Update app.py

app.py

@@ -10,24 +10,6 @@ try:
 except ImportError:
     HUGGINGFACE_ENDPOINT_AVAILABLE = False
     print("langchain-huggingface not available, using fallback")
-
-from langchain.schema import BaseLanguageModel
-from langchain.callbacks.manager import CallbackManagerForLLMRun
-from typing import Any, List, Optional
-
-# Simple mock LLM for testing
-class MockLLM(BaseLanguageModel):
-    def _llm_type(self) -> str:
-        return "mock"
-    
-    def _call(
-        self, 
-        prompt: str, 
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[CallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> str:
-        return f"Based on the document context, here's a response to your query: {prompt[:100]}... [This is a mock response for testing. Please configure a proper LLM.]"
 from langchain_community.embeddings import HuggingFaceEmbeddings
 
 # You can use this section to suppress warnings generated by your code:
@@ -51,57 +33,46 @@ def get_llm():
     # Check if API token is properly set
     api_token = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
     if not api_token or api_token == "hf_YOUR_HUGGINGFACE_TOKEN":
-        print("Warning: No valid API token found. Using mock LLM for testing.")
-        return MockLLM()
+        raise ValueError("Please set a valid HUGGINGFACEHUB_API_TOKEN environment variable. You can get one from https://huggingface.co/settings/tokens")
     
-    if HUGGINGFACE_ENDPOINT_AVAILABLE:
-        try:
-            # Try the newer HuggingFaceEndpoint first
-            llm = HuggingFaceEndpoint(
-                repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
-                max_length=512,
-                temperature=0.1,
-                huggingfacehub_api_token=api_token
-            )
-            print("Successfully initialized HuggingFaceEndpoint")
-            return llm
-        except Exception as e:
-            print(f"HuggingFaceEndpoint failed: {e}")
+    # Try different models in order of preference
+    models_to_try = [
+        ("mistralai/Mixtral-8x7B-Instruct-v0.1", "text-generation"),
+        ("microsoft/DialoGPT-medium", "text-generation"),
+        ("google/flan-t5-base", "text2text-generation"),
+        ("huggingface/CodeBERTa-small-v1", "text-generation")
+    ]
     
-    try:
-        # Fallback to traditional HuggingFaceHub
-        llm = HuggingFaceHub(
-            repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
-            task="text-generation",
-            model_kwargs={
-                "temperature": 0.1, 
-                "max_length": 512,
-                "do_sample": True,
-                "top_p": 0.9
-            },
-            huggingfacehub_api_token=api_token
-        )
-        print("Successfully initialized HuggingFaceHub")
-        return llm
-    except Exception as e:
-        print(f"HuggingFaceHub with Mixtral failed: {e}")
+    for repo_id, task in models_to_try:
+        if HUGGINGFACE_ENDPOINT_AVAILABLE:
+            try:
+                llm = HuggingFaceEndpoint(
+                    repo_id=repo_id,
+                    max_length=512,
+                    temperature=0.1,
+                    huggingfacehub_api_token=api_token
+                )
+                print(f"Successfully initialized HuggingFaceEndpoint with {repo_id}")
+                return llm
+            except Exception as e:
+                print(f"HuggingFaceEndpoint with {repo_id} failed: {e}")
         
-        # Try with a smaller, more reliable model
         try:
             llm = HuggingFaceHub(
-                repo_id="google/flan-t5-base",
-                task="text2text-generation",
+                repo_id=repo_id,
+                task=task,
                 model_kwargs={
-                    "temperature": 0.1,
+                    "temperature": 0.1, 
                     "max_length": 512
                 },
                 huggingfacehub_api_token=api_token
             )
-            print("Successfully initialized HuggingFaceHub with FLAN-T5")
+            print(f"Successfully initialized HuggingFaceHub with {repo_id}")
             return llm
-        except Exception as e2:
-            print(f"All HuggingFace models failed. Using mock LLM. Errors: {e}, {e2}")
-            return MockLLM()
+        except Exception as e:
+            print(f"HuggingFaceHub with {repo_id} failed: {e}")
+    
+    raise ValueError("All LLM initialization attempts failed. Please check your API token and internet connection.")
 
 ## Document loader
 def document_loader(file_path):
@@ -266,12 +237,20 @@ def retriever_qa(file, query):
         
         return result_text
         
+    except ValueError as ve:
+        # Handle specific ValueError (like API token issues)
+        if "API token" in str(ve):
+            return f"Configuration Error: {ve}\n\nPlease:\n1. Get a HuggingFace API token from https://huggingface.co/settings/tokens\n2. Set it as HUGGINGFACEHUB_API_TOKEN environment variable"
+        else:
+            return f"Error: {ve}"
     except Exception as e:
         error_msg = str(e)
         if "API token" in error_msg or "authentication" in error_msg.lower():
             return "Error: Please check your Hugging Face API token configuration."
         elif "embedding" in error_msg.lower():
             return "Error: Failed to create document embeddings. Please try uploading a different PDF file."
+        elif "InferenceClient" in error_msg:
+            return "Error: HuggingFace library compatibility issue. Please try updating your dependencies or contact support."
         else:
             return f"Error processing your request: {error_msg}"