Update app.py

app.py

@@ -68,11 +68,6 @@ def getEmbeddingModel(embeddingId):
     return OpenAIEmbeddings()
 
 
-def getLLMModel(LLMID):
-    llm = OpenAI(temperature=0.0)
-    return llm
-
-
 def clearKBUploadDirectory(uploads_dir):
     for filename in os.listdir(uploads_dir):
         file_path = os.path.join(uploads_dir, filename)
@@ -86,90 +81,11 @@ def clearKBUploadDirectory(uploads_dir):
             print('Failed to delete %s. Reason: %s' % (file_path, e))
 
 
-def loadKB(fileprovided, urlProvided, uploads_dir, request):
-    documents = []
-    if fileprovided:
-        # Delete Files
-        clearKBUploadDirectory(uploads_dir)
-        # Read and Embed New Files provided
-        for file in request.files.getlist('files[]'):
-            print("File Received>>>" + file.filename)
-            file.save(os.path.join(uploads_dir, secure_filename(file.filename)))
-            loader = PyPDFLoader(os.path.join(uploads_dir, secure_filename(file.filename)))
-            documents.extend(loader.load())
-    else:
-        loader = TextLoader('Jio.txt')
-        documents.extend(loader.load())
-
-    if urlProvided:
-        weburl = request.form.getlist('weburl')
-        print(weburl)
-        urlList = weburl[0].split(';')
-        print(urlList)
-        print("Selenium Started", datetime.now().strftime("%H:%M:%S"))
-        # urlLoader=RecursiveUrlLoader(urlList[0])
-        urlLoader = SeleniumURLLoader(urlList)
-        print("Selenium Completed", datetime.now().strftime("%H:%M:%S"))
-        documents.extend(urlLoader.load())
-        print("inside selenium loader:")
-        print(documents)
-
-    return documents
-
-
-def getRAGChain(customerName,customerDistrict, custDetailsPresent,vectordb):
-    chain = RetrievalQA.from_chain_type(
-        llm=getLLMModel(0),
-        chain_type='stuff',
-        retriever=vectordb.as_retriever(),
-        verbose=False,
-        chain_type_kwargs={
-            "verbose": False,
-            "prompt": createPrompt(customerName, customerDistrict, custDetailsPresent),
-            "memory": ConversationBufferWindowMemory(
-                k=3,
-                memory_key="history",
-                input_key="question"),
-        }
-    )
-    return chain
-
-def createVectorDB(documents):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=150)
-    texts = text_splitter.split_documents(documents)
-    print("All chunk List START ***********************\n\n")
-    pretty_print_docs(texts)
-    print("All chunk List END ***********************\n\n")
-    embeddings = getEmbeddingModel(0)
-    vectordb = Chroma.from_documents(texts, embeddings)
-    return vectordb
-
-def createPrompt(cName, cCity, custDetailsPresent):
-    cProfile = "Customer's Name is " + cName + "\nCustomer's lives in or customer's Resident State or Customer's place is " + cCity + "\n"
-    print(cProfile)
-
-    template1 = """You role is of a Professional Customer Support Executive and your name is Jio AIAssist.
-        You are talking to the below customer whose information is provided in block delimited by <cp></cp>.
-        Use the following customer related information (delimited by <cp></cp>) and context (delimited by <ctx></ctx>) to answer the question at the end by thinking step by step alongwith reaonsing steps:
-        If you don't know the answer, just say that you don't know, don't try to make up an answer.
-        Use the customer information to replace entities in the question before answering\n
-        \n"""
-
-    template2 = """
-        <ctx>
-        {context}
-        </ctx>
-        <hs>
-        {history}
-        </hs>
-        Question: {question}
-        Answer: """
-
-    prompt_template = template1 + "<cp>\n" + cProfile + "\n</cp>\n" + template2
-    PROMPT = PromptTemplate(template=prompt_template, input_variables=["history", "context", "question"])
-    return PROMPT
-
-vectordb = createVectorDB(loadKB(False, False, uploads_dir, None))
+
+
+
+
+
 
 @app.route('/', methods=['GET'])
 def test():
@@ -278,7 +194,7 @@ def file_Upload():
         global vectordb
         #vectordb = Chroma.from_documents(texts,embeddings)
         vectordb=Chroma.from_documents(documents=texts, embedding=embeddings, collection_metadata={"hnsw:space": "cosine"})
-        return render_template("AISearch.html")
+        return render_template("index.html")
 
 if __name__ == '__main__':
     app.run(host='0.0.0.0',  port=int(os.environ.get('PORT', 7860)))