of this post.

In case, if you want read the previous posts from this series, then do visit the following links –

ANYTHING NOT LIKE YOUR OTHER LLM STACK – PART 1

ANYTHING NOT LIKE YOUR OTHER LLM STACK – PART 2

ANYTHING NOT LIKE YOUR OTHER LLM STACK – PART 3

The primary goal of this post is to optimize overall LLM response performance by finding the right balance between hardware capabilities and the optimization techniques offered by the Colibri framework. The objective is to achieve the best possible performance when running large language models (LLMs) locally, without relying on massive AI infrastructure or expensive cloud-based premium models.

But, before that let us watch the demo first.

Great! Based on the tests conducted across the use cases shown above, we observed significant differences in the total time required to generate a complete LLM response. The following summarizes the performance of each configuration using the same prompt and a response length of approximately 400 words:

  • Option 1 – Direct Execution Using the Colibri Framework (Command Line): Running the Colibri framework directly from the command line took between 16 and 22 minutes to generate the complete response.
  • Option 2 – Colibri Framework With a Wrapper Layer (Custom Web UI): Using a custom web interface with a wrapper layer built around the Colibri framework reduced the total response time to under 32 minutes for the same prompt.
  • Option 3 – Colibri Framework With a Wrapper Layer and Multi-Node Architecture (Custom Web UI):Integrating the wrapper layer with the Colibri framework in a multi-node configuration further reduced the total response time to 3 – 4 minutes or less, representing a substantial performance improvement over the previous configurations.

Key Takeaway: The multi-node configuration delivered the most significant performance improvement, reducing response generation time from over 16 to 22 minutes to 3 – 4 minutes or less. This demonstrates the potential of combining hardware resources with software optimization to make local LLM inference considerably faster, without relying on expensive cloud-based infrastructure.


Now, let’s explore how we achieved what initially seemed impossible. Before diving into the technical details, it is important to understand the core principles behind this solution. The key lies in a combination of software and hardware optimizations, along with efficient data transfer and communication between components. Each of these elements plays a critical role in achieving the performance improvements demonstrated above.

For this setup, I used a Satechi CubeDock Thunderbolt 5 docking station equipped with a Samsung 9100 PRO 2 TB NVMe SSD as an external high-speed storage solution, rather than upgrading the internal storage of my MacBook Pro M4 Max. This external SSD stores two different LLMs configured to run using the Colibri framework.

Since the MacBook Pro can directly access this high-speed SSD, I used SMB (Server Message Block) network sharing to make the model files accessible to both Mac minis. Each Mac mini mounts the shared storage over the network, allowing all three machines to access the centrally stored models without maintaining separate copies on their internal SSDs.

This approach helps overcome the individual storage limitations of the Mac minis while enabling a more flexible, multi-node architecture. However, shared storage does not increase the available RAM on each machine; memory utilization must still be managed according to each node’s hardware capabilities.

An important aspect of this architecture is that each LLM and computing node has a specific responsibility, while the MacBook Pro M4 Max serves as the primary or master node, coordinating the overall workflow and distributing tasks across the available resources.

Now, I’ll share the hardware details, which I bought it from Amazon & Quill (This is not a paid promotion for any of the products).

I’ve been using my Mac minis and MacBook Pro for quite some time, so I decided to put these existing machines to better use by combining them into a multi-node computing cluster.

You can adopt a similar approach using your existing computers, provided they meet the hardware and software requirements of your setup. The machines do not necessarily need identical specifications, as different nodes can contribute based on their individual capabilities.

The key takeaway? Don’t be too quick to discard your older computers! With the right configuration and optimization, they can still serve a valuable purpose in modern AI workloads. Unless you’re upgrading or trading them in as part of a worthwhile deal, consider how you might repurpose them. You never know when those additional computing resources might come in handy.


In this section, I’ll explain how each computing node can run a specific LLM based on its available memory and hardware capabilities, with each model assigned a particular task. By distributing these tasks across multiple nodes and executing them in parallel, we can significantly reduce the overall processing time and improve the efficiency of the entire system.

The goal is to demonstrate how this multi-node architecture can deliver competitive LLM response performance, potentially approaching that of commercial, cloud-based LLM services for certain workloads, while making the most of existing hardware resources and minimizing infrastructure costs.

As you can see that, the Mini’s will share the caches, whereas the Master node won’t as they belongs to complete two different kinds of model families.

Until or unless the Mac Mini’s are available the entire process will take place in the master node only.

Now, the sequence of activities that happened as follows ->

As soon as you submit the prompt the following sequence of activities will take place –

  • The master node (MacBook Pro M4 Max) first analyzes the submitted request and breaks it down into high-level sections based on the topic and its context.
    • Task Distribution: Once the sections are defined, the master node shares each section’s specific context and instructions with the assigned Mac mini node.
    • Parallel Processing: Each Mac mini processes one request at a time. With two Mac minis operating simultaneously, the system can handle up to two concurrent requests, allowing both nodes to independently generate relevant content for their assigned sections.
    • Task Queue and Monitoring: While both nodes are busy processing their current assignments, the remaining sections stay in a queue. The Web UI displays the status of each section, making it easy to identify which tasks are being processed and which are waiting for an available node.
    • Automatic Task Execution: As soon as a Mac mini completes its assigned section, it automatically picks up the next task from its queue. Using the context and instructions provided by the master node, it generates the content for that section. This process continues until all assigned sections are completed.
  • By distributing independent tasks across multiple computing nodes, this architecture enables parallel content generation, efficient resource utilization, and reduced overall response time compared with processing every section sequentially on a single node.
  • As soon as a child node (Mac mini) completes its assigned section, the master node (MacBook Pro M4 Max) begins the first phase of content review. During this phase, the master node checks for incomplete sentences or unfinished paragraphs. If any are identified, it analyzes the surrounding context and attempts to complete them while preserving the original meaning and flow.
    • Phase 1 – Section-Level Review: The master node reviews each completed section individually, identifying and correcting incomplete sentences or paragraphs to ensure the content is clear, coherent, and contextually relevant.
    • Phase 2 – Final Content Review and Refinement: Once all child nodes have completed their assigned sections and the first review phase is finished, the master node performs a second review of the entire response. During this phase, it identifies and removes duplicate statements, repetitive phrases, and redundant information across sections. It may also add important details or missing points that the child nodes did not include in their initial responses.
  • This two-phase review process helps improve the consistency, completeness, and overall quality of the final response while taking advantage of parallel content generation across multiple computing nodes.

The below image will explain the above-points clearly –

In the above, we’re showing the example of the following prompt -> “How to prepare Ilish-vape food in Bengali-Indian style?”

Hope this will give you clarity that you are looking for.

All the nodes will be connected by Thunderbolt 5 to get faster network communication.

And, here is the way all the nodes are connected ->

Satechi CubeDock (Samsung 2 TB SSD) -> MacBook Pro -> Mac Mini 1
-> Mac Mini 2

So, both the Mini’s are also diretly connected with the MacBook Pro as well.

Verify SMB is running on the MacBook Pro

networksetup -getinfo "Thunderbolt Bridge"

Verify the IP address & then execute the following –

sudo lsof -nP -iTCP:445 -sTCP:LISTEN

This checks whether the SMB service is listening for connections.

sudo launchctl print system/com.apple.smbd

Now, test the following in the Mini’s –

Configuring the SMB Drive:

nc -vz -G 5 192.168.100.X 445

X – represent your actual IP address (All the IP Address mentioned here are dummy in nature).

Then test the IP Address –

ping -c 20 192.168.100.Y

Remember, here the IP Address that is mentioned is the MacBook Pro’s IP Address i.e. Master node.

Mount the SSD from Finder

Using Command + K, you need to browse through the specific drive & navigate to the specific folder to mount it in the respective node.

smb://192.168.100.Y

Verify the SMB Drive from the terminal

mount | grep smbfs
ls /Volumes

It will show the newly mounted drive from the terminal as well.

The following is directory structure of the repo for the wrapper Layer that is hosted via the designed UI –

CollibriWrapper/
├── .cursor/
│   ├── hooks.json
│   ├── hooks/inbuilt-memory-capture.sh
│   └── rules/inbuilt-memory.mdc
├── .gitignore
├── .vscode/settings.json
├── config/nodes.json
├── docs/
│   ├── API.md
│   └── NODES_METHODS_AND_ALGORITHMS.md
├── backend/
│   ├── requirements.txt
│   ├── app/
│   │   ├── __init__.py
│   │   ├── capabilities.py
│   │   ├── colibri.py
│   │   ├── config.py
│   │   ├── discover.py
│   │   ├── hoststats.py
│   │   ├── main.py
│   │   ├── orchestrator.py
│   │   ├── planner.py
│   │   ├── scheduler.py
│   │   └── volumes.py
│   └── tests/
│       ├── __init__.py
│       ├── test_capabilities.py
│       ├── test_cluster_schedule.py
│       ├── test_discover.py
│       └── test_planner.py
├── frontend/
│   ├── index.html
│   ├── package.json
│   ├── package-lock.json
│   ├── tsconfig.json
│   ├── vite.config.ts
│   └── src/
│       ├── App.tsx
│       ├── main.tsx
│       ├── styles.css
│       └── types.ts
├── scripts/
│   ├── colibri-volume.sh
│   ├── lib/libomp.dylib
│   ├── restart-from-ui.sh
│   ├── stack-common.sh
│   ├── start.sh
│   ├── start-wrapper.sh
│   ├── stop.sh
│   ├── worker-host.py
│   ├── worker-start.sh
│   └── worker-stop.sh
└── data/
    ├── run/
    │   ├── canvas.log
    │   ├── colibri.log
    │   ├── colibri.volume
    │   ├── memory.log
    │   ├── memory-node.pid
    │   └── wrapper.log
    └── sessions/
        ├── 114af16ca1514055b309408288d8432a.json
        └── 686e1efe04f94ca293aac47e0f75ba5c.json

Start The Master Node:

We’ll be browsing through the right path (In our case) ->

cd /Volumes/TD_BLACK/StartUp/CollibriWrapper/scripts

# Start the Master Node
./start.sh

Stop The Master Node:

# To Stop the Master Node
./stop.sh

Start the Worker Node:

./worker-start.sh

Stop the Worker Node:

./worker-stop.sh

So, we’ve done it. 🙂

I hope you all like this effort & let me know your feedback. I’ll be back with another topic. Until then, Happy Avenging!

Anything not like your other LLM Stack – Part 1

Hi Guys,

Today, I’ll be presenting a brand new LLM that you can configure locally & based on your computation, I/O & other factors. We’re going to understand the open-source project named -> Colibri.

We’ll be presenting a series of simple & complex process, which will be partially optimized based on various scenarious.

Colibrì is an open-source inference engine for running very large Mixture-of-Experts (MoE) AI models locally. Its central idea is unusual: instead of requiring hundreds of gigabytes—or even terabytes—of model weights to fit entirely in RAM or GPU VRAM, it treats VRAM + RAM + NVMe storage as one memory hierarchy.

The router determines which experts are needed for each token, and Colibrì loads or caches those experts as required. In other words, it effectively performs just-in-time loading of model weights.


Let us understand the overall capability in a simpler form –

CapabilityWhat Colibrì provides
Local large-model inferenceRuns very large MoE models locally rather than requiring a hosted API.
Models larger than RAM/VRAMStreams routed experts from SSD/NVMe instead of loading the full model into memory.
CPU-only operationA GPU is not mandatory. CPU-only operation is supported.
GPU accelerationSupports heterogeneous acceleration paths including CUDA, Metal, Vulkan, and AMD/HIP in documented configurations.
Memory multitieringModel weights can be distributed across VRAM → RAM → NVMe according to available hardware.
Large open modelsCurrently documents support for nine MoE model families, including GLM, Kimi, DeepSeek, Qwen, Inkling, and OLMoE.
Local Chat interfacecoli chat provides direct interactive inference.
Web UIcoli web provides a browser-based interface with performance information and model visualization.
OpenAI-compatible APIcoli serve exposes endpoints such as /v1/chat/completions and /v1/models.
Anthropic-compatible APIAlso provides /v1/messages, allowing some Anthropic-compatible software to communicate with Colibrì.
Tool/function callingAvailable for certain supported engines, including GLM, DeepSeek V4, and Kimi K3.
Coding-tool integrationCan act as a local backend for compatible coding applications that accept an OpenAI-compatible endpoint.
Persistent KV cacheConversation state can be persisted and reused rather than completely prefilling the model again.
Multi-machine experimentsIncludes an experimental/local cluster mechanism in which other Macs can execute routed expert FFNs.
Research/observabilityProvides expert routing telemetry, profiling, Brain visualization, Atlas visualization, benchmarking, and experimentation facilities.
Open sourceEngine is released under Apache 2.0.

For more information, please refer to the following link.

Let us understand how this works for the larger models –

For the project’s reference GLM-5.2 model, the approximately 430 GB quantized model does not need 430 GB of RAM. The documentation describes keeping roughly 9.9 GB of dense components resident while streaming routed experts from storage as needed.

Please go throught he following link for more details.

Let us calculate it –

Model → must largely fit RAM/VRAM → inference
NVMe ↔ RAM ↔ VRAM → dynamically selected experts → inference

Colibrì calls this a multitier hierarchy. Fast memory affects performance, but the design aims to avoid changing the model merely because less VRAM/RAM is available. For more information, let us understand it from the official link.

That architectural concept is probably the project’s most significant contribution.

Model familyApprox. total parametersApprox. storage/RAM characteristics documented by Colibrì
GLM-5.2 / GLM-5.3744B~372 GB disk; 16 GB minimum RAM
GLM-5.3-Flash321B~195 GB converted; ~25 GB RAM
Inkling975B~469 GB; ~25 GB RAM with int4 dense container
Kimi K32.8T~1.6 TB disk; 32 GB+ RAM
DeepSeek V4 Flash284B~167 GB; 16 GB minimum
DeepSeek V4.1 Flash552Bseparate current engine implementation
Qwen3.8-Flash-Next125B + 51B n-gram~185.5 GB; 16 GB minimum
Qwen3.6-35B-A3B35B / ~3B active~20 GB; ~24 GB RAM
OLMoE7B~7 GB; ~8 GB RAM

The current repository specifically describes Kimi K3 at 2.8 trillion parameters, which illustrates how far the storage-streaming approach is intended to scale. One important distinction: Colibrì does not create these models. It is the inference engine that runs compatible open-weight models.

This is another major difference from frameworks primarily designed around GPU residency. The official quick-start says the baseline requirements for GLM-5.2 are approximately:

~16 GB RAM minimum, ~380 GB free storage, with fast NVMe recommended.

A GPU is optional. Refer to this link.

A GPU can significantly accelerate inference, but Colibrì’s architecture intentionally allows CPU + RAM + SSD operation. The repository currently contains backends for CUDA, Metal, Vulkan, and AMD/HIP-related configurations. Please refer the following link.

This makes Colibrì particularly interesting for heterogeneous hardware rather than only expensive data-center GPU configurations.

So, you don’t need the GPU to run any model.


This could be one of its most useful practical capabilities.

Run the following command:

coli serve

Creates an OpenAI-compatible HTTP API. The official documentation currently lists endpoints, including:

GET /v1/models

GET /v1/models/{model}

POST /v1/chat/completions

POST /v1/completions

It supports streaming responses, token usage, temperature, top-p, maximum-token parameters, and stop sequences.

So, you can use the application either from the postman or using API-based call or from using a curl statement while invoking the following entries –

http://localhost:8000/v1

That makes Colibrì much more than a command-line model runner.

Interestingly, Colibrì now exposes:

/v1/messages

for software built around the Anthropic Messages API.

The documentation specifically discusses using this interface with compatible clients, including Claude Code-style integrations. For more information, please refer the following link.

Therefore, the architecture can look approximately like:

This opens some interesting possibilities for private local AI applications, coding assistants, RAG systems, research environments, and experimental agents.


Some of the models support tool/function calling. This is particularly relevent if you are thinking of agentic systems. So, Colibri potentially provides the LLM reasoing/tool-call layer of a local agent architecture.

Colibrì itself isn’t a complete agent orchestration framework like AutoGen or similar systems; it provides the model inference/API layer on which an agent framework could operate.

Colibri also offered web dashboard accessible through:

coli web

The project describes three particularly interesting views –

Dashboard provides token-generation and performance metrics, including time breakdowns and VRAM/RAM/disk utilization.

Brain visualizes the model’s experts and shows which experts activate during generation.

Atlas visualizes measured expert specialization and routing affinities as a three-dimensional representation.

That makes Colibrì interesting not only for inference but also for studying how MoE models route information internally.

For more information, you can refer the following link.


Let us continue this topic in our next series.

Until then, Happy Avenging! 🙂

Real-time video summary assistance App – Part 1

Today, we’ll discuss another topic in our two-part series. We will understand the importance of the MCP protocol for communicating between agents.

This will be an in-depth highly technical as well as depicting using easy-to-understand visuals.

But, before that, let us understand the demo first.

Isn’t it exciting?


Let us first understand in easy language about the MCP protocol.

MCP (Multi-Agent Communication Protocol) is a custom message exchange system that facilitates structured and scalable communication among multiple AI agents operating within an application. These agents collaborate asynchronously or in real-time to complete complex tasks by sharing results, context, and commands through a common messaging layer.

How MCP Protocol Helps:

FeatureBenefit
Agent-Oriented ArchitectureEach agent handles a focused task, improving modularity and scalability.
Event-Driven Message PassingAgents communicate based on triggers, not polling—leading to faster and efficient responses.
Structured Communication FormatAll messages follow a standard format (e.g., JSON) with metadata for sender, recipient, type, and payload.
State PreservationAgents maintain context across messages using memory (e.g., ConversationBufferMemory) to ensure coherence.

How It Works (Step-by-Step):

  • 📥 User uploads or streams a video.
  • 🧑‍💻 MCP Protocol triggers the Transcription Agent to start converting audio into text.
  • 🌐 Translation Agent receives this text (if a different language is needed).
  • 🧾 Summarization Agent receives the translated or original transcript and generates a concise summary.
  • 📚 Research Agent checks for references or terminology used in the video.
  • 📄 Documentation Agent compiles the output into a structured report.
  • 🔁 All communication between agents flows through MCP, ensuring consistent message delivery and coordination.

Now, let us understand the solution that we intend to implement for our solutions:

This app provides live summarization and contextual insights from videos such as webinars, interviews, or YouTube recordings using multiple cooperating AI agents. These agents may include:

  • Transcription Agent: Converts spoken words to text.
  • Translation Agent: Translates text to different languages (if needed).
  • Summarization Agent: Generates concise summaries.
  • Research Agent: Finds background or supplementary data related to the discussion.
  • Documentation Agent: Converts outputs into structured reports or learning materials.

We need to understand one more thing before deep diving into the code. Part of your conversation may be mixed, like part Hindi & part English. So, in that case, it will break the sentences into chunks & then convert all of them into the same language. Hence, the following rules are applied while translating the sentences –


Now, we will go through the basic frame of the system & try to understand how it fits all the principles that we discussed above for this particular solution mapped against the specific technology –

  1. Documentation Agent built with the LangChain framework
  2. Research Agent built with the AutoGen framework
  3. MCP Broker for seamless communication between agents

Let us understand from the given picture the flow of the process that our app is trying to implement –


Great! So, now, we’ll focus on some of the key Python scripts & go through their key features.

But, before that, we share the group of scripts that belong to specific tasks.

  • clsMCPMessage.py
  • clsMCPBroker.py
  • clsYouTubeVideoProcessor.py
  • clsLanguageDetector.py
  • clsTranslationAgent.py
  • clsTranslationService.py
  • clsDocumentationAgent.py
  • clsResearchAgent.py

Now, we’ll review some of the script in this post, along with the next post, as a continuation from this post.

class clsMCPMessage(BaseModel):
    """Message format for MCP protocol"""
    id: str = Field(default_factory=lambda: str(uuid.uuid4()))
    timestamp: float = Field(default_factory=time.time)
    sender: str
    receiver: str
    message_type: str  # "request", "response", "notification"
    content: Dict[str, Any]
    reply_to: Optional[str] = None
    conversation_id: str
    metadata: Dict[str, Any] = {}
    
class clsMCPBroker:
    """Message broker for MCP protocol communication between agents"""
    
    def __init__(self):
        self.message_queues: Dict[str, queue.Queue] = {}
        self.subscribers: Dict[str, List[str]] = {}
        self.conversation_history: Dict[str, List[clsMCPMessage]] = {}
    
    def register_agent(self, agent_id: str) -> None:
        """Register an agent with the broker"""
        if agent_id not in self.message_queues:
            self.message_queues[agent_id] = queue.Queue()
            self.subscribers[agent_id] = []
    
    def subscribe(self, subscriber_id: str, publisher_id: str) -> None:
        """Subscribe an agent to messages from another agent"""
        if publisher_id in self.subscribers:
            if subscriber_id not in self.subscribers[publisher_id]:
                self.subscribers[publisher_id].append(subscriber_id)
    
    def publish(self, message: clsMCPMessage) -> None:
        """Publish a message to its intended receiver"""
        # Store in conversation history
        if message.conversation_id not in self.conversation_history:
            self.conversation_history[message.conversation_id] = []
        self.conversation_history[message.conversation_id].append(message)
        
        # Deliver to direct receiver
        if message.receiver in self.message_queues:
            self.message_queues[message.receiver].put(message)
        
        # Deliver to subscribers of the sender
        for subscriber in self.subscribers.get(message.sender, []):
            if subscriber != message.receiver:  # Avoid duplicates
                self.message_queues[subscriber].put(message)
    
    def get_message(self, agent_id: str, timeout: Optional[float] = None) -> Optional[clsMCPMessage]:
        """Get a message for the specified agent"""
        try:
            return self.message_queues[agent_id].get(timeout=timeout)
        except (queue.Empty, KeyError):
            return None
    
    def get_conversation_history(self, conversation_id: str) -> List[clsMCPMessage]:
        """Get the history of a conversation"""
        return self.conversation_history.get(conversation_id, [])

Imagine a system where different virtual agents (like robots or apps) need to talk to each other. To do that, they send messages back and forth—kind of like emails or text messages. This code is responsible for:

  • Making sure those messages are properly written (like filling out all parts of a form).
  • Making sure messages are delivered to the right people.
  • Keeping a record of conversations so you can go back and review what was said.

This part (clsMCPMessage) is like a template or a form that every message needs to follow. Each message has:

  • ID: A unique number so every message is different (like a serial number).
  • Time Sent: When the message was created.
  • Sender & Receiver: Who sent the message and who is supposed to receive it.
  • Type of Message: Is it a request, a response, or just a notification?
  • Content: The actual information or question the message is about.
  • Reply To: If this message is answering another one, this tells which one.
  • Conversation ID: So we know which group of messages belongs to the same conversation.
  • Extra Info (Metadata): Any other small details that might help explain the message.

This (clsMCPBroker) is the system (or “post office”) that makes sure messages get to where they’re supposed to go. Here’s what it does:

1. Registering an Agent

  • Think of this like signing up a new user in the system.
  • Each agent gets their own personal mailbox (called a “message queue”) so others can send them messages.

2. Subscribing to Another Agent

  • If Agent A wants to receive copies of messages from Agent B, they can “subscribe” to B.
  • This is like signing up for B’s newsletter—whenever B sends something, A gets a copy.

3. Sending a Message

  • When someone sends a message:
    • It is saved into a conversation history (like keeping emails in your inbox).
    • It is delivered to the main person it was meant for.
    • And, if anyone subscribed to the sender, they get a copy too—unless they’re already the main receiver (to avoid sending duplicates).

4. Receiving Messages

  • Each agent can check their personal mailbox to see if they got any new messages.
  • If there are no messages, they’ll either wait for some time or move on.

5. Viewing Past Conversations

  • You can look up all messages that were part of a specific conversation.
  • This is helpful for remembering what was said earlier.

In systems where many different smart tools or services need to work together and communicate, this kind of communication system makes sure everything is:

  • Organized
  • Delivered correctly
  • Easy to trace back when needed

So, in this post, we’ll finish it here. We’ll cover the rest of the post in the next post.

I’ll bring some more exciting topics in the coming days from the Python verse.

Till then, Happy Avenging!  🙂

Building the optimized Indic Language bot by using the Python-based Sarvam AI LLMs – Part 2

As we discover in our previous post about the Sarvam AI basic capabilities & a glimpse of code review. Today, we’ll finish the rest of the part & some of the matrices comparing against other popular LLMs.

Before that, you can refer to the previous post for a recap, which is available here.

Also, we’re providing the demo here –


Now, let us jump into the rest of the code –

clsSarvamAI.py (This script will capture the audio input in Indic languages & then provide an LLM response in the form of audio in Indic languages. In this post, we’ll discuss part of the code. In the next part, we’ll be discussing the next important methods. Note that we’re only going to discuss a few important functions here.)

def createWavFile(self, audio, output_filename="output.wav", target_sample_rate=16000):
      try:
          # Get the raw audio data as bytes
          audio_data = audio.get_raw_data()

          # Get the original sample rate
          original_sample_rate = audio.sample_rate

          # Open the output file in write mode
          with wave.open(output_filename, 'wb') as wf:
              # Set parameters: nchannels, sampwidth, framerate, nframes, comptype, compname
              wf.setnchannels(1)  # Assuming mono audio
              wf.setsampwidth(2)  # 16-bit audio (int16)
              wf.setframerate(original_sample_rate)

              # Write audio data in chunks
              chunk_size = 1024 * 10  # Chunk size (adjust based on memory constraints)
              for i in range(0, len(audio_data), chunk_size):
                  wf.writeframes(audio_data[i:i+chunk_size])

          # Log the current timestamp
          var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
          print('Audio Time: ', str(var))

          return 0

      except Exception as e:
          print('Error: <Wav File Creation>: ', str(e))
          return 1

Purpose:

This method saves recorded audio data into a WAV file format.

What it Does:

  • Takes raw audio data and converts it into bytes.
  • Gets the original sample rate of the audio.
  • Opens a new WAV file in write mode.
  • Sets the parameters for the audio file (like the number of channels, sample width, and frame rate).
  • Writes the audio data into the file in small chunks to manage memory usage.
  • Logs the current time to keep track of when the audio was saved.
  • Returns 0 on success or 1 if there was an error.

The “createWavFile” method takes the recorded audio and saves it as a WAV file on your computer. It converts the audio into bytes and writes them into small file parts. If something goes wrong, it prints an error message.


def chunkBengaliResponse(self, text, max_length=500):
      try:
          chunks = []
          current_chunk = ""

          # Use regex to split on sentence-ending punctuation
          sentences = re.split(r'(।|\?|!)', text)

          for i in range(0, len(sentences), 2):
              sentence = sentences[i] + (sentences[i+1] if i+1 < len(sentences) else '')

              if len(current_chunk) + len(sentence) <= max_length:
                  current_chunk += sentence
              else:
                  if current_chunk:
                      chunks.append(current_chunk.strip())
                  current_chunk = sentence

          if current_chunk:
              chunks.append(current_chunk.strip())

          return chunks
      except Exception as e:
          x = str(e)
          print('Error: <<Chunking Bengali Response>>: ', x)

          return ''

Purpose:

This method breaks down a large piece of text (in Bengali) into smaller, manageable chunks.

What it Does:

  • Initializes an empty list to store the chunks of text.
  • It uses a regular expression to split the text based on punctuation marks like full stops (।), question marks (?), and exclamation points (!).
  • Iterates through the split sentences to form chunks that do not exceed a specified maximum length (max_length).
  • Adds each chunk to the list until the entire text is processed.
  • Returns the list of chunks or an empty string if an error occurs.

The chunkBengaliResponse method takes a long Bengali text and splits it into smaller, easier-to-handle parts. It uses punctuation marks to determine where to split. If there’s a problem while splitting, it prints an error message.


def playWav(self, audio_data):
      try:
          # Create a wav file object from the audio data
          WavFile = wave.open(io.BytesIO(audio_data), 'rb')

          # Extract audio parameters
          channels = WavFile.getnchannels()
          sample_width = WavFile.getsampwidth()
          framerate = WavFile.getframerate()
          n_frames = WavFile.getnframes()

          # Read the audio data
          audio = WavFile.readframes(n_frames)
          WavFile.close()

          # Convert audio data to numpy array
          dtype_map = {1: np.int8, 2: np.int16, 3: np.int32, 4: np.int32}
          audio_np = np.frombuffer(audio, dtype=dtype_map[sample_width])

          # Reshape audio if stereo
          if channels == 2:
              audio_np = audio_np.reshape(-1, 2)

          # Play the audio
          sd.play(audio_np, framerate)
          sd.wait()

          return 0
      except Exception as e:
          x = str(e)
          print('Error: <<Playing the Wav>>: ', x)

          return 1

Purpose:

This method plays audio data stored in a WAV file format.

What it Does:

  • Reads the audio data from a WAV file object.
  • Extracts parameters like the number of channels, sample width, and frame rate.
  • Converts the audio data into a format that the sound device can process.
  • If the audio is stereo (two channels), it reshapes the data for playback.
  • Plays the audio through the speakers.
  • Returns 0 on success or 1 if there was an error.

The playWav method takes audio data from a WAV file and plays it through your computer’s speakers. It reads the data and converts it into a format your speakers can understand. If there’s an issue playing the audio, it prints an error message.


  def audioPlayerWorker(self, queue):
      try:
          while True:
              var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
              print('Response Audio Time: ', str(var))
              audio_bytes = queue.get()
              if audio_bytes is None:
                  break
              self.playWav(audio_bytes)
              queue.task_done()

          return 0
      except Exception as e:
          x = str(e)
          print('Error: <<Audio Player Worker>>: ', x)

          return 1

Purpose:

This method continuously plays audio from a queue until there is no more audio to play.

What it Does:

  • It enters an infinite loop to keep checking for audio data in the queue.
  • Retrieves audio data from the queue and plays it using the “playWav”-method.
  • Logs the current time each time an audio response is played.
  • It breaks the loop if it encounters a None value, indicating no more audio to play.
  • Returns 0 on success or 1 if there was an error.

The audioPlayerWorker method keeps checking a queue for new audio to play. It plays each piece of audio as it comes in and stops when there’s no more audio. If there’s an error during playback, it prints an error message.


  async def processChunk(self, chText, url_3, headers):
      try:
          sarvamAPIKey = self.sarvamAPIKey
          model_1 = self.model_1
          langCode_1 = self.langCode_1
          speakerName = self.speakerName

          print()
          print('Chunk Response: ')
          vText = chText.replace('*','').replace(':',' , ')
          print(vText)

          payload_3 = {
              "inputs": [vText],
              "target_language_code": langCode_1,
              "speaker": speakerName,
              "pitch": 0.15,
              "pace": 0.95,
              "loudness": 2.1,
              "speech_sample_rate": 16000,
              "enable_preprocessing": True,
              "model": model_1
          }
          response_3 = requests.request("POST", url_3, json=payload_3, headers=headers)
          audio_data = response_3.text
          data = json.loads(audio_data)
          byte_data = data['audios'][0]
          audio_bytes = base64.b64decode(byte_data)

          return audio_bytes
      except Exception as e:
          x = str(e)
          print('Error: <<Process Chunk>>: ', x)
          audio_bytes = base64.b64decode('')

          return audio_bytes

Purpose:

This asynchronous method processes a chunk of text to generate audio using an external API.

What it Does:

  • Cleans up the text chunk by removing unwanted characters.
  • Prepares a payload with the cleaned text and other parameters required for text-to-speech conversion.
  • Sends a POST request to an external API to generate audio from the text.
  • Decodes the audio data received from the API (in base64 format) into raw audio bytes.
  • Returns the audio bytes or an empty byte string if there is an error.

The processChunk method takes a text, sends it to an external service to be converted into speech, and returns the audio data. If something goes wrong, it prints an error message.


  async def processAudio(self, audio):
      try:
          model_2 = self.model_2
          model_3 = self.model_3
          url_1 = self.url_1
          url_2 = self.url_2
          url_3 = self.url_3
          sarvamAPIKey = self.sarvamAPIKey
          audioFile = self.audioFile
          WavFile = self.WavFile
          langCode_1 = self.langCode_1
          langCode_2 = self.langCode_2
          speakerGender = self.speakerGender

          headers = {
              "api-subscription-key": sarvamAPIKey
          }

          audio_queue = Queue()
          data = {
              "model": model_2,
              "prompt": templateVal_1
          }
          files = {
              "file": (audioFile, open(WavFile, "rb"), "audio/wav")
          }

          response_1 = requests.post(url_1, headers=headers, data=data, files=files)
          tempDert = json.loads(response_1.text)
          regionalT = tempDert['transcript']
          langCd = tempDert['language_code']
          statusCd = response_1.status_code
          payload_2 = {
              "input": regionalT,
              "source_language_code": langCode_2,
              "target_language_code": langCode_1,
              "speaker_gender": speakerGender,
              "mode": "formal",
              "model": model_3,
              "enable_preprocessing": True
          }

          response_2 = requests.request("POST", url_2, json=payload_2, headers=headers)
          regionalT_2 = response_2.text
          data_ = json.loads(regionalT_2)
          regionalText = data_['translated_text']
          chunked_response = self.chunkBengaliResponse(regionalText)

          audio_thread = Thread(target=self.audioPlayerWorker, args=(audio_queue,))
          audio_thread.start()

          for chText in chunked_response:
              audio_bytes = await self.processChunk(chText, url_3, headers)
              audio_queue.put(audio_bytes)

          audio_queue.join()
          audio_queue.put(None)
          audio_thread.join()

          var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
          print('Retrieval Time: ', str(var))

          return 0

      except Exception as e:
          x = str(e)
          print('Error: <<Processing Audio>>: ', x)

          return 1

Purpose:

This asynchronous method handles the complete audio processing workflow, including speech recognition, translation, and audio playback.

What it Does:

  • Initializes various configurations and headers required for processing.
  • Sends the recorded audio to an API to get the transcript and detected language.
  • Translates the transcript into another language using another API.
  • Splits the translated text into smaller chunks using the chunkBengaliResponse method.
  • Starts an audio playback thread to play each processed audio chunk.
  • Sends each text chunk to the processChunk method to convert to speech and adds the audio data to the queue for playback.
  • Waits for all audio chunks to be processed and played before finishing.
  • Logs the current time when the process is complete.
  • Returns 0 on success or 1 if there was an error.

The “processAudio”-method takes recorded audio, recognizes what was said, translates it into another language, splits the translated text into parts, converts each part into speech, and plays it back. It uses different services to do this; if there’s a problem at any step, it prints an error message.

And, here is the performance stats (Captured from Sarvam AI website) –


So, finally, we’ve done it. You can view the complete code in this GitHub link.

I’ll bring some more exciting topics in the coming days from the Python verse.

Till then, Happy Avenging! 🙂

Building the optimized Indic Language bot by using the Python-based Sarvam AI LLMs – Part 1

In the rapidly evolving landscape of artificial intelligence, Sarvam AI has emerged as a pioneering force in developing language technologies for Indian languages. This article series aims to provide an in-depth look at Sarvam AI’s Indic APIs, exploring their features, performance, and potential impact on the Indian tech ecosystem.

This LLM aims to bridge the language divide in India’s digital landscape by providing powerful, accessible AI tools for Indic languages.

India has 22 official languages and hundreds of dialects, presenting a unique challenge for technology adoption and digital inclusion. Even though all the government work happens in both the official language along with English language.

Developers can fine-tune the models for specific domains or use cases, improving accuracy for specialized applications.

As of 2024, Sarvam AI’s Indic APIs support the following languages:

  • Hindi
  • Bengali
  • Tamil
  • Telugu
  • Marathi
  • Gujarati
  • Kannada
  • Malayalam
  • Punjabi
  • Odia

Before delving into the details, I strongly recommend taking a look at the demo.

Isn’t this exciting? Let us understand the flow of events in the following diagram –

The application interacts with Sarvam AI’s API. After interpreting the initial audio inputs from the computer, it uses Sarvam AI’s API to get the answer based on the selected Indic language, Bengali.

pip install SpeechRecognition==3.10.4
pip install pydub==0.25.1
pip install sounddevice==0.5.0
pip install numpy==1.26.4
pip install soundfile==0.12.1

clsSarvamAI.py (This script will capture the audio input in Indic languages & then provide an LLM response in the form of audio in Indic languages. In this post, we’ll discuss part of the code. In the next part, we’ll be discussing the next important methods. Note that we’re only going to discuss a few important functions here.)

def initializeMicrophone(self):
      try:
          for index, name in enumerate(sr.Microphone.list_microphone_names()):
              print(f"Microphone with name \"{name}\" found (device_index={index})")
          return sr.Microphone()
      except Exception as e:
          x = str(e)
          print('Error: <<Initiating Microphone>>: ', x)

          return ''

  def realTimeTranslation(self):
      try:
          WavFile = self.WavFile
          recognizer = sr.Recognizer()
          try:
              microphone = self.initializeMicrophone()
          except Exception as e:
              print(f"Error initializing microphone: {e}")
              return

          with microphone as source:
              print("Adjusting for ambient noise. Please wait...")
              recognizer.adjust_for_ambient_noise(source, duration=5)
              print("Microphone initialized. Start speaking...")

              try:
                  while True:
                      try:
                          print("Listening...")
                          audio = recognizer.listen(source, timeout=5, phrase_time_limit=5)
                          print("Audio captured. Recognizing...")

                          #var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
                          #print('Before Audio Time: ', str(var))

                          self.createWavFile(audio, WavFile)

                          try:
                              text = recognizer.recognize_google(audio, language="bn-BD")  # Bengali language code
                              sentences = text.split('।')  # Bengali full stop

                              print('Sentences: ')
                              print(sentences)
                              print('*'*120)

                              if not text:
                                  print("No speech detected. Please try again.")
                                  continue

                              if str(text).lower() == 'টাটা':
                                  raise BreakOuterLoop("Based on User Choice!")

                              asyncio.run(self.processAudio(audio))

                          except sr.UnknownValueError:
                              print("Google Speech Recognition could not understand audio")
                          except sr.RequestError as e:
                              print(f"Could not request results from Google Speech Recognition service; {e}")

                      except sr.WaitTimeoutError:
                          print("No speech detected within the timeout period. Listening again...")
                      except BreakOuterLoop:
                          raise
                      except Exception as e:
                          print(f"An unexpected error occurred: {e}")

                      time.sleep(1)  # Short pause before next iteration

              except BreakOuterLoop as e:
                  print(f"Exited : {e}")

          # Removing the temporary audio file that was generated at the begining
          os.remove(WavFile)

          return 0
      except Exception as e:
          x = str(e)
          print('Error: <<Real-time Translation>>: ', x)

          return 1

Purpose:

This method is responsible for setting up and initializing the microphone for audio input.

What it Does:

  • It attempts to list all available microphones connected to the system.
  • It prints the microphone’s name and corresponding device index (a unique identifier) for each microphone.
  • If successful, it returns a microphone object (sr.Microphone()), which can be used later to capture audio.
  • If this process encounters an error (e.g., no microphones being found or an internal error), it catches the exception, prints an error message, and returns an empty string (“).

The “initializeMicrophone” Method finds all microphones connected to the computer and prints their names. If it finds a microphone, it prepares to use it for recording. If something goes wrong, it tells you what went wrong and stops the process.

Purpose:
This Method uses the microphone to handle real-time speech translation from a user. It captures spoken audio, converts it into text, and processes it further.

What it Does:

  • Initializes a recognizer object (sr.Recognizer()) for speech recognition.
  • Call initializeMicrophone to set up the microphone. If initialization fails, an error message is printed, and the process is stopped.
  • Once the microphone is set up successfully, it adjusts for ambient noise to enhance accuracy.
  • Enters a loop to continuously listen for audio input from the user:
    • It waits for the user to speak and captures the audio.
    • Converts the captured audio to text using Google’s Speech Recognition service, specifying Bengali as the language.
    • If text is successfully captured and recognized:
      • Splits the text into sentences using the Bengali full-stop character.
      • Prints the sentences.
      • It checks if the text is a specific word (“টাটা”), and if so, it raises an exception to stop the loop (indicating that the user wants to exit).
      • Otherwise, it processes the audio asynchronously with processAudio.
    • If no speech is detected or an error occurs, it prints the relevant message and continues listening.
  • If the user decides to exit or if an error occurs, it breaks out of the loop, deletes any temporary audio files created, and returns a status code (0 for success, 1 for failure).


The “realTimeTranslation” method continuously listens to the microphone for the user to speak. It captures what is said and tries to understand it using Google’s service, specifically for the Bengali language. It then splits what was said into sentences and prints them out. If the user says “টাটা” (which means “goodbye” in Bengali), it stops listening and exits. If it cannot understand the user or if there is a problem, it will let the user know and try again. It will print an error and stop the process if something goes wrong.


Let’s wait for the next part & enjoy this part.

Enabling & Exploring Stable Defussion – Part 1

This new solution will evaluate the power of Stable Defussion, which is created solutions as we progress & refine our prompt from scratch by using Stable Defussion & Python. This post opens new opportunities for IT companies & business start-ups looking to deliver solutions & have better performance compared to the paid version of Stable Defussion AI’s API performance. This project is for the advanced Python, Stable Defussion for data Science Newbies & AI evangelists.

In a series of posts, I’ll explain and focus on the Stable Defussion API and custom solution using the Python-based SDK of Stable Defussion.

But, before that, let us view the video that it generates from the prompt by using the third-party API:

Prompt to Video

And, let us understand the prompt that we supplied to create the above video –

Isn’t it exciting?

However, I want to stress this point: the video generated by the Stable Defusion (Stability AI) API was able to partially apply the animation effect. Even though the animation applies to the cloud, It doesn’t apply the animation to the wave. But, I must admit, the quality of the video is quite good.


Let us understand the code and how we run the solution, and then we can try to understand its performance along with the other solutions later in the subsequent series.

As you know, we’re exploring the code base of the third-party API, which will actually execute a series of API calls that create a video out of the prompt.

Let us understand some of the important snippet –

class clsStabilityAIAPI:
    def __init__(self, STABLE_DIFF_API_KEY, OUT_DIR_PATH, FILE_NM, VID_FILE_NM):
        self.STABLE_DIFF_API_KEY = STABLE_DIFF_API_KEY
        self.OUT_DIR_PATH = OUT_DIR_PATH
        self.FILE_NM = FILE_NM
        self.VID_FILE_NM = VID_FILE_NM

    def delFile(self, fileName):
        try:
            # Deleting the intermediate image
            os.remove(fileName)

            return 0 
        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return 1

    def generateText2Image(self, inputDescription):
        try:
            STABLE_DIFF_API_KEY = self.STABLE_DIFF_API_KEY
            fullFileName = self.OUT_DIR_PATH + self.FILE_NM
            
            if STABLE_DIFF_API_KEY is None:
                raise Exception("Missing Stability API key.")
            
            response = requests.post(f"{api_host}/v1/generation/{engine_id}/text-to-image",
                                    headers={
                                        "Content-Type": "application/json",
                                        "Accept": "application/json",
                                        "Authorization": f"Bearer {STABLE_DIFF_API_KEY}"
                                        },
                                        json={
                                            "text_prompts": [{"text": inputDescription}],
                                            "cfg_scale": 7,
                                            "height": 1024,
                                            "width": 576,
                                            "samples": 1,
                                            "steps": 30,
                                            },)
            
            if response.status_code != 200:
                raise Exception("Non-200 response: " + str(response.text))
            
            data = response.json()

            for i, image in enumerate(data["artifacts"]):
                with open(fullFileName, "wb") as f:
                    f.write(base64.b64decode(image["base64"]))      
            
            return fullFileName

        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return 'N/A'

    def image2VideoPassOne(self, imgNameWithPath):
        try:
            STABLE_DIFF_API_KEY = self.STABLE_DIFF_API_KEY

            response = requests.post(f"https://api.stability.ai/v2beta/image-to-video",
                                    headers={"authorization": f"Bearer {STABLE_DIFF_API_KEY}"},
                                    files={"image": open(imgNameWithPath, "rb")},
                                    data={"seed": 0,"cfg_scale": 1.8,"motion_bucket_id": 127},
                                    )
            
            print('First Pass Response:')
            print(str(response.text))
            
            genID = response.json().get('id')

            return genID 
        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return 'N/A'

    def image2VideoPassTwo(self, genId):
        try:
            generation_id = genId
            STABLE_DIFF_API_KEY = self.STABLE_DIFF_API_KEY
            fullVideoFileName = self.OUT_DIR_PATH + self.VID_FILE_NM

            response = requests.request("GET", f"https://api.stability.ai/v2beta/image-to-video/result/{generation_id}",
                                        headers={
                                            'accept': "video/*",  # Use 'application/json' to receive base64 encoded JSON
                                            'authorization': f"Bearer {STABLE_DIFF_API_KEY}"
                                            },) 
            
            print('Retrieve Status Code: ', str(response.status_code))
            
            if response.status_code == 202:
                print("Generation in-progress, try again in 10 seconds.")

                return 5
            elif response.status_code == 200:
                print("Generation complete!")
                with open(fullVideoFileName, 'wb') as file:
                    file.write(response.content)

                print("Successfully Retrieved the video file!")

                return 0
            else:
                raise Exception(str(response.json()))
            
        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return 1

Now, let us understand the code –

This function is called when an object of the class is created. It initializes four properties:

  • STABLE_DIFF_API_KEY: the API key for Stability AI services.
  • OUT_DIR_PATH: the folder path to save files.
  • FILE_NM: the name of the generated image file.
  • VID_FILE_NM: the name of the generated video file.

This function deletes a file specified by fileName.

  • If successful, it returns 0.
  • If an error occurs, it logs the error and returns 1.

This function generates an image based on a text description:

  • Sends a request to the Stability AI text-to-image endpoint using the API key.
  • Saves the resulting image to a file.
  • Returns the file’s path on success or 'N/A' if an error occurs.

This function uploads an image to create a video in its first phase:

  • Sends the image to Stability AI’s image-to-video endpoint.
  • Logs the response and extracts the id (generation ID) for the next phase.
  • Returns the id if successful or 'N/A' on failure.

This function retrieves the video created in the second phase using the genId:

  • Checks the video generation status from the Stability AI endpoint.
  • If complete, saves the video file and returns 0.
  • If still processing, returns 5.
  • Logs and returns 1 for any errors.

As you can see, the code is pretty simple to understand & we’ve taken all the necessary actions in case of any unforeseen network issues or even if the video is not ready after our job submission in the following lines of the main calling script (generateText2VideoAPI.py) –

waitTime = 10
time.sleep(waitTime)

# Failed case retry
retries = 1
success = False

try:
    while not success:
        try:
            z = r1.image2VideoPassTwo(gID)
        except Exception as e:
            success = False

        if z == 0:
            success = True
        else:
            wait = retries * 2 * 15
            str_R1 = "retries Fail! Waiting " + str(wait) + " seconds and retrying!"

            print(str_R1)

            time.sleep(wait)
            retries += 1

        # Checking maximum retries
        if retries >= maxRetryNo:
            success = True
            raise  Exception
except:
    print()

And, let us see how the run looks like –

Let us understand the CPU utilization –

As you can see, CPU utilization is minimal since most tasks are at the API end.


So, we’ve done it. 🙂

Please find the next series on this topic below:

Enabling & Exploring Stable Defussion – Part 2

Enabling & Exploring Stable Defussion – Part 3

Please let me know your feedback after reviewing all the posts! 🙂

RAG implementation of LLMs by using Python, Haystack & React (Part – 2)

Today, we’ll share the second installment of the RAG implementation. If you are new here, please visit the previous post for full context.

In this post, we’ll be discussing the Haystack framework more. Again, before discussing the main context, I want to present the demo here.

Demo

Let us look at the flow diagram as it captures the sequence of events that unfold as part of the process, where today, we’ll pay our primary attention.

As you can see today, we’ll discuss the red dotted line, which contextualizes the source data into the Vector DBs.

Let us understand the flow of events here –

  1. The main Python application will consume the nested JSON by invoking the museum API in multiple threads.
  2. The application will clean the nested data & extract the relevant attributes after flattening the JSON.
  3. It will create the unstructured text-based context, which is later fed to the Vector DB framework.

pip install farm-haystack==1.19.0
pip install Flask==2.2.5
pip install Flask-Cors==4.0.0
pip install Flask-JWT-Extended==4.5.2
pip install Flask-Session==0.5.0
pip install openai==0.27.8
pip install pandas==2.0.3
pip install tensorflow==2.11.1

We’re using the Metropolitan Museum API to feed the data to our Vector DB. For more information, please visit the following link. And this is free to use & moreover, we’re using it for education scenarios.


We’ll discuss the tokenization part highlighted in a red dotted line from the above picture.

We’ll discuss the scripts in the diagram as part of the flow mentioned above.

  • clsExtractJSON.py (This is the main class that will extract the content from the museum API using parallel calls.)
def genData(self):
    try:
        base_url = self.base_url
        header_token = self.header_token
        basePath = self.basePath
        outputPath = self.outputPath
        mergedFile = self.mergedFile
        subdir = self.subdir
        Ind = self.Ind
        var_1 = datetime.now().strftime("%H.%M.%S")


        devVal = list()
        objVal = list()

        # Main Details
        headers = {'Cookie':header_token}
        payload={}

        url = base_url + '/departments'

        date_ranges = self.generateFirstDayOfLastTenYears()

        # Getting all the departments
        try:
            print('Department URL:')
            print(str(url))

            response = requests.request("GET", url, headers=headers, data=payload)
            parsed_data = json.loads(response.text)

            print('Department JSON:')
            print(str(parsed_data))

            # Extract the "departmentId" values into a Python list
            for dept_det in parsed_data['departments']:
                for info in dept_det:
                    if info == 'departmentId':
                        devVal.append(dept_det[info])

        except Exception as e:
            x = str(e)
            print('Error: ', x)
            devVal = list()

        # List to hold thread objects
        threads = []

        # Calling the Data using threads
        for dep in devVal:
            t = threading.Thread(target=self.getDataThread, args=(dep, base_url, headers, payload, date_ranges, objVal, subdir, Ind,))
            threads.append(t)
            t.start()

        # Wait for all threads to complete
        for t in threads:
            t.join()

        res = self.mergeCsvFilesInDirectory(basePath, outputPath, mergedFile)

        if res == 0:
            print('Successful!')
        else:
            print('Failure!')

        return 0

    except Exception as e:
        x = str(e)
        print('Error: ', x)

        return 1

The above code translates into the following steps –

  1. The above method first calls the generateFirstDayOfLastTenYears() plan to populate records for every department after getting all the unique departments by calling another API.
  2. Then, it will call the getDataThread() methods to fetch all the relevant APIs simultaneously to reduce the overall wait time & create individual smaller files.
  3. Finally, the application will invoke the mergeCsvFilesInDirectory() method to merge all the chunk files into one extensive historical data.
def generateFirstDayOfLastTenYears(self):
    yearRange = self.yearRange
    date_format = "%Y-%m-%d"
    current_year = datetime.now().year

    date_ranges = []
    for year in range(current_year - yearRange, current_year + 1):
        first_day_of_year_full = datetime(year, 1, 1)
        first_day_of_year = first_day_of_year_full.strftime(date_format)
        date_ranges.append(first_day_of_year)

    return date_ranges

The first method will generate the first day of each year for the last ten years, including the current year.

def getDataThread(self, dep, base_url, headers, payload, date_ranges, objVal, subdir, Ind):
    try:
        cnt = 0
        cnt_x = 1
        var_1 = datetime.now().strftime("%H.%M.%S")

        for x_start_date in date_ranges:
            try:
                urlM = base_url + '/objects?metadataDate=' + str(x_start_date) + '&departmentIds=' + str(dep)

                print('Nested URL:')
                print(str(urlM))

                response_obj = requests.request("GET", urlM, headers=headers, data=payload)
                objectDets = json.loads(response_obj.text)

                for obj_det in objectDets['objectIDs']:
                    objVal.append(obj_det)

                for objId in objVal:
                    urlS = base_url + '/objects/' + str(objId)

                    print('Final URL:')
                    print(str(urlS))

                    response_det = requests.request("GET", urlS, headers=headers, data=payload)
                    objDetJSON = response_det.text

                    retDB = self.createData(objDetJSON)
                    retDB['departmentId'] = str(dep)

                    if cnt == 0:
                        df_M = retDB
                    else:
                        d_frames = [df_M, retDB]
                        df_M = pd.concat(d_frames)

                    if cnt == 1000:
                        cnt = 0
                        clog.logr('df_M_' + var_1 + '_' + str(cnt_x) + '_' + str(dep) +'.csv', Ind, df_M, subdir)
                        cnt_x += 1
                        df_M = pd.DataFrame()

                    cnt += 1

            except Exception as e:
                x = str(e)
                print('Error X:', x)
        return 0

    except Exception as e:
        x = str(e)
        print('Error: ', x)

        return 1

The above method will invoke the individual API call to fetch the relevant artifact information.

def mergeCsvFilesInDirectory(self, directory_path, output_path, output_file):
    try:
        csv_files = [file for file in os.listdir(directory_path) if file.endswith('.csv')]
        data_frames = []

        for file in csv_files:
            encodings_to_try = ['utf-8', 'utf-8-sig', 'latin-1', 'cp1252']
            for encoding in encodings_to_try:
                try:
                    FullFileName = directory_path + file
                    print('File Name: ', FullFileName)
                    df = pd.read_csv(FullFileName, encoding=encoding)
                    data_frames.append(df)
                    break  # Stop trying other encodings if the reading is successful
                except UnicodeDecodeError:
                    continue

        if not data_frames:
            raise Exception("Unable to read CSV files. Check encoding or file format.")

        merged_df = pd.concat(data_frames, ignore_index=True)

        merged_full_name = os.path.join(output_path, output_file)
        merged_df.to_csv(merged_full_name, index=False)

        for file in csv_files:
            os.remove(os.path.join(directory_path, file))

        return 0

    except Exception as e:
        x = str(e)
        print('Error: ', x)
        return 1

The above method will merge all the small files into a single, more extensive historical data that contains over ten years of data (the first day of ten years of data, to be precise).

For the complete code, please visit the GitHub.

  • 1_ReadMuseumJSON.py (This is the main class that will invoke the class, which will extract the content from the museum API using parallel calls.)
#########################################################
#### Written By: SATYAKI DE                          ####
#### Written On: 27-Jun-2023                         ####
#### Modified On 28-Jun-2023                         ####
####                                                 ####
#### Objective: This is the main calling             ####
#### python script that will invoke the              ####
#### shortcut application created inside MAC         ####
#### enviornment including MacBook, IPad or IPhone.  ####
####                                                 ####
#########################################################
import datetime
from clsConfigClient import clsConfigClient as cf

import clsExtractJSON as cej

########################################################
################    Global Area   ######################
########################################################

cJSON = cej.clsExtractJSON()

basePath = cf.conf['DATA_PATH']
outputPath = cf.conf['OUTPUT_PATH']
mergedFile = cf.conf['MERGED_FILE']

########################################################
################  End Of Global Area   #################
########################################################

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

def main():
    try:
        var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        print('*'*120)
        print('Start Time: ' + str(var))
        print('*'*120)

        r1 = cJSON.genData()

        if r1 == 0:
            print()
            print('Successfully Scrapped!')
        else:
            print()
            print('Failed to Scrappe!')

        print('*'*120)
        var1 = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        print('End Time: ' + str(var1))

    except Exception as e:
        x = str(e)
        print('Error: ', x)

if __name__ == '__main__':
    main()

The above script calls the main class after instantiating the class.

  • clsCreateList.py (This is the main class that will extract the relevant attributes from the historical files & then create the right input text to create the documents for contextualize into the Vector DB framework.)
def createRec(self):
    try:
        basePath = self.basePath
        fileName = self.fileName
        Ind = self.Ind
        subdir = self.subdir
        base_url = self.base_url
        outputPath = self.outputPath
        mergedFile = self.mergedFile
        cleanedFile = self.cleanedFile

        FullFileName = outputPath + mergedFile

        df = pd.read_csv(FullFileName)
        df2 = df[listCol]
        dfFin = df2.drop_duplicates().reset_index(drop=True)

        dfFin['artist_URL'] = dfFin['artistWikidata_URL'].combine_first(dfFin['artistULAN_URL'])
        dfFin['object_URL'] = dfFin['objectURL'].combine_first(dfFin['objectWikidata_URL'])
        dfFin['Wiki_URL'] = dfFin['Wikidata_URL'].combine_first(dfFin['AAT_URL']).combine_first(dfFin['URL']).combine_first(dfFin['object_URL'])

        # Dropping the old Dtype Columns
        dfFin.drop(['artistWikidata_URL'], axis=1, inplace=True)
        dfFin.drop(['artistULAN_URL'], axis=1, inplace=True)
        dfFin.drop(['objectURL'], axis=1, inplace=True)
        dfFin.drop(['objectWikidata_URL'], axis=1, inplace=True)
        dfFin.drop(['AAT_URL'], axis=1, inplace=True)
        dfFin.drop(['Wikidata_URL'], axis=1, inplace=True)
        dfFin.drop(['URL'], axis=1, inplace=True)

        # Save the filtered DataFrame to a new CSV file
        #clog.logr(cleanedFile, Ind, dfFin, subdir)
        res = self.addHash(dfFin)

        if res == 0:
            print('Added Hash!')
        else:
            print('Failed to add hash!')

        # Generate the text for each row in the dataframe
        for _, row in dfFin.iterrows():
            x = self.genPrompt(row)
            self.addDocument(x, cleanedFile)

        return documents

    except Exception as e:
        x = str(e)
        print('Record Error: ', x)

        return documents

The above code will read the data from the extensive historical file created from the earlier steps & then it will clean the file by removing all the duplicate records (if any) & finally, it will create three unique URLs that constitute artist, object & wiki.

Also, this application will remove the hyperlink with a specific hash value, which will feed into the vector DB. Vector DB could be better with the URLs. Hence, we will store the URLs in a separate file by storing the associate hash value & later, we’ll fetch it in a lookup from the open AI response.

Then, this application will generate prompts dynamically & finally create the documents for later steps of vector DB consumption by invoking the addDocument() methods.

For more details, please visit the GitHub link.

  • 1_1_testCreateRec.py (This is the main class that will call the above class.)
#########################################################
#### Written By: SATYAKI DE                          ####
#### Written On: 27-Jun-2023                         ####
#### Modified On 28-Jun-2023                         ####
####                                                 ####
#### Objective: This is the main calling             ####
#### python script that will invoke the              ####
#### shortcut application created inside MAC         ####
#### enviornment including MacBook, IPad or IPhone.  ####
####                                                 ####
#########################################################

from clsConfigClient import clsConfigClient as cf
import clsL as log
import clsCreateList as ccl

from datetime import datetime, timedelta

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

###############################################
###           Global Section                ###
###############################################

#Initiating Logging Instances
clog = log.clsL()
cl = ccl.clsCreateList()

var = datetime.now().strftime(".%H.%M.%S")

documents = []

###############################################
###    End of Global Section                ###
###############################################
def main():
    try:
        var = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        print('*'*120)
        print('Start Time: ' + str(var))
        print('*'*120)

        print('*'*240)
        print('Creating Index store:: ')
        print('*'*240)

        documents = cl.createRec()

        print('Inserted Sample Records: ')
        print(str(documents))
        print('\n')

        r1 = len(documents)

        if r1 > 0:
            print()
            print('Successfully Indexed sample records!')
        else:
            print()
            print('Failed to sample Indexed recrods!')

        print('*'*120)
        var1 = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        print('End Time: ' + str(var1))

    except Exception as e:
        x = str(e)
        print('Error: ', x)

if __name__ == '__main__':
    main()

The above script invokes the main class after instantiating it & invokes the createRec() methods to tokenize the data into the vector DB.

This above test script will be used to test the above clsCreateList class. However, the class will be used inside another class.

– Satyaki
  • clsFeedVectorDB.py (This is the main class that will feed the documents into the vector DB.)
#########################################################
#### Written By: SATYAKI DE                          ####
#### Written On: 27-Jun-2023                         ####
#### Modified On 28-Sep-2023                         ####
####                                                 ####
#### Objective: This is the main calling             ####
#### python script that will invoke the              ####
#### haystack frameowrk to contextulioze the docs    ####
#### inside the vector DB.                           ####
####                                                 ####
#########################################################

from haystack.document_stores.faiss import FAISSDocumentStore
from haystack.nodes import DensePassageRetriever
import openai
import pandas as pd
import os
import clsCreateList as ccl

from clsConfigClient import clsConfigClient as cf
import clsL as log

from datetime import datetime, timedelta

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

###############################################
###           Global Section                ###
###############################################

Ind = cf.conf['DEBUG_IND']
openAIKey = cf.conf['OPEN_AI_KEY']

os.environ["TOKENIZERS_PARALLELISM"] = "false"

#Initiating Logging Instances
clog = log.clsL()
cl = ccl.clsCreateList()

var = datetime.now().strftime(".%H.%M.%S")

# Encode your data to create embeddings
documents = []

var_1 = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
print('*'*120)
print('Start Time: ' + str(var_1))
print('*'*120)

print('*'*240)
print('Creating Index store:: ')
print('*'*240)

documents = cl.createRec()

print('Inserted Sample Records: ')
print(documents[:5])
print('\n')
print('Type:')
print(type(documents))

r1 = len(documents)

if r1 > 0:
    print()
    print('Successfully Indexed records!')
else:
    print()
    print('Failed to Indexed recrods!')

print('*'*120)
var_2 = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
print('End Time: ' + str(var_2))

# Passing OpenAI API Key
openai.api_key = openAIKey

###############################################
###    End of Global Section                ###
###############################################

class clsFeedVectorDB:
    def __init__(self):
        self.basePath = cf.conf['DATA_PATH']
        self.modelFileName = cf.conf['CACHE_FILE']
        self.vectorDBPath = cf.conf['VECTORDB_PATH']
        self.vectorDBFileName = cf.conf['VECTORDB_FILE_NM']
        self.queryModel = cf.conf['QUERY_MODEL']
        self.passageModel = cf.conf['PASSAGE_MODEL']

    def retrieveDocuments(self, question, retriever, top_k=3):
        return retriever.retrieve(question, top_k=top_k)

    def generateAnswerWithGPT3(self, retrievedDocs, question):
        documents_text = " ".join([doc.content for doc in retrievedDocs])
        prompt = f"Given the following documents: {documents_text}, answer the question: {question}"

        response = openai.Completion.create(
            model="text-davinci-003",
            prompt=prompt,
            max_tokens=150
        )
        return response.choices[0].text.strip()

    def ragAnswerWithHaystackAndGPT3(self, question, retriever):
        retrievedDocs = self.retrieveDocuments(question, retriever)
        return self.generateAnswerWithGPT3(retrievedDocs, question)

    def genData(self, strVal):
        try:
            basePath = self.basePath
            modelFileName = self.modelFileName
            vectorDBPath = self.vectorDBPath
            vectorDBFileName = self.vectorDBFileName
            queryModel = self.queryModel
            passageModel = self.passageModel

            print('*'*120)
            print('Index Your Data for Retrieval:')
            print('*'*120)

            FullFileName = basePath + modelFileName
            FullVectorDBname = vectorDBPath + vectorDBFileName

            sqlite_path = "sqlite:///" + FullVectorDBname + '.db'
            print('Vector DB Path: ', str(sqlite_path))

            indexFile = "vectorDB/" + str(vectorDBFileName) + '.faiss'
            indexConfig = "vectorDB/" + str(vectorDBFileName) + ".json"

            print('File: ', str(indexFile))
            print('Config: ', str(indexConfig))

            # Initialize DocumentStore
            document_store = FAISSDocumentStore(sql_url=sqlite_path)

            libName = "vectorDB/" + str(vectorDBFileName) + '.faiss'

            document_store.write_documents(documents)

            # Initialize Retriever
            retriever = DensePassageRetriever(document_store=document_store,
                                              query_embedding_model=queryModel,
                                              passage_embedding_model=passageModel,
                                              use_gpu=False)

            document_store.update_embeddings(retriever=retriever)

            document_store.save(index_path=libName, config_path="vectorDB/" + str(vectorDBFileName) + ".json")

            print('*'*120)
            print('Testing with RAG & OpenAI...')
            print('*'*120)

            answer = self.ragAnswerWithHaystackAndGPT3(strVal, retriever)

            print('*'*120)
            print('Testing Answer:: ')
            print(answer)
            print('*'*120)

            return 0

        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return 1

In the above script, the following essential steps took place –

  1. First, the application calls the clsCreateList class to store all the documents inside a dictionary.
  2. Then it stores the data inside the vector DB & creates & stores the model, which will be later reused (If you remember, we’ve used this as a model in our previous post).
  3. Finally, test with some sample use cases by providing the proper context to OpenAI & confirm the response.

Here is a short clip of how the RAG models contextualize with the source data.

RAG-Model Contextualization

So, finally, we’ve done it.

I know that this post is relatively bigger than my earlier post. But, I think, you can get all the details once you go through it.

You will get the complete codebase in the following GitHub link.

I’ll bring some more exciting topics in the coming days from the Python verse. Please share & subscribe to my post & let me know your feedback.

Till then, Happy Avenging! 🙂

RAG implementation of LLMs by using Python, Haystack & React (Part – 1)

Today, I will share a new post in a part series about creating end-end LLMs that feed source data with RAG implementation. I’ll also use OpenAI python-based SDK and Haystack embeddings in this case.

In this post, I’ve directly subscribed to OpenAI & I’m not using OpenAI from Azure. However, I’ll explore that in the future as well.

Before I explain the process to invoke this new library, why not view the demo first & then discuss it?

Demo

Let us look at the flow diagram as it captures the sequence of events that unfold as part of the process.

As you can see, to enable this large & complex solution, we must first establish the capabilities to build applications powered by LLMs, Transformer models, vector search, and more. You can use state-of-the-art NLP models to perform question-answering, answer generation, semantic document search, or build tools capable of complex decision-making and query resolution. Hence, steps no. 1 & 2 showcased the data embedding & creating that informed repository. We’ll be discussing that in our second part.

Once you have the informed repository, the system can interact with the end-users. As part of the query (shown in step 3), the prompt & the question are shared with the process engine, which then turned to reduce the volume & get relevant context from our informed repository & get the tuned context as part of the response (Shown in steps 4, 5 & 6).

Then, this tuned context is shared with the OpenAI for better response & summary & concluding remarks that are very user-friendly & easier to understand for end-users (Shown in steps 8 & 9).

The following are the important packages that are essential to this project –

pip install farm-haystack==1.19.0
pip install Flask==2.2.5
pip install Flask-Cors==4.0.0
pip install Flask-JWT-Extended==4.5.2
pip install Flask-Session==0.5.0
pip install openai==0.27.8
pip install pandas==2.0.3
pip install tensorflow==2.11.1

We’ve both the front-end using react & back-end APIs with Python-flask and the Open AI to create this experience.

Today, we’ll be going in reverse mode. We first discuss the main script & then explain all the other class scripts.

  • flaskServer.py (This is the main calling Python script to invoke the RAG-Server.)
#########################################################
#### Written By: SATYAKI DE                          ####
#### Written On: 27-Jun-2023                         ####
#### Modified On 28-Jun-2023                         ####
####                                                 ####
#### Objective: This is the main calling             ####
#### python script that will invoke the              ####
#### shortcut application created inside MAC         ####
#### enviornment including MacBook, IPad or IPhone.  ####
####                                                 ####
#########################################################

from flask import Flask, jsonify, request, session
from flask_cors import CORS
from werkzeug.security import check_password_hash, generate_password_hash
from flask_jwt_extended import JWTManager, jwt_required, create_access_token
import pandas as pd
from clsConfigClient import clsConfigClient as cf
import clsL as log
import clsContentScrapper as csc
import clsRAGOpenAI as crao
import csv
from datetime import timedelta
import os
import re
import json

########################################################
################    Global Area   ######################
########################################################
#Initiating Logging Instances
clog = log.clsL()

admin_key = cf.conf['ADMIN_KEY']
secret_key = cf.conf['SECRET_KEY']
session_path = cf.conf['SESSION_PATH']
sessionFile = cf.conf['SESSION_CACHE_FILE']

app = Flask(__name__)
CORS(app)  # This will enable CORS for all routes
app.config['JWT_SECRET_KEY'] = admin_key  # Change this!
app.secret_key = secret_key

jwt = JWTManager(app)

users = cf.conf['USER_NM']
passwd = cf.conf['USER_PWD']

cCScrapper = csc.clsContentScrapper()
cr = crao.clsRAGOpenAI()

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

# Define the aggregation functions
def join_unique(series):
    unique_vals = series.drop_duplicates().astype(str)
    return ', '.join(filter(lambda x: x != 'nan', unique_vals))

# Building the preaggregate cache
def groupImageWiki():
    try:
        base_path = cf.conf['OUTPUT_PATH']
        inputFile = cf.conf['CLEANED_FILE']
        outputFile = cf.conf['CLEANED_FILE_SHORT']
        subdir = cf.conf['SUBDIR_OUT']
        Ind = cf.conf['DEBUG_IND']

        inputCleanedFileLookUp = base_path + inputFile

        #Opening the file in dataframe
        df = pd.read_csv(inputCleanedFileLookUp)
        hash_values = df['Total_Hash'].unique()

        dFin = df[['primaryImage','Wiki_URL','Total_Hash']]

        # Ensure columns are strings and not NaN
        # Convert columns to string and replace 'nan' with an empty string
        dFin['primaryImage'] = dFin['primaryImage'].astype(str).replace('nan', '')
        dFin['Wiki_URL'] = dFin['Wiki_URL'].astype(str).replace('nan', '')

        dFin.drop_duplicates()

        # Group by 'Total_Hash' and aggregate
        dfAgg = dFin.groupby('Total_Hash').agg({'primaryImage': join_unique,'Wiki_URL': join_unique}).reset_index()

        return dfAgg

    except Exception as e:
        x = str(e)
        print('Error: ', x)

        df = pd.DataFrame()

        return df

resDf = groupImageWiki()

########################################################
################  End  Global Area  ####################
########################################################

def extractRemoveUrls(hash_value):
    image_urls = ''
    wiki_urls = ''
    # Parse the inner message JSON string
    try:

        resDf['Total_Hash'] = resDf['Total_Hash'].astype(int)
        filtered_df = resDf[resDf['Total_Hash'] == int(hash_value)]

        if not filtered_df.empty:
            image_urls = filtered_df['primaryImage'].values[0]
            wiki_urls = filtered_df['Wiki_URL'].values[0]

        return image_urls, wiki_urls

    except Exception as e:
        x = str(e)
        print('extractRemoveUrls Error: ', x)
        return image_urls, wiki_urls

def isIncomplete(line):
    """Check if a line appears to be incomplete."""

    # Check if the line ends with certain patterns indicating it might be incomplete.
    incomplete_patterns = [': [Link](', ': Approximately ', ': ']
    return any(line.endswith(pattern) for pattern in incomplete_patterns)

def filterData(data):
    """Return only the complete lines from the data."""

    lines = data.split('\n')
    complete_lines = [line for line in lines if not isIncomplete(line)]

    return '\n'.join(complete_lines)

def updateCounter(sessionFile):
    try:
        counter = 0

        # Check if the CSV file exists
        if os.path.exists(sessionFile):
            with open(sessionFile, 'r') as f:
                reader = csv.reader(f)
                for row in reader:
                    # Assuming the counter is the first value in the CSV
                    counter = int(row[0])

        # Increment counter
        counter += 1

        # Write counter back to CSV
        with open(sessionFile, 'w', newline='') as f:
            writer = csv.writer(f)
            writer.writerow([counter])

        return counter
    except Exception as e:
        x = str(e)
        print('Error: ', x)

        return 1

def getPreviousResult():
    try:
        fullFileName = session_path + sessionFile
        newCounterValue = updateCounter(fullFileName)

        return newCounterValue
    except Exception as e:
        x = str(e)
        print('Error: ', x)

        return 1

@app.route('/login', methods=['POST'])
def login():
    username = request.json.get('username', None)
    password = request.json.get('password', None)

    print('User Name: ', str(username))
    print('Password: ', str(password))

    #if username not in users or not check_password_hash(users.get(username), password):
    if ((username not in users) or (password not in passwd)):
        return jsonify({'login': False}), 401

    access_token = create_access_token(identity=username)
    return jsonify(access_token=access_token)

@app.route('/chat', methods=['POST'])
def get_chat():
    try:
        #session["key"] = "1D98KI"
        #session_id = session.sid
        #print('Session Id: ', str(session_id))

        cnt = getPreviousResult()
        print('Running Session Count: ', str(cnt))

        username = request.json.get('username', None)
        message = request.json.get('message', None)

        print('User: ', str(username))
        print('Content: ', str(message))

        if cnt == 1:
            retList = cCScrapper.extractCatalog()
        else:
            hashValue, cleanedData = cr.getData(str(message))
            print('Main Hash Value:', str(hashValue))

            imageUrls, wikiUrls = extractRemoveUrls(hashValue)
            print('Image URLs: ', str(imageUrls))
            print('Wiki URLs: ', str(wikiUrls))
            print('Clean Text:')
            print(str(cleanedData))
            retList = '{"records":[{"Id":"' + str(cleanedData) + '", "Image":"' + str(imageUrls) + '", "Wiki": "' + str(wikiUrls) + '"}]}'

        response = {
            'message': retList
        }

        print('JSON: ', str(response))
        return jsonify(response)

    except Exception as e:
        x = str(e)

        response = {
            'message': 'Error: ' + x
        }
        return jsonify(response)

@app.route('/api/data', methods=['GET'])
@jwt_required()
def get_data():
    response = {
        'message': 'Hello from Flask!'
    }
    return jsonify(response)

if __name__ == '__main__':
    app.run(debug=True)

Let us understand some of the important sections of the above script –

Function – login():

The login function retrieves a ‘username’ and ‘password’ from a JSON request and prints them. It checks if the provided credentials are missing from users or password lists, returning a failure JSON response if so. It creates and returns an access token in a JSON response if valid.

Function – get_chat():

The get_chat function retrieves the running session count and user input from a JSON request. Based on the session count, it extracts catalog data or processes the user’s message from the RAG framework that finally receives the refined response from the OpenAI, extracting hash values, image URLs, and wiki URLs. If an error arises, the function captures and returns the error as a JSON message.

Function – updateCounter():

The updateCounter function checks if a given CSV file exists and retrieves its counter value. It then increments the counter and writes it back to the CSV. If any errors occur, an error message is printed, and the function returns a value of 1.

Function – extractRemoveUrls():

The extractRemoveUrls function attempts to filter a data frame, resDf, based on a provided hash value to extract image and wiki URLs. If the data frame contains matching entries, it retrieves the corresponding URLs. Any errors encountered are printed, but the function always returns the image and wiki URLs, even if they are empty.

  • clsContentScrapper.py (This is the main class that brings the default options for the users if they agree with the initial prompt by the bot.)
#####################################################
#### Written By: SATYAKI DE                      ####
#### Written On: 27-May-2023                     ####
#### Modified On 28-May-2023                     ####
####                                             ####
#### Objective: This is the main calling         ####
#### python class that will invoke the           ####
#### LangChain of package to extract             ####
#### the transcript from the YouTube videos &    ####
#### then answer the questions based on the      ####
#### topics selected by the users.               ####
####                                             ####
#####################################################

from langchain.document_loaders import YoutubeLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.chains import LLMChain

from langchain.prompts.chat import (
    ChatPromptTemplate,
    SystemMessagePromptTemplate,
    HumanMessagePromptTemplate,
)

from googleapiclient.discovery import build

import clsTemplate as ct
from clsConfigClient import clsConfigClient as cf

import os

from flask import jsonify
import requests

###############################################
###           Global Section                ###
###############################################
open_ai_Key = cf.conf['OPEN_AI_KEY']
os.environ["OPENAI_API_KEY"] = open_ai_Key
embeddings = OpenAIEmbeddings(openai_api_key=open_ai_Key)

YouTube_Key = cf.conf['YOUTUBE_KEY']
youtube = build('youtube', 'v3', developerKey=YouTube_Key)

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

###############################################
###    End of Global Section                ###
###############################################

class clsContentScrapper:
    def __init__(self):
        self.model_name = cf.conf['MODEL_NAME']
        self.temp_val = cf.conf['TEMP_VAL']
        self.max_cnt = int(cf.conf['MAX_CNT'])
        self.url = cf.conf['BASE_URL']
        self.header_token = cf.conf['HEADER_TOKEN']

    def extractCatalog(self):
        try:
            base_url = self.url
            header_token = self.header_token

            url = base_url + '/departments'

            print('Full URL: ', str(url))

            payload={}
            headers = {'Cookie': header_token}

            response = requests.request("GET", url, headers=headers, data=payload)

            x = response.text

            return x
        except Exception as e:
            discussedTopic = []
            x = str(e)
            print('Error: ', x)

            return x

Let us understand the the core part that require from this class.

Function – extractCatalog():

The extractCatalog function uses specific headers to make a GET request to a constructed URL. The URL is derived by appending ‘/departments’ to a base_url, and a header token is used in the request headers. If successful, it returns the text of the response; if there’s an exception, it prints the error and returns the error message.

  • clsRAGOpenAI.py (This is the main class that brings the RAG-enabled context that is fed to OpenAI for fine-tuned response with less cost.)
#########################################################
#### Written By: SATYAKI DE                          ####
#### Written On: 27-Jun-2023                         ####
#### Modified On 28-Jun-2023                         ####
####                                                 ####
#### Objective: This is the main calling             ####
#### python script that will invoke the              ####
#### shortcut application created inside MAC         ####
#### enviornment including MacBook, IPad or IPhone.  ####
####                                                 ####
#########################################################

from haystack.document_stores.faiss import FAISSDocumentStore
from haystack.nodes import DensePassageRetriever
import openai

from clsConfigClient import clsConfigClient as cf
import clsL as log

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

import os
import re
###############################################
###           Global Section                ###
###############################################
Ind = cf.conf['DEBUG_IND']
queryModel = cf.conf['QUERY_MODEL']
passageModel = cf.conf['PASSAGE_MODEL']

#Initiating Logging Instances
clog = log.clsL()

os.environ["TOKENIZERS_PARALLELISM"] = "false"

vectorDBFileName = cf.conf['VECTORDB_FILE_NM']

indexFile = "vectorDB/" + str(vectorDBFileName) + '.faiss'
indexConfig = "vectorDB/" + str(vectorDBFileName) + ".json"

print('File: ', str(indexFile))
print('Config: ', str(indexConfig))

# Also, provide `config_path` parameter if you set it when calling the `save()` method:
new_document_store = FAISSDocumentStore.load(index_path=indexFile, config_path=indexConfig)

# Initialize Retriever
retriever = DensePassageRetriever(document_store=new_document_store,
                                  query_embedding_model=queryModel,
                                  passage_embedding_model=passageModel,
                                  use_gpu=False)


###############################################
###    End of Global Section                ###
###############################################

class clsRAGOpenAI:
    def __init__(self):
        self.basePath = cf.conf['DATA_PATH']
        self.fileName = cf.conf['FILE_NAME']
        self.Ind = cf.conf['DEBUG_IND']
        self.subdir = str(cf.conf['OUT_DIR'])
        self.base_url = cf.conf['BASE_URL']
        self.outputPath = cf.conf['OUTPUT_PATH']
        self.vectorDBPath = cf.conf['VECTORDB_PATH']
        self.openAIKey = cf.conf['OPEN_AI_KEY']
        self.temp = cf.conf['TEMP_VAL']
        self.modelName = cf.conf['MODEL_NAME']
        self.maxToken = cf.conf['MAX_TOKEN']

    def extractHash(self, text):
        try:
            # Regular expression pattern to match 'Ref: {' followed by a number and then '}'
            pattern = r"Ref: \{'(\d+)'\}"
            match = re.search(pattern, text)

            if match:
                return match.group(1)
            else:
                return None
        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return None

    def removeSentencesWithNaN(self, text):
        try:
            # Split text into sentences using regular expression
            sentences = re.split('(?<!\w\.\w.)(?<![A-Z][a-z]\.)(?<=\.|\?)\s', text)
            # Filter out sentences containing 'nan'
            filteredSentences = [sentence for sentence in sentences if 'nan' not in sentence]
            # Rejoin the sentences
            return ' '.join(filteredSentences)
        except Exception as e:
            x = str(e)
            print('Error: ', x)

            return ''

    def retrieveDocumentsReader(self, question, top_k=9):
        return retriever.retrieve(question, top_k=top_k)

    def generateAnswerWithGPT3(self, retrieved_docs, question):
        try:
            openai.api_key = self.openAIKey
            temp = self.temp
            modelName = self.modelName
            maxToken = self.maxToken

            documentsText = " ".join([doc.content for doc in retrieved_docs])

            filteredDocs = self.removeSentencesWithNaN(documentsText)
            hashValue = self.extractHash(filteredDocs)

            print('RAG Docs:: ')
            print(filteredDocs)
            #prompt = f"Given the following documents: {documentsText}, answer the question accurately based on the above data with the supplied http urls: {question}"

            # Set up a chat-style prompt with your data
            messages = [
                {"role": "system", "content": "You are a helpful assistant, answer the question accurately based on the above data with the supplied http urls. Only relevant content needs to publish. Please do not provide the facts or the texts that results crossing the max_token limits."},
                {"role": "user", "content": filteredDocs}
            ]

            # Chat style invoking the latest model
            response = openai.ChatCompletion.create(
                model=modelName,
                messages=messages,
                temperature = temp,
                max_tokens=maxToken
            )
            return hashValue, response.choices[0].message['content'].strip().replace('\n','\\n')
        except Exception as e:
            x = str(e)
            print('failed to get from OpenAI: ', x)
            return 'Not Available!'

    def ragAnswerWithHaystackAndGPT3(self, question):
        retrievedDocs = self.retrieveDocumentsReader(question)
        return self.generateAnswerWithGPT3(retrievedDocs, question)

    def getData(self, strVal):
        try:
            print('*'*120)
            print('Index Your Data for Retrieval:')
            print('*'*120)

            print('Response from New Docs: ')
            print()

            hashValue, answer = self.ragAnswerWithHaystackAndGPT3(strVal)

            print('GPT3 Answer::')
            print(answer)
            print('Hash Value:')
            print(str(hashValue))

            print('*'*240)
            print('End Of Use RAG to Generate Answers:')
            print('*'*240)

            return hashValue, answer
        except Exception as e:
            x = str(e)
            print('Error: ', x)
            answer = x
            hashValue = 1

            return hashValue, answer

Let us understand some of the important block –

Function – ragAnswerWithHaystackAndGPT3():

The ragAnswerWithHaystackAndGPT3 function retrieves relevant documents for a given question using the retrieveDocumentsReader method. It then generates an answer for the query using GPT-3 with the retrieved documents via the generateAnswerWithGPT3 method. The final response is returned.

Function – generateAnswerWithGPT3():

The generateAnswerWithGPT3 function, given a list of retrieved documents and a question, communicates with OpenAI’s GPT-3 to generate an answer. It first processes the documents, filtering and extracting a hash value. Using a chat-style format, it prompts GPT-3 with the processed documents and captures its response. If an error occurs, an error message is printed, and “Not Available!” is returned.

Function – retrieveDocumentsReader():

The retrieveDocumentsReader function takes in a question and an optional parameter, top_k (defaulted to 9). It is called the retriever.retrieve method with the given parameters. The result of the retrieval will generate at max nine responses from the RAG engine, which will be fed to OpenAI.

  • App.js (This is the main react script, that will create the interface & parse the data apart from the authentication)
// App.js
import React, { useState } from 'react';
import axios from 'axios';
import './App.css';

const App = () => {
  const [isLoggedIn, setIsLoggedIn] = useState(false);
  const [username, setUsername] = useState('');
  const [password, setPassword] = useState('');
  const [message, setMessage] = useState('');
  const [chatLog, setChatLog] = useState([{ sender: 'MuBot', message: 'Welcome to MuBot! Please explore the world of History from our brilliant collections! Do you want to proceed to see the catalog?'}]);

  const handleLogin = async (e) => {
    e.preventDefault();
    try {
      const response = await axios.post('http://localhost:5000/login', { username, password });
      if (response.status === 200) {
        setIsLoggedIn(true);
      }
    } catch (error) {
      console.error('Login error:', error);
    }
  };

  const sendMessage = async (username) => {
    if (message.trim() === '') return;

    // Create a new chat entry
    const newChatEntry = {
      sender: 'user',
      message: message.trim(),
    };

    // Clear the input field
    setMessage('');

    try {
      // Make API request to Python-based API
      const response = await axios.post('http://localhost:5000/chat', { message: newChatEntry.message }); // Replace with your API endpoint URL
      const responseData = response.data;

      // Print the response to the console for debugging
      console.log('API Response:', responseData);

      // Parse the nested JSON from the 'message' attribute
      const jsonData = JSON.parse(responseData.message);

      // Check if the data contains 'departments'
      if (jsonData.departments) {

        // Extract the 'departments' attribute from the parsed data
        const departments = jsonData.departments;

        // Extract the department names and create a single string with line breaks
        const botResponseText = departments.reduce((acc, department) => {return acc + department.departmentId + ' ' + department.displayName + '\n';}, '');

        // Update the chat log with the bot's response
        setChatLog((prevChatLog) => [...prevChatLog, { sender: 'user', message: message }, { sender: 'bot', message: botResponseText },]);
      }
      else if (jsonData.records)
      {
        // Data structure 2: Artwork information
        const records = jsonData.records;

        // Prepare chat entries
        const chatEntries = [];

        // Iterate through records and extract text, image, and wiki information
        records.forEach((record) => {
          const textInfo = Object.entries(record).map(([key, value]) => {
            if (key !== 'Image' && key !== 'Wiki') {
              return `${key}: ${value}`;
            }
            return null;
          }).filter((info) => info !== null).join('\n');

          const imageLink = record.Image;
          //const wikiLinks = JSON.parse(record.Wiki.replace(/'/g, '"'));
          //const wikiLinks = record.Wiki;
          const wikiLinks = record.Wiki.split(',').map(link => link.trim());

          console.log('Wiki:', wikiLinks);

          // Check if there is a valid image link
          const hasValidImage = imageLink && imageLink !== '[]';

          const imageElement = hasValidImage ? (
            <img src={imageLink} alt="Artwork" style={{ maxWidth: '100%' }} />
          ) : null;

          // Create JSX elements for rendering the wiki links (if available)
          const wikiElements = wikiLinks.map((link, index) => (
            <div key={index}>
              <a href={link} target="_blank" rel="noopener noreferrer">
                Wiki Link {index + 1}
              </a>
            </div>
          ));

          if (textInfo) {
            chatEntries.push({ sender: 'bot', message: textInfo });
          }

          if (imageElement) {
            chatEntries.push({ sender: 'bot', message: imageElement });
          }

          if (wikiElements.length > 0) {
            chatEntries.push({ sender: 'bot', message: wikiElements });
          }
        });

        // Update the chat log with the bot's response
        setChatLog((prevChatLog) => [...prevChatLog, { sender: 'user', message }, ...chatEntries, ]);
      }

    } catch (error) {
      console.error('Error sending message:', error);
    }
  };

  if (!isLoggedIn) {
    return (
      <div className="login-container">
        <h2>Welcome to the MuBot</h2>
        <form onSubmit={handleLogin} className="login-form">
          <input
            type="text"
            placeholder="Enter your name"
            value={username}
            onChange={(e) => setUsername(e.target.value)}
            required
          />
          <input
            type="password"
            placeholder="Enter your password"
            value={password}
            onChange={(e) => setPassword(e.target.value)}
            required
          />
          <button type="submit">Login</button>
        </form>
      </div>
    );
  }

  return (
    <div className="chat-container">
      <div className="chat-header">
        <h2>Hello, {username}</h2>
        <h3>Chat with MuBot</h3>
      </div>
      <div className="chat-log">
        {chatLog.map((chatEntry, index) => (
          <div
            key={index}
            className={`chat-entry ${chatEntry.sender === 'user' ? 'user' : 'bot'}`}
          >
            <span className="user-name">{chatEntry.sender === 'user' ? username : 'MuBot'}</span>
            <p className="chat-message">{chatEntry.message}</p>
          </div>
        ))}
      </div>
      <div className="chat-input">
        <input
          type="text"
          placeholder="Type your message..."
          value={message}
          onChange={(e) => setMessage(e.target.value)}
          onKeyPress={(e) => {
            if (e.key === 'Enter') {
              sendMessage();
            }
          }}
        />
        <button onClick={sendMessage}>Send</button>
      </div>
    </div>
  );
};

export default App;

Please find some of the important logic –

Function – handleLogin():

The handleLogin asynchronous function responds to an event by preventing its default action. It attempts to post a login request with a username and password to a local server endpoint. If the response is successful with a status of 200, it updates a state variable to indicate a successful login; otherwise, it logs any encountered errors.

Function – sendMessage():

The sendMessage asynchronous function is designed to handle the user’s chat interaction:

  1. If the message is empty (after trimming spaces), the function exits without further action.
  2. A chat entry object is created with the sender set as ‘user’ and the trimmed message.
  3. The input field’s message is cleared, and an API request is made to a local server endpoint with the chat message.
  4. If the API responds with a ‘departments’ attribute in its JSON, a bot response is crafted by iterating over department details.
  5. If the API responds with ‘records’ indicating artwork information, the bot crafts responses for each record, extracting text, images, and wiki links, and generating JSX elements for rendering them.
  6. After processing the API response, the chat log state is updated with the user’s original message and the bot’s responses.
  7. Errors, if encountered, are logged to the console.

This function enables interactive chat with bot responses that vary based on the nature of the data received from the API.


Let us explore the directory structure starting from the parent to some of the important child folder should look like this –


So, finally, we’ve done it.

I know that this post is relatively bigger than my earlier post. But, I think, you can get all the details once you go through it.

You will get the complete codebase in the following GitHub link.

I’ll bring some more exciting topics in the coming days from the Python verse. Please share & subscribe to my post & let me know your feedback.

Till then, Happy Avenging! 🙂

Realtime reading from a Streaming using Computer Vision

This week we’re going to extend one of our earlier posts & trying to read an entire text from streaming using computer vision. If you want to view the previous post, please click the following link.

But, before we proceed, why don’t we view the demo first?

Demo

Architecture:

Let us understand the architecture flow –

Architecture flow

The above diagram shows that the application, which uses the Open-CV, analyzes individual frames from the source & extracts the complete text within the video & displays it on top of the target screen besides prints the same in the console.

Python Packages:

pip install imutils==0.5.4
pip install matplotlib==3.5.2
pip install numpy==1.21.6
pip install opencv-contrib-python==4.6.0.66
pip install opencv-contrib-python-headless==4.6.0.66
pip install opencv-python==4.6.0.66
pip install opencv-python-headless==4.6.0.66
pip install pandas==1.3.5
pip install Pillow==9.1.1
pip install pytesseract==0.3.9
pip install python-dateutil==2.8.2

CODE:

Let us now understand the code. For this use case, we will only discuss three python scripts. However, we need more than these three. However, we have already discussed them in some of the early posts. Hence, we will skip them here.

  • clsReadingTextFromStream.py (This is the main class of python script that will extract the text from the WebCAM streaming in real-time.)
##################################################
#### Written By: SATYAKI DE ####
#### Written On: 22-Jul-2022 ####
#### Modified On 25-Jul-2022 ####
#### ####
#### Objective: This is the main class of ####
#### python script that will invoke the ####
#### extraction of texts from a WebCAM. ####
#### ####
##################################################
# Importing necessary packages
from clsConfig import clsConfig as cf
from imutils.object_detection import non_max_suppression
import numpy as np
import pytesseract
import imutils
import time
import cv2
import time
###############################################
### Global Section ###
###############################################
# Two output layer names for the text detector model
lNames = cf.conf['LAYER_DET']
# Tesseract OCR text param values
strVal = "-l " + str(cf.conf['LANG']) + " --oem " + str(cf.conf['OEM_VAL']) + " --psm " + str(cf.conf['PSM_VAL']) + ""
config = (strVal)
###############################################
### End of Global Section ###
###############################################
class clsReadingTextFromStream:
def __init__(self):
self.sep = str(cf.conf['SEP'])
self.Curr_Path = str(cf.conf['INIT_PATH'])
self.CacheL = int(cf.conf['CACHE_LIM'])
self.modelPath = str(cf.conf['MODEL_PATH']) + str(cf.conf['MODEL_FILE_NAME'])
self.minConf = float(cf.conf['MIN_CONFIDENCE'])
self.wt = int(cf.conf['WIDTH'])
self.ht = int(cf.conf['HEIGHT'])
self.pad = float(cf.conf['PADDING'])
self.title = str(cf.conf['TITLE'])
self.Otitle = str(cf.conf['ORIG_TITLE'])
self.drawTag = cf.conf['DRAW_TAG']
self.aRange = int(cf.conf['ASCII_RANGE'])
self.sParam = cf.conf['SUBTRACT_PARAM']
def findBoundBox(self, boxes, res, rW, rH, orig, origW, origH, pad):
try:
# Loop over the bounding boxes
for (spX, spY, epX, epY) in boxes:
# Scale the bounding box coordinates based on the respective
# ratios
spX = int(spX * rW)
spY = int(spY * rH)
epX = int(epX * rW)
epY = int(epY * rH)
# To obtain a better OCR of the text we can potentially
# apply a bit of padding surrounding the bounding box.
# And, computing the deltas in both the x and y directions
dX = int((epX - spX) * pad)
dY = int((epY - spY) * pad)
# Apply padding to each side of the bounding box, respectively
spX = max(0, spX - dX)
spY = max(0, spY - dY)
epX = min(origW, epX + (dX * 2))
epY = min(origH, epY + (dY * 2))
# Extract the actual padded ROI
roi = orig[spY:epY, spX:epX]
# Choose the proper OCR Config
text = pytesseract.image_to_string(roi, config=config)
# Add the bounding box coordinates and OCR'd text to the list
# of results
res.append(((spX, spY, epX, epY), text))
# Sort the results bounding box coordinates from top to bottom
res = sorted(res, key=lambda r:r[0][1])
return res
except Exception as e:
x = str(e)
print(x)
return res
def predictText(self, imgScore, imgGeo):
try:
minConf = self.minConf
# Initializing the bounding box rectangles & confidence score by
# extracting the rows & columns from the imgScore volume.
(numRows, numCols) = imgScore.shape[2:4]
rects = []
confScore = []
for y in range(0, numRows):
# Extract the imgScore probabilities to derive potential
# bounding box coordinates that surround text
imgScoreData = imgScore[0, 0, y]
xVal0 = imgGeo[0, 0, y]
xVal1 = imgGeo[0, 1, y]
xVal2 = imgGeo[0, 2, y]
xVal3 = imgGeo[0, 3, y]
anglesData = imgGeo[0, 4, y]
for x in range(0, numCols):
# If our score does not have sufficient probability,
# ignore it
if imgScoreData[x] < minConf:
continue
# Compute the offset factor as our resulting feature
# maps will be 4x smaller than the input frame
(offX, offY) = (x * 4.0, y * 4.0)
# Extract the rotation angle for the prediction and
# then compute the sin and cosine
angle = anglesData[x]
cos = np.cos(angle)
sin = np.sin(angle)
# Derive the width and height of the bounding box from
# imgGeo
h = xVal0[x] + xVal2[x]
w = xVal1[x] + xVal3[x]
# Compute both the starting and ending (x, y)-coordinates
# for the text prediction bounding box
epX = int(offX + (cos * xVal1[x]) + (sin * xVal2[x]))
epY = int(offY - (sin * xVal1[x]) + (cos * xVal2[x]))
spX = int(epX - w)
spY = int(epY - h)
# Adding bounding box coordinates and probability score
# to the respective lists
rects.append((spX, spY, epX, epY))
confScore.append(imgScoreData[x])
# return a tuple of the bounding boxes and associated confScore
return (rects, confScore)
except Exception as e:
x = str(e)
print(x)
rects = []
confScore = []
return (rects, confScore)
def processStream(self, debugInd, var):
try:
sep = self.sep
Curr_Path = self.Curr_Path
CacheL = self.CacheL
modelPath = self.modelPath
minConf = self.minConf
wt = self.wt
ht = self.ht
pad = self.pad
title = self.title
Otitle = self.Otitle
drawTag = self.drawTag
aRange = self.aRange
sParam = self.sParam
val = 0
# Initialize the video stream and allow the camera sensor to warm up
print("[INFO] Starting video stream...")
cap = cv2.VideoCapture(0)
# Loading the pre-trained text detector
print("[INFO] Loading Text Detector...")
net = cv2.dnn.readNet(modelPath)
# Loop over the frames from the video stream
while True:
try:
# Grab the frame from our video stream and resize it
success, frame = cap.read()
orig = frame.copy()
(origH, origW) = frame.shape[:2]
# Setting new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (wt, ht)
rW = origW / float(newW)
rH = origH / float(newH)
# Resize the frame and grab the new frame dimensions
frame = cv2.resize(frame, (newW, newH))
(H, W) = frame.shape[:2]
# Construct a blob from the frame and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(frame, 1.0, (W, H), sParam, swapRB=True, crop=False)
net.setInput(blob)
(confScore, imgGeo) = net.forward(lNames)
# Decode the predictions, then apply non-maxima suppression to
# suppress weak, overlapping bounding boxes
(rects, confidences) = self.predictText(confScore, imgGeo)
boxes = non_max_suppression(np.array(rects), probs=confidences)
# Initialize the list of results
res = []
# Getting BoundingBox boundaries
res = self.findBoundBox(boxes, res, rW, rH, orig, origW, origH, pad)
for ((spX, spY, epX, epY), text) in res:
# Display the text OCR by using Tesseract APIs
print("Reading Text::")
print("=" *60)
print(text)
print("=" *60)
# Removing the non-ASCII text so it can draw the text on the frame
# using OpenCV, then draw the text and a bounding box surrounding
# the text region of the input frame
text = "".join([c if ord(c) < aRange else "" for c in text]).strip()
output = orig.copy()
cv2.rectangle(output, (spX, spY), (epX, epY), drawTag, 2)
cv2.putText(output, text, (spX, spY - 20), cv2.FONT_HERSHEY_SIMPLEX, 1.2, drawTag, 3)
# Show the output frame
cv2.imshow(title, output)
#cv2.imshow(Otitle, frame)
# If the `q` key was pressed, break from the loop
if cv2.waitKey(1) == ord('q'):
break
val = 0
except Exception as e:
x = str(e)
print(x)
val = 1
# Performing cleanup at the end
cap.release()
cv2.destroyAllWindows()
return val
except Exception as e:
x = str(e)
print('Error:', x)
return 1

Please find the key snippet from the above script –

# Two output layer names for the text detector model

lNames = cf.conf['LAYER_DET']

# Tesseract OCR text param values

strVal = "-l " + str(cf.conf['LANG']) + " --oem " + str(cf.conf['OEM_VAL']) + " --psm " + str(cf.conf['PSM_VAL']) + ""
config = (strVal)

The first line contains the two output layers’ names for the text detector model. Among them, the first one indicates the outcome possibilities & the second one use to derive the bounding box coordinates of the predicted text.

The second line contains various options for the tesseract APIs. You need to understand the opportunities in detail to make them work. These are the essential options for our use case –

  • Language – The intended language, for example, English, Spanish, Hindi, Bengali, etc.
  • OEM flag – In this case, the application will use 4 to indicate LSTM neural net model for OCR.
  • OEM Value – In this case, the selected value is 7, indicating that the application treats the ROI as a single line of text.

For more details, please refer to the config file.

print("[INFO] Loading Text Detector...")
net = cv2.dnn.readNet(modelPath)

The above lines bring the already created model & load it to memory for evaluation.

# Setting new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (wt, ht)
rW = origW / float(newW)
rH = origH / float(newH)

# Resize the frame and grab the new frame dimensions
frame = cv2.resize(frame, (newW, newH))
(H, W) = frame.shape[:2]

# Construct a blob from the frame and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(frame, 1.0, (W, H), sParam, swapRB=True, crop=False)
net.setInput(blob)
(confScore, imgGeo) = net.forward(lNames)

# Decode the predictions, then apply non-maxima suppression to
# suppress weak, overlapping bounding boxes
(rects, confidences) = self.predictText(confScore, imgGeo)
boxes = non_max_suppression(np.array(rects), probs=confidences)

The above lines are more of preparing individual frames to get the bounding box by resizing the height & width followed by a forward pass of the model to obtain two output layer sets. And then apply the non-maxima suppression to remove the weak, overlapping bounding box by interpreting the prediction. In short, this will identify the potential text region & put the bounding box surrounding it.

# Initialize the list of results
res = []

# Getting BoundingBox boundaries
res = self.findBoundBox(boxes, res, rW, rH, orig, origW, origH, pad)

The above function will create the bounding box surrounding the predicted text regions. Also, we will capture the expected text inside the result variable.

for (spX, spY, epX, epY) in boxes:
  # Scale the bounding box coordinates based on the respective
  # ratios
  spX = int(spX * rW)
  spY = int(spY * rH)
  epX = int(epX * rW)
  epY = int(epY * rH)

  # To obtain a better OCR of the text we can potentially
  # apply a bit of padding surrounding the bounding box.
  # And, computing the deltas in both the x and y directions
  dX = int((epX - spX) * pad)
  dY = int((epY - spY) * pad)

  # Apply padding to each side of the bounding box, respectively
  spX = max(0, spX - dX)
  spY = max(0, spY - dY)
  epX = min(origW, epX + (dX * 2))
  epY = min(origH, epY + (dY * 2))

  # Extract the actual padded ROI
  roi = orig[spY:epY, spX:epX]

Now, the application will scale the bounding boxes based on the previously computed ratio for actual text recognition. In this process, the application also padded the bounding boxes & then extracted the padded region of interest.

# Choose the proper OCR Config
text = pytesseract.image_to_string(roi, config=config)

# Add the bounding box coordinates and OCR'd text to the list
# of results
res.append(((spX, spY, epX, epY), text))

Using OCR options, the application extracts the text within the video frame & adds that to the res list.

# Sort the results bounding box coordinates from top to bottom
res = sorted(res, key=lambda r:r[0][1])

It then sends a sorted output to the primary calling functions.

for ((spX, spY, epX, epY), text) in res:
  # Display the text OCR by using Tesseract APIs
  print("Reading Text::")
  print("=" *60)
  print(text)
  print("=" *60)

  # Removing the non-ASCII text so it can draw the text on the frame
  # using OpenCV, then draw the text and a bounding box surrounding
  # the text region of the input frame
  text = "".join([c if ord(c) < aRange else "" for c in text]).strip()
  output = orig.copy()

  cv2.rectangle(output, (spX, spY), (epX, epY), drawTag, 2)
  cv2.putText(output, text, (spX, spY - 20), cv2.FONT_HERSHEY_SIMPLEX, 1.2, drawTag, 3)

  # Show the output frame
  cv2.imshow(title, output)

Finally, it fetches the potential text region along with the text & then prints on top of the source video. Also, it removed some non-printable characters during this time to avoid any cryptic texts.

  • readingVideo.py (Main calling script.)
#####################################################
#### Written By: SATYAKI DE ####
#### Written On: 22-Jul-2022 ####
#### Modified On 25-Jul-2022 ####
#### ####
#### Objective: This is the main calling ####
#### python script that will invoke the ####
#### clsReadingTextFromStream class to initiate ####
#### the reading capability in real-time ####
#### & display text via Web-CAM. ####
#####################################################
# We keep the setup code in a different class as shown below.
import clsReadingTextFromStream as rtfs
from clsConfig import clsConfig as cf
import datetime
import logging
###############################################
### Global Section ###
###############################################
# Instantiating all the main class
x1 = rtfs.clsReadingTextFromStream()
###############################################
### End of Global Section ###
###############################################
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'readingTextFromVideo.log', level=logging.INFO)
print('Started reading text from videos!')
# Execute all the pass
r1 = x1.processStream(debugInd, var)
if (r1 == 0):
print('Successfully read text from the Live Stream!')
else:
print('Failed to read text from the Live Stream!')
var2 = datetime.datetime.now()
c = var2 - var1
minutes = c.total_seconds() / 60
print('Total difference in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()
view raw readingVideo.py hosted with ❤ by GitHub

Please find the key snippet –

# Instantiating all the main class

x1 = rtfs.clsReadingTextFromStream()

# Execute all the pass
r1 = x1.processStream(debugInd, var)

if (r1 == 0):
    print('Successfully read text from the Live Stream!')
else:
    print('Failed to read text from the Live Stream!')

The above lines instantiate the main calling class & then invoke the function to get the desired extracted text from the live streaming video if that is successful.

FOLDER STRUCTURE:

Here is the folder structure that contains all the files & directories in MAC O/S –

You will get the complete codebase in the following Github link.

Unfortunately, I cannot upload the model due to it’s size. I will share on the need basis.

I’ll bring some more exciting topic in the coming days from the Python verse. Please share & subscribe my post & let me know your feedback.

Till then, Happy Avenging! 🙂

Note: All the data & scenario posted here are representational data & scenarios & available over the internet & for educational purpose only. Some of the images (except my photo) that we’ve used are available over the net. We don’t claim the ownership of these images. There is an always room for improvement & especially the prediction quality.

Neural prophet – The enhanced version of Facebook’s forecasting API

Hi Team,

Today, I’ll be explaining the enhancement of one of the previous posts. I know that I’ve shared the fascinating API named prophet-API, which Facebook developed. One can quickly get more accurate predictions with significantly fewer data points. (If you want to know more about that post, please click on the following link.)

However, there is another enhancement on top of that API, which is more accurate. However, one needs to know – when they should consider using it. So, today, we’ll be talking about the neural prophet API.

But, before we start digging deep, why don’t we view the demo first?

Demo

Let’s visit a diagram. That way, you can understand where you can use it. Also, I’ll be sharing some of the links from the original site for better information mining.

Source: Neural Prophet (Official Site)

As one can see, this API is trying to bridge between the different groups & it enables the time-series computation efficiently.

WHERE TO USE:

Let’s visit another diagram from the same source.

Source: Neural Prophet (Official Site)

So, I hope these two pictures give you a clear picture & relatively set your expectations to more ground reality.


ARCHITECTURE:

Let us explore the architecture –

Architecture Diagram

As one can see, the application is processing IoT data & creating a historical data volume, out of which the model is gradually predicting correct outcomes with higher confidence.

For more information on this API, please visit the following link.


CODE:

Let’s explore the essential scripts here.

  1. clsConfig.py (Configuration file for the entire application.)
################################################
#### Written By: SATYAKI DE ####
#### Written On: 15-May-2020 ####
#### Modified On: 28-Dec-2021 ####
#### ####
#### Objective: This script is a config ####
#### file, contains all the keys for ####
#### Machine-Learning & streaming dashboard.####
#### ####
################################################
import os
import platform as pl
import pandas as p
class clsConfig(object):
Curr_Path = os.path.dirname(os.path.realpath(__file__))
os_det = pl.system()
if os_det == "Windows":
sep = '\\'
else:
sep = '/'
conf = {
'APP_ID': 1,
'ARCH_DIR': Curr_Path + sep + 'arch' + sep,
'PROFILE_PATH': Curr_Path + sep + 'profile' + sep,
'LOG_PATH': Curr_Path + sep + 'log' + sep,
'REPORT_PATH': Curr_Path + sep + 'report',
'FILE_NAME': Curr_Path + sep + 'Data' + sep + 'thermostatIoT.csv',
'SRC_PATH': Curr_Path + sep + 'data' + sep,
'APP_DESC_1': 'Old Video Enhancement!',
'DEBUG_IND': 'N',
'INIT_PATH': Curr_Path,
'SUBDIR': 'data',
'SEP': sep,
'testRatio':0.2,
'valRatio':0.2,
'epochsVal':8,
'sleepTime':3,
'sleepTime1':6,
'factorVal':0.2,
'learningRateVal':0.001,
'event1': {
'event': 'SummerEnd',
'ds': p.to_datetime([
'2010-04-01', '2011-04-01', '2012-04-01',
'2013-04-01', '2014-04-01', '2015-04-01',
'2016-04-01', '2017-04-01', '2018-04-01',
'2019-04-01', '2020-04-01', '2021-04-01',
]),},
'event2': {
'event': 'LongWeekend',
'ds': p.to_datetime([
'2010-12-01', '2011-12-01', '2012-12-01',
'2013-12-01', '2014-12-01', '2015-12-01',
'2016-12-01', '2017-12-01', '2018-12-01',
'2019-12-01', '2020-12-01', '2021-12-01',
]),}
}
view raw clsConfig.py hosted with ❤ by GitHub

The only key snippet would be passing a nested json element with pandas dataframe in the following lines –

'event1': {
    'event': 'SummerEnd',
    'ds': p.to_datetime([
        '2010-04-01', '2011-04-01', '2012-04-01',
        '2013-04-01', '2014-04-01', '2015-04-01',
        '2016-04-01', '2017-04-01', '2018-04-01',
        '2019-04-01', '2020-04-01', '2021-04-01',
    ]),},
'event2': {
    'event': 'LongWeekend',
    'ds': p.to_datetime([
        '2010-12-01', '2011-12-01', '2012-12-01',
        '2013-12-01', '2014-12-01', '2015-12-01',
        '2016-12-01', '2017-12-01', '2018-12-01',
        '2019-12-01', '2020-12-01', '2021-12-01',
    ]),}

As one can see, our application is equipped with the events to predict our use case better.

2. clsPredictIonIoT.py (Main class file, which will invoke neural-prophet forecast for the entire application.)

################################################
#### Written By: SATYAKI DE ####
#### Written On: 19-Feb-2022 ####
#### Modified On 21-Feb-2022 ####
#### ####
#### Objective: This python script will ####
#### perform the neural-prophet forecast ####
#### based on the historical input received ####
#### from IoT device. ####
################################################
# We keep the setup code in a different class as shown below.
from clsConfig import clsConfig as cf
import psutil
import os
import pandas as p
import json
import datetime
from neuralprophet import NeuralProphet, set_log_level
from neuralprophet import set_random_seed
from neuralprophet.benchmark import Dataset, NeuralProphetModel, SimpleExperiment, CrossValidationExperiment
import time
import clsL as cl
import matplotlib.pyplot as plt
###############################################
### Global Section ###
###############################################
# Initiating Log class
l = cl.clsL()
set_random_seed(10)
set_log_level("ERROR", "INFO")
###############################################
### End of Global Section ###
###############################################
class clsPredictIonIoT:
def __init__(self):
self.sleepTime = int(cf.conf['sleepTime'])
self.event1 = cf.conf['event1']
self.event2 = cf.conf['event2']
def forecastSeries(self, inputDf):
try:
sleepTime = self.sleepTime
event1 = self.event1
event2 = self.event2
df = inputDf
print('IoTData: ')
print(df)
## user specified events
# history events
SummerEnd = p.DataFrame(event1)
LongWeekend = p.DataFrame(event2)
dfEvents = p.concat((SummerEnd, LongWeekend))
# NeuralProphet Object
# Adding events
m = NeuralProphet(loss_func="MSE")
# set the model to expect these events
m = m.add_events(["SummerEnd", "LongWeekend"])
# create the data df with events
historyDf = m.create_df_with_events(df, dfEvents)
# fit the model
metrics = m.fit(historyDf, freq="D")
# forecast with events known ahead
futureDf = m.make_future_dataframe(df=historyDf, events_df=dfEvents, periods=365, n_historic_predictions=len(df))
forecastDf = m.predict(df=futureDf)
events = forecastDf[(forecastDf['event_SummerEnd'].abs() + forecastDf['event_LongWeekend'].abs()) > 0]
events.tail()
## plotting forecasts
fig = m.plot(forecastDf)
## plotting components
figComp = m.plot_components(forecastDf)
## plotting parameters
figParam = m.plot_parameters()
#################################
#### Train & Test Evaluation ####
#################################
m = NeuralProphet(seasonality_mode= "multiplicative", learning_rate = 0.1)
dfTrain, dfTest = m.split_df(df=df, freq="MS", valid_p=0.2)
metricsTrain = m.fit(df=dfTrain, freq="MS")
metricsTest = m.test(df=dfTest)
print('metricsTest:: ')
print(metricsTest)
# Predict Into Future
metricsTrain2 = m.fit(df=df, freq="MS")
futureDf = m.make_future_dataframe(df, periods=24, n_historic_predictions=48)
forecastDf = m.predict(futureDf)
fig = m.plot(forecastDf)
# Visualize training
m = NeuralProphet(seasonality_mode="multiplicative", learning_rate=0.1)
dfTrain, dfTest = m.split_df(df=df, freq="MS", valid_p=0.2)
metrics = m.fit(df=dfTrain, freq="MS", validation_df=dfTest, plot_live_loss=True)
print('Tail of Metrics: ')
print(metrics.tail(1))
######################################
#### Time-series Cross-Validation ####
######################################
METRICS = ['SmoothL1Loss', 'MAE', 'RMSE']
params = {"seasonality_mode": "multiplicative", "learning_rate": 0.1}
folds = NeuralProphet(**params).crossvalidation_split_df(df, freq="MS", k=5, fold_pct=0.20, fold_overlap_pct=0.5)
metricsTrain = p.DataFrame(columns=METRICS)
metricsTest = p.DataFrame(columns=METRICS)
for dfTrain, dfTest in folds:
m = NeuralProphet(**params)
train = m.fit(df=dfTrain, freq="MS")
test = m.test(df=dfTest)
metricsTrain = metricsTrain.append(train[METRICS].iloc[-1])
metricsTest = metricsTest.append(test[METRICS].iloc[-1])
print('Stats: ')
dfStats = metricsTest.describe().loc[["mean", "std", "min", "max"]]
print(dfStats)
####################################
#### Using Benchmark Framework ####
####################################
print('Starting extracting result set for Benchmark:')
ts = Dataset(df = df, name = "thermoStatsCPUUsage", freq = "MS")
params = {"seasonality_mode": "multiplicative"}
exp = SimpleExperiment(
model_class=NeuralProphetModel,
params=params,
data=ts,
metrics=["MASE", "RMSE"],
test_percentage=25,
)
resultTrain, resultTest = exp.run()
print('Test result for Benchmark:: ')
print(resultTest)
print('Finished extracting result test for Benchmark!')
####################################
#### Cross Validate Experiment ####
####################################
print('Starting extracting result set for Corss-Validation:')
ts = Dataset(df = df, name = "thermoStatsCPUUsage", freq = "MS")
params = {"seasonality_mode": "multiplicative"}
exp_cv = CrossValidationExperiment(
model_class=NeuralProphetModel,
params=params,
data=ts,
metrics=["MASE", "RMSE"],
test_percentage=10,
num_folds=3,
fold_overlap_pct=0,
)
resultTrain, resultTest = exp_cv.run()
print('resultTest for Cross Validation:: ')
print(resultTest)
print('Finished extracting result test for Corss-Validation!')
######################################################
#### 3-Phase Train, Test & Validation Experiment ####
######################################################
print('Starting 3-phase Train, Test & Validation Experiment!')
m = NeuralProphet(seasonality_mode= "multiplicative", learning_rate = 0.1)
# create a test holdout set:
dfTrainVal, dfTest = m.split_df(df=df, freq="MS", valid_p=0.2)
# create a validation holdout set:
dfTrain, dfVal = m.split_df(df=dfTrainVal, freq="MS", valid_p=0.2)
# fit a model on training data and evaluate on validation set.
metricsTrain1 = m.fit(df=dfTrain, freq="MS")
metrics_val = m.test(df=dfVal)
# refit model on training and validation data and evaluate on test set.
metricsTrain2 = m.fit(df=dfTrainVal, freq="MS")
metricsTest = m.test(df=dfTest)
metricsTrain1["split"] = "train1"
metricsTrain2["split"] = "train2"
metrics_val["split"] = "validate"
metricsTest["split"] = "test"
metrics_stat = metricsTrain1.tail(1).append([metricsTrain2.tail(1), metrics_val, metricsTest]).drop(columns=['RegLoss'])
print('Metrics Stat:: ')
print(metrics_stat)
# Train, Cross-Validate and Cross-Test evaluation
METRICS = ['SmoothL1Loss', 'MAE', 'RMSE']
params = {"seasonality_mode": "multiplicative", "learning_rate": 0.1}
crossVal, crossTest = NeuralProphet(**params).double_crossvalidation_split_df(df, freq="MS", k=5, valid_pct=0.10, test_pct=0.10)
metricsTrain1 = p.DataFrame(columns=METRICS)
metrics_val = p.DataFrame(columns=METRICS)
for dfTrain1, dfVal in crossVal:
m = NeuralProphet(**params)
train1 = m.fit(df=dfTrain, freq="MS")
val = m.test(df=dfVal)
metricsTrain1 = metricsTrain1.append(train1[METRICS].iloc[-1])
metrics_val = metrics_val.append(val[METRICS].iloc[-1])
metricsTrain2 = p.DataFrame(columns=METRICS)
metricsTest = p.DataFrame(columns=METRICS)
for dfTrain2, dfTest in crossTest:
m = NeuralProphet(**params)
train2 = m.fit(df=dfTrain2, freq="MS")
test = m.test(df=dfTest)
metricsTrain2 = metricsTrain2.append(train2[METRICS].iloc[-1])
metricsTest = metricsTest.append(test[METRICS].iloc[-1])
mtrain2 = metricsTrain2.describe().loc[["mean", "std"]]
print('Train 2 Stats:: ')
print(mtrain2)
mval = metrics_val.describe().loc[["mean", "std"]]
print('Validation Stats:: ')
print(mval)
mtest = metricsTest.describe().loc[["mean", "std"]]
print('Test Stats:: ')
print(mtest)
return 0
except Exception as e:
x = str(e)
print('Error: ', x)
return 1

Some of the key snippets that I will discuss here are as follows –

## user specified events
# history events
SummerEnd = p.DataFrame(event1)
LongWeekend = p.DataFrame(event2)

dfEvents = p.concat((SummerEnd, LongWeekend))

# NeuralProphet Object
# Adding events
m = NeuralProphet(loss_func="MSE")

# set the model to expect these events
m = m.add_events(["SummerEnd", "LongWeekend"])

# create the data df with events
historyDf = m.create_df_with_events(df, dfEvents)

Creating & adding events into your model will allow it to predict based on the milestones.

# fit the model
metrics = m.fit(historyDf, freq="D")

# forecast with events known ahead
futureDf = m.make_future_dataframe(df=historyDf, events_df=dfEvents, periods=365, n_historic_predictions=len(df))
forecastDf = m.predict(df=futureDf)

events = forecastDf[(forecastDf['event_SummerEnd'].abs() + forecastDf['event_LongWeekend'].abs()) > 0]
events.tail()

## plotting forecasts
fig = m.plot(forecastDf)

## plotting components
figComp = m.plot_components(forecastDf)

## plotting parameters
figParam = m.plot_parameters()

Based on the daily/monthly collected data, our algorithm tries to plot the data points & predict a future trend, which will look like this –

Future Data Points

From the above diagram, we can conclude that the CPU’s trend has been growing day by day since the beginning. However, there are some events when we can see a momentary drop in requirements due to the climate & holidays. During those times, either people are not using them or are not at home.

Apart from that, I’ve demonstrated the use of a benchwork framework, & splitting the data into Train, Test & Validation & captured the RMSE values. I would request you to go through that & post any questions if you have any.

You can witness the train & validation datasets & visualize them in the standard manner, which will look something like –

Demo

3. readingIoT.py (Main invoking script.)

###############################################
#### Written By: SATYAKI DE ####
#### Written On: 21-Feb-2022 ####
#### Modified On 21-Feb-2022 ####
#### ####
#### Objective: This python script will ####
#### invoke the main class to use the ####
#### stored historical IoT data stored & ####
#### then transform, cleanse, predict & ####
#### analyze the data points into more ####
#### meaningful decision-making insights. ####
###############################################
# We keep the setup code in a different class as shown below.
from clsConfig import clsConfig as cf
import datetime
import logging
import pandas as p
import clsPredictIonIoT as cpt
###############################################
### Global Section ###
###############################################
sep = str(cf.conf['SEP'])
Curr_Path = str(cf.conf['INIT_PATH'])
fileName = str(cf.conf['FILE_NAME'])
###############################################
### End of Global Section ###
###############################################
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
# Initiating Prediction class
x1 = cpt.clsPredictIonIoT()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'IoT_NeuralProphet.log', level=logging.INFO)
# Reading the source IoT data
iotData = p.read_csv(fileName)
df = iotData.rename(columns={'MonthlyDate': 'ds', 'AvgIoTCPUUsage': 'y'})[['ds', 'y']]
r1 = x1.forecastSeries(df)
if (r1 == 0):
print('Successfully IoT forecast predicted!')
else:
print('Failed to predict IoT forecast!')
var2 = datetime.datetime.now()
c = var2 - var1
minutes = c.total_seconds() / 60
print('Total Run Time in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()
view raw readingIoT.py hosted with ❤ by GitHub

Here are some of the key snippets –

# Reading the source IoT data
iotData = p.read_csv(fileName)
df = iotData.rename(columns={'MonthlyDate': 'ds', 'AvgIoTCPUUsage': 'y'})[['ds', 'y']]

r1 = x1.forecastSeries(df)

if (r1 == 0):
    print('Successfully IoT forecast predicted!')
else:
    print('Failed to predict IoT forecast!')

var2 = datetime.datetime.now()

In those above lines, the main calling application is invoking the neural-forecasting class & passing the pandas dataframe containing IoT’s historical data to train its model.

For your information, here is the outcome of the run, when you invoke the main calling script –

Demo – Continue

FOLDER STRUCTURE:

Please find the folder structure as shown –

Directory Structure

So, we’ve done it.

You will get the complete codebase in the following Github link.

I’ll bring some more exciting topic in the coming days from the Python verse. Please share & subscribe my post & let me know your feedback.

Till then, Happy Avenging! 😀

Note: All the data & scenario posted here are representational data & scenarios & available over the internet & for educational purpose only. Some of the images (except my photo) that we’ve used are available over the net. We don’t claim the ownership of these images. There is an always room for improvement & especially the prediction quality.