origin working

app.py

@@ -1,10 +1,12 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 from main import main
+from langchain_core.messages import BaseMessage
+
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 def respond(
@@ -24,8 +26,7 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
-    response = main(' '.join(message))
+    response = main(messages,message)
 
     return response
 

document_handler.py

@@ -2,8 +2,6 @@ import os
 import pickle
 from langchain_community.document_loaders.sitemap import SitemapLoader
 
-docs_file_path = 'sitemap_docs.pkl'
-
 def save_documents_to_disk(docs, file_path):
     """Save the documents to a file using pickle."""
     with open(file_path, 'wb') as file:

main.py

@@ -2,7 +2,8 @@ import argparse
 import logging
 from document_handler import load_documents_from_disk, load_documents_from_sitemap, save_documents_to_disk
 from vectorstore_handler import load_or_create_vectorstore, get_embeddings
-from query_executor import execute_query
+from query_executor import QuestionAnsweringAssistant
+import re
 
 # Configure logging
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', handlers=[
@@ -10,11 +11,16 @@ logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(
     logging.StreamHandler()
 ])
 
-def main(query):
+logger = logging.getLogger(__name__)
+
+
+def main(messages,query):
     # Path to save the documents
     sitemap_url = "https://www.originws.it/page-sitemap.xml"
-    docs_file_path = 'sitemap_docs.pkl'
+    sitemap_str = re.sub(r'[^a-zA-Z0-9]', '_', sitemap_url)
+    docs_file_path = sitemap_str+'.pkl'
 
+    qaa = QuestionAnsweringAssistant(logger)
     # Try to load documents from disk
     docs = load_documents_from_disk(docs_file_path)
 
@@ -29,12 +35,13 @@ def main(query):
 
     # Get embeddings and load/create the vectorstore
     embeddings = get_embeddings()
-    vectorstore = load_or_create_vectorstore(docs, embeddings)
+    vectorstore = load_or_create_vectorstore(docs, embeddings, sitemap_str)
 
     # Now that the vectorstore is ready, let's query it
     question = query
     logging.info(f"Executing query: {question}")
-    response = execute_query(question, vectorstore)
+    condensed = qaa.condense_query(messages,question)
+    response = qaa.execute_query(condensed, vectorstore)
     
     # Log the response
     logging.info(f"Query response: {response}")

query_executor.py

@@ -1,51 +1,89 @@
+import logging
 from langchain_openai import ChatOpenAI
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.runnables import RunnablePassthrough
 from langchain_anthropic import ChatAnthropic
 
+class QuestionAnsweringAssistant:
+    RAG_TEMPLATE = """
+    You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise but friendly. 
+    If the question is about yourself, answer you're the digital assistant coach of OriginWS. 
 
-RAG_TEMPLATE = """
-You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise but friendly. 
-If the question is about yourself, answer you're the digital assistant coach of OriginWS. 
-
-<context>
-{context}
-</context>
-
-Answer the following question:
-
-{question}"""
-
-def format_docs(docs):
-    """Format documents into a single string."""
-    return "\n\n".join(doc.page_content for doc in docs)
-
-def execute_query(question, vectorstore):
-    """Run the query against the vectorstore and return a response."""
-    print(f"Searching for: {question}")
-    docs = vectorstore.similarity_search(question, k=10)
-    print(f"Found {len(docs)} relevant documents for the query.")
-
-    # Set up the LLM and prompt handling
-    llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
-    
-    #llm = ChatAnthropic(model="claude-3-5-sonnet-20241022",temperature=0,max_tokens=1024,timeout=None,max_retries=2,
-        # api_key="...",
-        # base_url="...",
-        # other params...
-    #)
-    # Define the RAG prompt template
-    rag_prompt = ChatPromptTemplate.from_template(RAG_TEMPLATE)
-
-    # Create the chain
-    chain = (
-        RunnablePassthrough.assign(context=lambda input: format_docs(input["context"]))
-        | rag_prompt
-        | llm
-        | StrOutputParser()
-    )
-
-    # Run the chain with the query
-    response = chain.invoke({"context": docs, "question": question})
-    return response
+    <context>
+    {context}
+    </context>
+
+    Answer the following question:
+
+    {question}"""
+
+    CONDENSE_PROMPT = """
+    Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.
+
+    Here's some example: 
+
+    user: jungle up... di cosa si tratta?
+assistant: Jungle Up è una nuova tipologia di allenamento. Combina tecniche di allenamento ispirate ai movimenti animali.
+user: è possibile iscriversi?
+
+    Follow Up Input: è possibile iscriversi?
+
+    Standalone question: è possibile iscriversi al corso Jungle Up?
+    ----
+    Chat History:
+
+    {chat_history}
+
+    Follow Up Input: {question}
+
+    Standalone question:
+    """
+
+    def __init__(self, logger: logging.Logger, model_name="gpt-4o-mini", temperature=0):
+        self.logger = logger
+        self.llm = ChatOpenAI(model=model_name, temperature=temperature)
+        self.logger.info("QuestionAnsweringAssistant initialized with model: %s", model_name)
+
+    def format_docs(self, docs):
+        """Format documents into a single string."""
+        formatted_docs = "\n\n".join(doc.page_content for doc in docs)
+        self.logger.debug("Formatted documents for context: %s", formatted_docs)
+        return formatted_docs
+
+    def condense_query(self, messages, message):
+        """Rephrase the follow-up question to be a standalone question."""
+        self.logger.debug("Condensing query. History: %s, Current message: %s", messages, message)
+
+        # Format the chat history for the prompt
+        chat_history = "\n".join([f"{msg['role']}: {msg['content']}" for msg in messages])
+
+        # Use the prompt to rephrase the last user message
+        prompt_input = self.CONDENSE_PROMPT.format(chat_history=chat_history, question=message)
+        self.logger.info("Prompt condense: %s", prompt_input)
+        response = self.llm.invoke(prompt_input)
+        
+        #self.logger.info("Condensed query response: %s", response)
+        return response.content
+
+    def execute_query(self, question, vectorstore):
+        """Run the query against the vectorstore and return a response."""
+        self.logger.info("Searching for condensed question: %s", question)
+        docs = vectorstore.similarity_search(question, k=10)
+        self.logger.info("Found %d relevant documents for the query.", len(docs))
+
+        # Define the RAG prompt template
+        rag_prompt = ChatPromptTemplate.from_template(self.RAG_TEMPLATE)
+
+        # Create the chain
+        chain = (
+            RunnablePassthrough.assign(context=lambda input: self.format_docs(input["context"]))
+            | rag_prompt
+            | self.llm
+            | StrOutputParser()
+        )
+
+        # Run the chain with the query
+        response = chain.invoke({"context": docs, "question": question})
+        #self.logger.info("Query executed successfully. Response: %s", response)
+        return response

vectorstore_handler.py

@@ -3,17 +3,16 @@ from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings
 from langchain_chroma import Chroma
 
-chroma_db_dir = 'chroma_vectorstore'
 
 def get_embeddings():
     """Initialize and return OpenAI embeddings."""
     return OpenAIEmbeddings(model="text-embedding-3-large")
 
-def load_or_create_vectorstore(docs, embeddings):
+def load_or_create_vectorstore(docs, embeddings,path):
     """Load or create a Chroma vectorstore."""
-    if os.path.exists(chroma_db_dir):
+    if os.path.exists(path):
         print("Loading existing Chroma vector store from disk...")
-        return Chroma(persist_directory=chroma_db_dir, embedding_function=embeddings)
+        return Chroma(persist_directory=path, embedding_function=embeddings)
     
     # Split documents if vectorstore doesn't exist
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
@@ -22,6 +21,6 @@ def load_or_create_vectorstore(docs, embeddings):
     
     # Create new vectorstore
     print("Creating new Chroma vector store...")
-    vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings, persist_directory=chroma_db_dir)
-    print(f"Vectorstore created and saved to {chroma_db_dir}")
+    vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings, persist_directory=path)
+    print(f"Vectorstore created and saved to {path}")
     return vectorstore