Update app.py

app.py

@@ -31,12 +31,6 @@ collection_name = os.getenv("MONGO_COLLECTION", "files_collection")
 index_name = os.getenv("MONGO_VECTOR_INDEX", "vector_index")
 
 HF_TOKEN = os.getenv("HF_TOKEN")
-try:
-    api = HfApi(token=HF_TOKEN)
-    user_info = api.whoami()
-    st.success(f"✅ Hugging Face token is valid. Logged in as: {user_info['name']}")
-except Exception as e:
-    st.error(f"❌ Hugging Face token is invalid or has insufficient permissions: {e}")
 
 MONGO_URI = f"mongodb+srv://{user}:{password}@{cluster}/{db_name}?retryWrites=true&w=majority"
 
@@ -60,22 +54,54 @@ Respond truthfully. If the answer is not available, say "This information is not
 # =================== Vector Search Setup ===================
 @st.cache_resource
 def init_vector_search() -> MongoDBAtlasVectorSearch:
-    embedding_model = HuggingFaceInferenceAPIEmbeddings(
-        api_key=HF_TOKEN,
-        model_name="sentence-transformers/paraphrase-MiniLM-L6-v2"
-    )
+    from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
+    from langchain_community.vectorstores import MongoDBAtlasVectorSearch
+
+    HF_TOKEN = os.getenv("HF_TOKEN", "").strip()
+    model_name = "sentence-transformers/paraphrase-MiniLM-L6-v2"
+
     try:
-        test_vector = embedding_model.embed_query("test query")
-        print("✅ Embedding model test vector:", test_vector[:5])
+        st.write(f"🔌 Connecting to Hugging Face model: `{model_name}`")
+        embedding_model = HuggingFaceInferenceAPIEmbeddings(
+            api_key=HF_TOKEN,
+            model_name=model_name
+        )
+
+        # Test if embedding works
+        test_vector = embedding_model.embed_query("Test query for Grant Buddy")
+        st.success(f"✅ HF embedding model connected. Vector length: {len(test_vector)}")
+
     except Exception as e:
-        st.error(f"❌ Failed to embed test query: {e}")
-        raise
-    return MongoDBAtlasVectorSearch.from_connection_string(
-        connection_string=MONGO_URI,
-        namespace=f"{db_name}.{collection_name}",
-        embedding=embedding_model,
-        index_name=index_name,
-    )
+        st.error("❌ Failed to connect to Hugging Face Embedding API")
+        st.error(f"Error: {e}")
+        raise e  # Stop app here if embedding fails
+
+    # MongoDB setup
+    user = quote_plus(os.getenv("MONGO_USERNAME", "").strip())
+    password = quote_plus(os.getenv("MONGO_PASSWORD", "").strip())
+    cluster = os.getenv("MONGO_CLUSTER", "").strip()
+    db_name = os.getenv("MONGO_DB_NAME", "files").strip()
+    collection_name = os.getenv("MONGO_COLLECTION", "files_collection").strip()
+    index_name = os.getenv("MONGO_VECTOR_INDEX", "vector_index").strip()
+
+    MONGO_URI = f"mongodb+srv://{user}:{password}@{cluster}/{db_name}?retryWrites=true&w=majority"
+
+    # Connect to vector search
+    try:
+        vector_store = MongoDBAtlasVectorSearch.from_connection_string(
+            connection_string=MONGO_URI,
+            namespace=f"{db_name}.{collection_name}",
+            embedding=embedding_model,
+            index_name=index_name
+        )
+        st.success("✅ Connected to MongoDB Vector Search")
+        return vector_store
+
+    except Exception as e:
+        st.error("❌ Failed to connect to MongoDB Atlas Vector Search")
+        st.error(f"Error: {e}")
+        raise e
+
 
 # =================== Format Retrieved Chunks ===================
 def format_docs(docs: List[Document]) -> str: