Update app.py

app.py

@@ -20,8 +20,7 @@ import torch
 import tqdm 
 import accelerate
 
-
-default_persist_directory = './chromaDB/'
+default_persist_directory = './ChromaDB'
 
 llm_name0 = "mistralai/Mixtral-8x7B-Instruct-v0.1"
 
@@ -52,10 +51,9 @@ def create_db(splits, collection_name):
     vectordb = Chroma.from_documents(
         documents=splits,
         embedding=embedding,
+        persist_directory="./chroma_db", 
         client=new_client,
-        collection_name=collection_name,
-        persist_directory=default_persist_directory
-    )
+        collection_name=collection_name)       
     return vectordb
 
 
@@ -78,30 +76,7 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
         llm = HuggingFaceHub(
             repo_id=llm_model, 
             model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k, "load_in_8bit": True}
-        )
-    elif llm_model == "microsoft/phi-2":
-        raise gr.Error("phi-2 model requires 'trust_remote_code=True', currently not supported by langchain HuggingFaceHub...")
-        llm = HuggingFaceHub(
-            repo_id=llm_model, 
-            model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k, "trust_remote_code": True, "torch_dtype": "auto"}
-        )
-    elif llm_model == "TinyLlama/TinyLlama-1.1B-Chat-v1.0":
-        llm = HuggingFaceHub(
-            repo_id=llm_model, 
-            model_kwargs={"temperature": temperature, "max_new_tokens": 250, "top_k": top_k}
-        )
-    elif llm_model == "meta-llama/Llama-2-7b-chat-hf":
-        raise gr.Error("Llama-2-7b-chat-hf model requires a Pro subscription...")
-        llm = HuggingFaceHub(
-            repo_id=llm_model, 
-            model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k}
-        )
-    else:
-        llm = HuggingFaceHub(
-            repo_id=llm_model, 
-            # model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k, "trust_remote_code": True, "torch_dtype": "auto"}
-            model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k}
-        )
+        )    
     
     progress(0.75, desc="Defining buffer memory...")
     memory = ConversationBufferMemory(
@@ -164,7 +139,7 @@ def format_chat_history(message, chat_history):
 def conversation(qa_chain, message, history):
     formatted_chat_history = format_chat_history(message, history)
     #print("formatted_chat_history",formatted_chat_history)
-   
+    formatted_chat_history = ""
     # Generate response using QA chain
     response = qa_chain({"question": message, "chat_history": formatted_chat_history})
     response_answer = response["answer"]
@@ -199,12 +174,7 @@ def demo():
         collection_name = gr.State()
         
         gr.Markdown(
-        """<center><h2>PDF-based chatbot (powered by LangChain and open-source LLMs)</center></h2>
-        <h3>Ask any questions about your PDF documents, along with follow-ups</h3>
-        <b>Note:</b> This AI assistant performs retrieval-augmented generation from your PDF documents. \
-        When generating answers, it takes past questions into account (via conversational memory), and includes document references for clarity purposes.</i>
-        <br><b>Warning:</b> This space uses the free CPU Basic hardware from Hugging Face. Some steps and LLM models used below (free inference endpoints) can take some time to generate an output.<br>
-        """)
+        """<center><h2>ChatPDF</center></h2>""")
         with gr.Tab("Step 1 - Document pre-processing"):
             with gr.Row():
                 document = gr.Files(height=100, file_count="multiple", file_types=["pdf"], interactive=True, label="Upload your PDF documents (single or multiple)")