Use Groq

agent.py

@@ -1,9 +1,12 @@
+import os
+
 # --- Langchain / Langraph ---
 from langchain_community.tools.tavily_search import TavilySearchResults
 from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
 from langchain_core.runnables import RunnableLambda
 from langchain_core.tools import tool
 from langchain_experimental.tools.python.tool import PythonREPLTool
+from langchain_groq import ChatGroq
 from langchain_huggingface import (
     ChatHuggingFace,
     HuggingFaceEmbeddings,
@@ -67,22 +70,12 @@ Your response must always begin with: FINAL ANSWER:
 )
 
 
-def build_agent_graph(provider: str = "huggingface"):
+def build_agent_graph(provider: str = "groq"):
     # Define toolset
     tools = [search_web_sources, run_python_code]
 
     # Instantiate LLM
-    llm = ChatHuggingFace(
-        llm=HuggingFaceEndpoint(
-            repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-            task="text-generation",
-            max_new_tokens=1024,
-            do_sample=False,
-            repetition_penalty=1.03,
-            temperature=0,
-        ),
-        verbose=True,
-    )
+    llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
 
     # Bind tools to the LLM
     llm_with_tools = llm.bind_tools(tools)

requirements.txt

@@ -4,6 +4,7 @@ langchain
 langchain-core
 langchain-community
 langchain_huggingface
+langchain-groq
 langchain-experimental
 langchain-tavily
 langgraph