Update agent.py

agent.py

@@ -1,23 +1,28 @@
-"""LangGraph Agent"""
 import os
 from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
-from langgraph.prebuilt import ToolNode
+from langgraph.prebuilt import tools_condition, ToolNode
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
 from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_community.document_loaders import WikipediaLoader
-from langchain_community.document_loaders import ArxivLoader
-from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
+from langchain_community.vectorstores import Chroma
+from langchain_core.documents import Document
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
 from langchain.tools.retriever import create_retriever_tool
-from supabase.client import Client, create_client
+import json
+from langchain.vectorstores import Chroma
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.schema import Document
 
 load_dotenv()
 
+os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
+groq_api_key = os.getenv("GROQ_API_KEY")
+
+# Tools
 @tool
 def multiply(a: int, b: int) -> int:
     """Multiply two numbers.
@@ -111,80 +116,101 @@ def arvix_search(query: str) -> str:
         ])
     return {"arvix_results": formatted_search_docs}
 
+@tool
+def similar_question_search(question: str) -> str:
+    """Search the vector database for similar questions and return the first results.
+    
+    Args:
+        question: the question human provided."""
+    matched_docs = vector_store.similarity_search(query, 3)
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in matched_docs
+        ])
+    return {"similar_questions": formatted_search_docs}
 
-
-# load the system prompt from the file
-with open("system_prompt.txt", "r", encoding="utf-8") as f:
-    system_prompt = f.read()
+# Load system prompt
+system_prompt = """
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+FINAL ANSWER: [YOUR FINAL ANSWER]. 
+YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 
+"""
 
 # System message
 sys_msg = SystemMessage(content=system_prompt)
 
-# build a retriever
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
-supabase: Client = create_client(
-    os.environ.get("SUPABASE_URL"), 
-    os.environ.get("SUPABASE_SERVICE_KEY"))
-vector_store = SupabaseVectorStore(
-    client=supabase,
-    embedding= embeddings,
-    table_name="documents",
-    query_name="match_documents_langchain",
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+
+with open('metadata.jsonl', 'r') as jsonl_file:
+    json_list = list(jsonl_file)
+
+json_QA = []
+for json_str in json_list:
+    json_data = json.loads(json_str)
+    json_QA.append(json_data)
+
+documents = []
+for sample in json_QA:
+    content = f"Question : {sample['Question']}\n\nFinal answer : {sample['Final answer']}"
+    metadata = {"source": sample["task_id"]}
+    documents.append(Document(page_content=content, metadata=metadata))
+
+# Initialize vector store and add documents
+vector_store = Chroma.from_documents(
+    documents=documents,
+    embedding=embeddings,
+    persist_directory="./chroma_db",
+    collection_name="my_collection"
 )
-create_retriever_tool = create_retriever_tool(
+vector_store.persist()
+print("Documents inserted:", vector_store._collection.count())
+
+
+# Retriever tool (optional if you want to expose to agent)
+retriever_tool = create_retriever_tool(
     retriever=vector_store.as_retriever(),
     name="Question Search",
     description="A tool to retrieve similar questions from a vector store.",
 )
 
-
-
+# Tool list
 tools = [
-    multiply,
-    add,
-    subtract,
-    divide,
-    modulus,
-    wiki_search,
-    web_search,
-    arvix_search,
+    multiply, add, subtract, divide, modulus,
+    wiki_search, web_search, arvix_search,
 ]
 
-# Build graph function
+# Build graph
 def build_graph(provider: str = "groq"):
-    """Build the graph"""
-    # Load environment variables from .env file
-    if provider == "google":
-        # Google Gemini
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-    elif provider == "groq":
-        # Groq https://console.groq.com/docs/models
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
-    elif provider == "huggingface":
-        # TODO: Add huggingface endpoint
-        llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(
-                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
-                temperature=0,
-            ),
-        )
-    else:
-        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
-    # Bind tools to LLM
+    # if provider == "google":
+    #     llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    # elif provider == "groq":
+    #     llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
+    # elif provider == "huggingface":
+    #     llm = ChatHuggingFace(
+    #     llm=HuggingFaceEndpoint(
+    #         repo_id="mosaicml/mpt-30b",
+    #         temperature=0,
+    #     )
+    # )
+    # else:
+    #     raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
+
+    # llm_with_tools = llm.bind_tools(tools)
+    llm = ChatGroq(model="qwen-qwq-32b", temperature=0,api_key=groq_api_key)
     llm_with_tools = llm.bind_tools(tools)
 
-    # Node
     def assistant(state: MessagesState):
-        """Assistant node"""
         return {"messages": [llm_with_tools.invoke(state["messages"])]}
-    
+
     def retriever(state: MessagesState):
-        """Retriever node"""
-        similar_question = vector_store.similarity_search(state["messages"][0].content)
-        example_msg = HumanMessage(
-            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
-        )
-        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        similar = vector_store.similarity_search(state["messages"][0].content)
+        if similar:
+            example_msg = HumanMessage(content=f"Here is a similar question:\n\n{similar[0].page_content}")
+            return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        return {"messages": [sys_msg] + state["messages"]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)
@@ -192,22 +218,7 @@ def build_graph(provider: str = "groq"):
     builder.add_node("tools", ToolNode(tools))
     builder.add_edge(START, "retriever")
     builder.add_edge("retriever", "assistant")
-    builder.add_conditional_edges(
-        "assistant",
-        tools_condition,
-    )
+    builder.add_conditional_edges("assistant", tools_condition)
     builder.add_edge("tools", "assistant")
 
-    # Compile graph
-    return builder.compile()
-
-# test
-if __name__ == "__main__":
-    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
-    # Build the graph
-    graph = build_graph(provider="groq")
-    # Run the graph
-    messages = [HumanMessage(content=question)]
-    messages = graph.invoke({"messages": messages})
-    for m in messages["messages"]:
-        m.pretty_print()
+    return builder.compile()