Update app.py

app.py

@@ -13,6 +13,9 @@ from langchain_community.embeddings import HuggingFaceEmbeddings
 from llama_parse import LlamaParse
 from langchain_core.documents import Document
 from huggingface_hub import InferenceClient
+import inspect
+
+print(inspect.signature(client.chat_completion))
 
 # Environment variables and configurations
 huggingface_token = os.environ.get("HUGGINGFACE_TOKEN")
@@ -70,7 +73,7 @@ def update_vectors(files, parser):
     
     return f"Vector store updated successfully. Processed {total_chunks} chunks from {len(files)} files using {parser}."
 
-def generate_chunked_response(prompt, max_tokens=1000, max_chunks=5, temperature=0.7, repetition_penalty=1.1):
+def generate_chunked_response(prompt, max_tokens=1000, max_chunks=5, temperature=0.7):
     client = InferenceClient(
         "meta-llama/Meta-Llama-3.1-8B-Instruct",
         token=huggingface_token,
@@ -84,9 +87,8 @@ def generate_chunked_response(prompt, max_tokens=1000, max_chunks=5, temperature
             chunk_response = ""
             for message in client.chat_completion(
                 messages=messages,
-                max_tokens=max_tokens,  # Changed from max_new_tokens to max_tokens
+                max_tokens=max_tokens,
                 temperature=temperature,
-                repetition_penalty=repetition_penalty,
                 stream=True,
             ):
                 chunk = message.choices[0].delta.content