Fix

app.py

@@ -4,6 +4,7 @@ import requests
 import inspect
 import pandas as pd
 from agent import build_graph
+from langchain_core.messages import HumanMessage  # Add this import
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -124,7 +125,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             error_json = e.response.json()
             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
         except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
+            error_detail += f" Response: {e.response.text[:500]"
         status_message = f"Submission Failed: {error_detail}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
@@ -197,5 +198,4 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
-    
+    demo.launch(debug=True, share=False)

lang.txt

@@ -199,130 +199,111 @@ if __name__ == "__main__":
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)
+    
 Final_Assignment_Template\agent.py:
 import os
+import json
 from dotenv import load_dotenv
+from langchain_core.messages import HumanMessage
 
-# Load environment variables
 load_dotenv()
-
-# Set protobuf implementation to avoid C++ extension issues
 os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
-
-# Load keys from environment
-groq_api_key = os.getenv("GROQ_API_KEY")
-serper_api_key = os.getenv("SERPER_API_KEY")
 hf_token = os.getenv("HUGGINGFACE_INFERENCE_TOKEN")
 
-# ---- Imports ----
 from langgraph.graph import START, StateGraph, MessagesState
 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_google_genai import ChatGoogleGenerativeAI
 from langchain_community.tools.tavily_search import TavilySearchResults
 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 langchain.vectorstores import Chroma
-from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.schema import Document
-import json
 
-# ---- Tools ----
+# ---- Tool Definitions (with docstrings) ----
 
 @tool
 def multiply(a: int, b: int) -> int:
+    """Multiply two integers and return the result."""
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
+    """Add two integers and return the result."""
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
+    """Subtract second integer from the first and return the result."""
     return a - b
 
 @tool
 def divide(a: int, b: int) -> float:
+    """Divide first integer by second and return the result as a float."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulus(a: int, b: int) -> int:
+    """Return the remainder when first integer is divided by second."""
     return a % b
 
 @tool
 def wiki_search(query: str) -> str:
+    """Search Wikipedia for the query and return text of up to 2 documents."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
     formatted = "\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
-        ]
+        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}
 
 @tool
 def web_search(query: str) -> str:
+    """Search the web for the query using Tavily and return up to 3 results."""
     search_docs = TavilySearchResults(max_results=3).invoke(query=query)
     formatted = "\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
-        ]
+        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}
 
 @tool
 def arvix_search(query: str) -> str:
+    """Search Arxiv for the query and return content from up to 3 papers."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
     formatted = "\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
-        ]
+        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}
 
-# ---- Embedding & Vector Store Setup ----
-
+# Build vector store once
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-
-json_QA = []
-with open('metadata.jsonl', 'r') as jsonl_file:
-    for line in jsonl_file:
-        json_QA.append(json.loads(line))
-
+json_QA = [json.loads(line) for line in open("metadata.jsonl", "r")]
 documents = [
     Document(
         page_content=f"Question : {sample['Question']}\n\nFinal answer : {sample['Final answer']}",
         metadata={"source": sample["task_id"]}
-    )
-    for sample in json_QA
+    ) for sample in json_QA
 ]
-
 vector_store = Chroma.from_documents(
     documents=documents,
     embedding=embeddings,
     persist_directory="./chroma_db",
     collection_name="my_collection"
 )
-vector_store.persist()
 print("Documents inserted:", vector_store._collection.count())
 
 @tool
 def similar_question_search(query: str) -> str:
+    """Search for questions similar to the input query using the vector store."""
     matched_docs = vector_store.similarity_search(query, 3)
     formatted = "\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
-        ]
+        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}
 
@@ -334,29 +315,28 @@ Now, I will ask you a question. Report your thoughts, and finish your answer wit
 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...
 """
-
 sys_msg = SystemMessage(content=system_prompt)
 
-# ---- Tool List ----
-
 tools = [
     multiply, add, subtract, divide, modulus,
     wiki_search, web_search, arvix_search, similar_question_search
 ]
 
-# ---- Graph Definition ----
+# ---- Graph Builder ----
 
-def build_graph(provider: str = "groq"):
-    if provider == "groq":
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0, api_key=groq_api_key)
-    elif provider == "google":
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-    elif provider == "huggingface":
+def build_graph(provider: str = "huggingface"):
+    if provider == "huggingface":
         llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(repo_id="mosaicml/mpt-30b", temperature=0)
+            llm=HuggingFaceEndpoint(
+                repo_id="mosaicml/mpt-30b",
+                temperature=0,
+                huggingfacehub_api_token=hf_token
+            )
         )
+    elif provider == "google":
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     else:
-        raise ValueError("Invalid provider: choose 'groq', 'google', or 'huggingface'.")
+        raise ValueError("Invalid provider: choose 'huggingface' or 'google'.")
 
     llm_with_tools = llm.bind_tools(tools)
 
@@ -380,6 +360,7 @@ def build_graph(provider: str = "groq"):
     builder.add_edge("tools", "assistant")
 
     return builder.compile()
+
 Final_Assignment_Template\metadata.jsonl:
 
 Final_Assignment_Template\requirements.txt: