Category: faiss

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

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

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

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

#########################################################
#### 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()

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

#########################################################
#### 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()

#########################################################
#### 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