Upload 2 files

agent.py

@@ -26,10 +26,6 @@ from langchain_huggingface import (
 
 load_dotenv()
 
-embddings = HuggingFaceEmbeddings(
-    model_name="sentence-transformers/all-mpnet-base-v2",
-)
-
 
 # Initialize the DuckDuckGo search tool
 search_tool = DuckDuckGoSearchResults()
@@ -84,27 +80,28 @@ def arvix_search(query: str) -> str:
 
 
 # Load LLM model
-# llm = ChatOpenAI(
-#     model="gpt-4o",
-#     base_url="https://models.inference.ai.azure.com",
-#     api_key=os.environ["GITHUB_TOKEN"],
-#     temperature=0.2,
-#     max_tokens=4096,
-# )
-llm = ChatHuggingFace(
-    llm=HuggingFaceEndpoint(
-        repo_id="microsoft/Phi-3-mini-4k-instruct",
-        temperature=0,
-        # huggingfacehub_api_token=os.environ["HUGGINGFACEHUB_API_TOKEN"],
-    ),
-    verbose=True,
+llm = ChatOpenAI(
+    model="gpt-4o",
+    base_url="https://models.inference.ai.azure.com",
+    api_key=os.environ["GITHUB_TOKEN"],
+    temperature=0.2,
+    max_tokens=4096,
 )
+# llm = ChatHuggingFace(
+#     llm=HuggingFaceEndpoint(
+#         # repo_id="microsoft/Phi-3-mini-4k-instruct",
+#         repo_id="Qwen/Qwen3-235B-A22B",
+#         temperature=0,
+#         # huggingfacehub_api_token=os.environ["HUGGINGFACEHUB_API_TOKEN"],
+#     ),
+#     verbose=True,
+# )
 
 tools = [
     arvix_search,
     wiki_search,
     # web_search,
-    search_tool,
+    # search_tool,
 ]
 # Bind the tools to the LLM
 model_with_tools = llm.bind_tools(tools)