Update components/chat.py

components/chat.py

@@ -41,124 +41,6 @@ def display_chat_interface():
             st.error(f"Error generating response: {e}")
             import traceback
             st.error(f"Detailed error: {traceback.format_exc()}")
-"""
 
-# Updating utils/database.py to ensure consistency in prompt variable names and agent handling.
 
-updated_utils_database_content = """
-# utils/database.py
-from langchain.memory import ConversationBufferWindowMemory
-from langchain_core.messages import (
-    HumanMessage, 
-    AIMessage, 
-    SystemMessage,
-    BaseMessage  # Added this import
-)
-from langchain.chains import ConversationalRetrievalChain
-from langchain.chat_models import ChatOpenAI
-from langchain.agents import AgentExecutor, Tool, create_openai_tools_agent
-from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain.agents.format_scratchpad.tools import format_to_tool_messages
-from langchain.agents.output_parsers.openai_tools import OpenAIToolsAgentOutputParser
-from langchain_core.runnables import RunnablePassthrough
-import os
-import streamlit as st
-
-def initialize_qa_system(vector_store):
-    \"\"\"Initialize QA system with proper chat handling\"\"\"
-    try:
-        llm = ChatOpenAI(
-            temperature=0.5,
-            model_name="gpt-4",
-            api_key=os.environ.get("OPENAI_API_KEY")
-        )
-
-        # Create chat memory
-        memory = ConversationBufferWindowMemory(
-            memory_key="chat_history",
-            return_messages=True,
-            k=5
-        )
-
-        # Create the prompt template with the correct variable names
-        prompt = ChatPromptTemplate.from_messages([
-            ("system", "You are a helpful assistant analyzing RFP documents."),
-            MessagesPlaceholder(variable_name="chat_history"),
-            ("user", "{input}\nContext: {context}"),
-            MessagesPlaceholder(variable_name="agent_scratchpad")
-        ])
-
-        # Create retriever function
-        retriever = vector_store.as_retriever(search_kwargs={"k": 2})
-
-        # Create the RAG pipeline
-        rag_pipe = (
-            {
-                "context": lambda x: retriever.get_relevant_documents(x["input"]),
-                "input": lambda x: x["input"],
-                "chat_history": lambda x: memory.chat_memory.messages,
-                "agent_scratchpad": lambda x: format_to_tool_messages(x["intermediate_steps"])
-            }
-            | prompt
-            | llm.bind(stop=["\\nHuman:"])
-            | OpenAIToolsAgentOutputParser()
-        )
-
-        # Create the agent executor
-        agent_executor = AgentExecutor(
-            agent=rag_pipe,
-            tools=[
-                Tool(
-                    name="RFP_Knowledge_Base",
-                    func=lambda x: retriever.get_relevant_documents(x),
-                    description="Use this tool to analyze RFP documents and answer questions about their content."
-                )
-            ],
-            memory=memory,
-            verbose=True,
-            handle_parsing_errors=True,
-            return_intermediate_steps=True
-        )
-
-        return agent_executor
-
-    except Exception as e:
-        st.error(f"Error initializing QA system: {e}")
-        return None
-        
-def initialize_faiss(embeddings, documents, document_names):
-    \"\"\"Initialize FAISS vector store\"\"\"
-    try:
-        from langchain.vectorstores import FAISS
-
-        vector_store = FAISS.from_texts(
-            documents,
-            embeddings,
-            metadatas=[{"source": name} for name in document_names],
-        )
-        return vector_store
-    except Exception as e:
-        st.error(f"Error initializing FAISS: {e}")
-        return None
-
-
-@st.cache_resource
-def get_embeddings_model():
-    \"\"\"Get the embeddings model\"\"\"
-    try:
-        from langchain.embeddings import HuggingFaceEmbeddings
-
-        model_name = "sentence-transformers/all-MiniLM-L6-v2"
-        embeddings = HuggingFaceEmbeddings(model_name=model_name)
-        return embeddings
-    except Exception as e:
-        st.error(f"Error loading embeddings model: {e}")
-        return None
-"""
-
-# Writing the updated contents back to the original files
-with open(components_chat_path, 'w') as chat_file:
-    chat_file.write(updated_components_chat_content)
 
-with open(utils_database_path, 'w') as database_file:
-    database_file.write(updated_utils_database_content)