working gradio

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
+from main import main
 """
 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
 """
@@ -25,19 +25,9 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    response = main(' '.join(message))
 
-        response += token
-        yield response
+    return response
 
 
 """

main.py

@@ -1,14 +1,16 @@
 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
 
-# Argument parsing for command line
-def main():
-    parser = argparse.ArgumentParser(description="Process a query to the Chroma vectorstore.")
-    parser.add_argument('query', type=str, help='The query to search in the vector store')
-    args = parser.parse_args()
+# Configure logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', handlers=[
+    logging.FileHandler("query_executor.log"),
+    logging.StreamHandler()
+])
 
+def main(query):
     # Path to save the documents
     sitemap_url = "https://www.originws.it/page-sitemap.xml"
     docs_file_path = 'sitemap_docs.pkl'
@@ -17,22 +19,24 @@ def main():
     docs = load_documents_from_disk(docs_file_path)
 
     if docs is None:
-        print("Documents not found on disk, loading from sitemap...")
+        logging.info("Documents not found on disk, loading from sitemap...")
         # Load documents using SitemapLoader
         docs = load_documents_from_sitemap(sitemap_url)
         save_documents_to_disk(docs, docs_file_path)
-        print("Documents saved to disk.")
+        logging.info("Documents saved to disk.")
     else:
-        print("Documents loaded from disk.")
+        logging.info("Documents loaded from disk.")
 
     # Get embeddings and load/create the vectorstore
     embeddings = get_embeddings()
     vectorstore = load_or_create_vectorstore(docs, embeddings)
 
     # Now that the vectorstore is ready, let's query it
-    question = args.query
+    question = query
+    logging.info(f"Executing query: {question}")
     response = execute_query(question, vectorstore)
-    print(response)
+    
+    # Log the response
+    logging.info(f"Query response: {response}")
 
-if __name__ == "__main__":
-    main()
+    return response

query_executor.py

@@ -2,9 +2,12 @@ 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
+
 
 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.
+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}
@@ -25,8 +28,13 @@ def execute_query(question, vectorstore):
     print(f"Found {len(docs)} relevant documents for the query.")
 
     # Set up the LLM and prompt handling
-    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
-
+    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)