Update app.py

app.py

@@ -41,23 +41,28 @@ def create_db(splits):
     return vectordb
 
 
+# Initialize langchain LLM chain
+from langchain_community.llms import HuggingFaceEndpoint
+
 # Initialize langchain LLM chain
 def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, progress=gr.Progress()):
     if llm_model == "meta-llama/Meta-Llama-3-8B-Instruct":
         llm = HuggingFaceEndpoint(
             repo_id=llm_model,
-            huggingfacehub_api_token = api_token,
-            temperature = temperature,
-            max_new_tokens = max_tokens,
-            top_k = top_k,
+            huggingfacehub_api_token=api_token,
+            temperature=temperature,
+            max_new_tokens=max_tokens,
+            top_k=top_k,
+            task="text-generation"  # Explicitly specify the task type
         )
     else:
         llm = HuggingFaceEndpoint(
-            huggingfacehub_api_token = api_token,
-            repo_id=llm_model, 
-            temperature = temperature,
-            max_new_tokens = max_tokens,
-            top_k = top_k,
+            huggingfacehub_api_token=api_token,
+            repo_id=llm_model,
+            temperature=temperature,
+            max_new_tokens=max_tokens,
+            top_k=top_k,
+            task="text-generation"  # Explicitly specify the task type
         )
     
     memory = ConversationBufferMemory(
@@ -66,7 +71,7 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
         return_messages=True
     )
 
-    retriever=vector_db.as_retriever()
+    retriever = vector_db.as_retriever()
     qa_chain = ConversationalRetrievalChain.from_llm(
         llm,
         retriever=retriever,
@@ -76,7 +81,7 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
         verbose=False,
     )
     return qa_chain
-
+    
 # Initialize database
 def initialize_database(list_file_obj, progress=gr.Progress()):
     # Create a list of documents (when valid)