Update app.py

app.py

@@ -68,10 +68,19 @@ def get_conversational_chain():
     Answer:
     """
     #model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, google_api_key=GOOGLE_API_KEY)
-    model = ChatGoogleGenerativeAI(model="gemini-1.0-pro-latest", temperature=0.3, google_api_key=GOOGLE_API_KEY)
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-    return chain
+    repo_id='meta-llama/Meta-Llama-3-70B'
+    llm = HuggingFaceEndpoint(
+    repo_id=repo_id, max_length=512, temperature=0.5, token=userdata.get('HUGGING_FACE_API_KEY'))
+    pt = ChatPromptTemplate.from_template(template)
+    # Retrieve and generate using the relevant snippets of the blog.
+    retriever = db.as_retriever()
+    rag_chain = (
+    {"context": retriever, "question": RunnablePassthrough()}
+    | pt
+    | llm
+    | StrOutputParser()
+     )
+    return rag_chain
 
 def embedding(chunk,query):
     #embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
@@ -80,10 +89,9 @@ def embedding(chunk,query):
     db = Chroma.from_documents(chunk,embeddings)
     doc = db.similarity_search(query)
     print(doc)
-    chain = get_conversational_chain()
-    response = chain({"input_documents": doc, "question": query}, return_only_outputs=True)
+    response = rag_chain.invoke(query)
     print(response)
-    return response["output_text"]
+    return response
     #st.write("Reply: ", response["output_text"])
 
 if 'messages' not in st.session_state: