Update agent.py

agent.py

@@ -11,109 +11,88 @@ 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_core.messages import SystemMessage, HumanMessage
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
 from langchain_core.tools import tool
 from langchain.tools.retriever import create_retriever_tool
 from supabase.client import Client, create_client
 
 load_dotenv()
-supabase_url='https://qzydfaroejcpolxfgfim.supabase.co'
-supabase_key='eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6InF6eWRmYXJvZWpjcG9seGZnZmltIiwicm9sZSI6InNlcnZpY2Vfcm9sZSIsImlhdCI6MTc0OTUwNTQyMywiZXhwIjoyMDY1MDgxNDIzfQ.IBjtn1tPcogCF6DSf8dgR29aTsC61Qh0XueXYcEWG_Q'
+
+supabase_url = 'https://qzydfaroejcpolxfgfim.supabase.co'
+supabase_key = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6InF6eWRmYXJvZWpjcG9seGZnZmltIiwicm9sZSI6InNlcnZpY2Vfcm9sZSIsImlhdCI6MTc0OTUwNTQyMywiZXhwIjoyMDY1MDgxNDIzfQ.IBjtn1tPcogCF6DSf8dgR29aTsC61Qh0XueXYcEWG_Q'
+
+
 @tool
 def multiply(a: int, b: int) -> int:
-    """Multiply two numbers.
-    Args:
-        a: first int
-        b: second int
-    """
+    """Multiply two numbers."""
     return a * b
 
+
 @tool
 def add(a: int, b: int) -> int:
-    """Add two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+    """Add two numbers."""
     return a + b
 
+
 @tool
 def subtract(a: int, b: int) -> int:
-    """Subtract two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+    """Subtract two numbers."""
     return a - b
 
+
 @tool
-def divide(a: int, b: int) -> int:
-    """Divide two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+def divide(a: int, b: int) -> float:
+    """Divide two numbers."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
+
 @tool
 def modulus(a: int, b: int) -> int:
-    """Get the modulus of two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+    """Get the modulus of two numbers."""
     return a % b
 
+
 @tool
-def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query and return maximum 2 results.
-    
-    Args:
-        query: The search query."""
+def wiki_search(query: str) -> dict:
+    """Search Wikipedia for a query and return maximum 2 results."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
     formatted_search_docs = "\n\n---\n\n".join(
         [
             f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
             for doc in search_docs
-        ])
+        ]
+    )
     return {"wiki_results": formatted_search_docs}
 
+
 @tool
-def web_search(query: str) -> str:
-    """Search Tavily for a query and return maximum 3 results.
-    
-    Args:
-        query: The search query."""
+def web_search(query: str) -> dict:
+    """Search Tavily for a query and return maximum 3 results."""
     search_docs = TavilySearchResults(max_results=3).invoke(query=query)
     formatted_search_docs = "\n\n---\n\n".join(
         [
             f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
             for doc in search_docs
-        ])
+        ]
+    )
     return {"web_results": formatted_search_docs}
 
+
 @tool
-def arvix_search(query: str) -> str:
-    """Search Arxiv for a query and return maximum 3 result.
-    
-    Args:
-        query: The search query."""
+def arvix_search(query: str) -> dict:
+    """Search Arxiv for a query and return maximum 3 results."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
     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 search_docs
-        ])
+        ]
+    )
     return {"arvix_results": 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()
@@ -121,24 +100,23 @@ with open("system_prompt.txt", "r", encoding="utf-8") as f:
 # System message
 sys_msg = SystemMessage(content=system_prompt)
 
-# build a retriever
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
+# Build embeddings and vector store client
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")  # dim=768
 supabase: Client = create_client(supabase_url, supabase_key)
 
 vector_store = SupabaseVectorStore(
     client=supabase,
-    embedding= embeddings,
+    embedding=embeddings,
     table_name="documents",
     query_name="match_documents_langchain",
 )
+
 create_retriever_tool = create_retriever_tool(
     retriever=vector_store.as_retriever(),
     name="Question Search",
     description="A tool to retrieve similar questions from a vector store.",
 )
 
-
-
 tools = [
     multiply,
     add,
@@ -153,87 +131,60 @@ tools = [
 # Build graph function
 def build_graph(provider: str = "huggingface"):
     """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
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
     elif provider == "huggingface":
-        # TODO: Add huggingface endpoint
         llm = ChatHuggingFace(
-          llm=HuggingFaceEndpoint(endpoint_url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf"),
-        temperature=0,
+            llm=HuggingFaceEndpoint(endpoint_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
+
     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]}
-
-    from langchain_core.messages import AIMessage
 
     def retriever(state: MessagesState):
-    query = state["messages"][-1].content
-    # 1. Embed the query to vector
-    query_embedding = embeddings.embed_query(query)  # list of floats
-
-    # 2. Call the RPC function directly
-    response = supabase.rpc(
-        'match_documents_langchain',
-        {
-            'match_count': 2,
-            'query_embedding': query_embedding
-        }
-    ).execute()
-
-    docs = response.data
-    if not docs or len(docs) == 0:
-        answer = "Sorry, I couldn't find an answer to your question."
-    else:
-        content = docs[0]['content']  # get content of the first matched doc
-        # Extract answer if it has 'Final answer :' pattern
-        if "Final answer :" in content:
-            answer = content.split("Final answer :")[-1].strip()
+        query = state["messages"][-1].content
+        query_embedding = embeddings.embed_query(query)  # list of floats
+
+        response = supabase.rpc(
+            'match_documents_langchain',
+            {
+                'match_count': 2,
+                'query_embedding': query_embedding
+            }
+        ).execute()
+
+        docs = response.data
+        if not docs or len(docs) == 0:
+            answer = "Sorry, I couldn't find an answer to your question."
         else:
-            answer = content.strip()
-
-    return {"messages": [AIMessage(content=answer)]}
-
+            content = docs[0]['content']  # get content of the first matched doc
+            if "Final answer :" in content:
+                answer = content.split("Final answer :")[-1].strip()
+            else:
+                answer = content.strip()
 
-   # builder = StateGraph(MessagesState)
-    #builder.add_node("retriever", retriever)
-    #builder.add_node("assistant", assistant)
-    #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_edge("tools", "assistant")
+        return {"messages": [AIMessage(content=answer)]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)
+    # If you want to integrate assistant and tools, uncomment and add edges accordingly
+    # builder.add_node("assistant", assistant)
+    # 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_edge("tools", "assistant")
 
-    # Retriever ist Start und Endpunkt
     builder.set_entry_point("retriever")
     builder.set_finish_point("retriever")
 
-    # Compile graph
-    return builder.compile()
+    return builder.compile()