Update app.py

app.py

@@ -25,12 +25,17 @@ import re
 
 
 # default_persist_directory = './chroma_HF/'
-list_llm = ["mistralai/Mistral-7B-Instruct-v0.2", "mistralai/Mixtral-8x7B-Instruct-v0.1", "mistralai/Mistral-7B-Instruct-v0.1", \
-    "google/gemma-7b-it","google/gemma-2b-it", \
-    "HuggingFaceH4/zephyr-7b-beta", "HuggingFaceH4/zephyr-7b-gemma-v0.1", \
-    "meta-llama/Llama-2-7b-chat-hf", "microsoft/phi-2", \
-    "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "mosaicml/mpt-7b-instruct", "tiiuae/falcon-7b-instruct", \
-    "google/flan-t5-xxl" , "core42/jais-13b"
+# list_llm = ["mistralai/Mistral-7B-Instruct-v0.2", "mistralai/Mixtral-8x7B-Instruct-v0.1", "mistralai/Mistral-7B-Instruct-v0.1", \
+#     "google/gemma-7b-it","google/gemma-2b-it", \
+#     "HuggingFaceH4/zephyr-7b-beta", "HuggingFaceH4/zephyr-7b-gemma-v0.1", \
+#     "meta-llama/Llama-2-7b-chat-hf", "microsoft/phi-2", \
+#     "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "mosaicml/mpt-7b-instruct", "tiiuae/falcon-7b-instruct", \
+#     "google/flan-t5-xxl" , "core42/jais-13b"
+# ]
+
+list_llm = [
+    "HuggingFaceH4/zephyr-7b-beta",
+    
 ]
 list_llm_simple = [os.path.basename(llm) for llm in list_llm]
 
@@ -121,7 +126,7 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
             top_k = top_k,
         )
     elif llm_model == "microsoft/phi-2":
-        # raise gr.Error("phi-2 model requires 'trust_remote_code=True', currently not supported by langchain HuggingFaceHub...")
+        raise gr.Error("phi-2 model requires 'trust_remote_code=True', currently not supported by langchain HuggingFaceHub...")
         llm = HuggingFaceEndpoint(
             repo_id=llm_model, 
             # model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k, "trust_remote_code": True, "torch_dtype": "auto"}
@@ -286,21 +291,16 @@ def demo():
         collection_name = gr.State()
         
         gr.Markdown(
-        """<center><h2>PDF-based chatbot</center></h2>
-        <h3>Ask any questions about your PDF documents</h3>""")
-        gr.Markdown(
-        """<b>Note:</b> This AI assistant, using Langchain and open-source LLMs, performs retrieval-augmented generation (RAG) from your PDF documents. \
-        The user interface explicitely shows multiple steps to help understand the RAG workflow. 
-        This chatbot takes past questions into account when generating answers (via conversational memory), and includes document references for clarity purposes.<br>
-        <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 a reply.
+        """<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>
         """)
-        
-        with gr.Tab("Step 1 - Upload PDF"):
+        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)")
                 # upload_btn = gr.UploadButton("Loading document...", height=100, file_count="multiple", file_types=["pdf"], scale=1)
-        
-        with gr.Tab("Step 2 - Process document"):
             with gr.Row():
                 db_btn = gr.Radio(["ChromaDB"], label="Vector database type", value = "ChromaDB", type="index", info="Choose your vector database")
             with gr.Accordion("Advanced options - Document text splitter", open=False):
@@ -311,15 +311,15 @@ def demo():
             with gr.Row():
                 db_progress = gr.Textbox(label="Vector database initialization", value="None")
             with gr.Row():
-                db_btn = gr.Button("Generate vector database")
+                db_btn = gr.Button("Generate vector database...")
             
-        with gr.Tab("Step 3 - Initialize QA chain"):
+        with gr.Tab("Step 2 - QA chain initialization"):
             with gr.Row():
                 llm_btn = gr.Radio(list_llm_simple, \
                     label="LLM models", value = list_llm_simple[0], type="index", info="Choose your LLM model")
             with gr.Accordion("Advanced options - LLM model", open=False):
                 with gr.Row():
-                    slider_temperature = gr.Slider(minimum = 0.01, maximum = 1.0, value=0.7, step=0.1, label="Temperature", info="Model temperature", interactive=True)
+                    slider_temperature = gr.Slider(minimum = 0.0, maximum = 1.0, value=0.7, step=0.1, label="Temperature", info="Model temperature", interactive=True)
                 with gr.Row():
                     slider_maxtokens = gr.Slider(minimum = 224, maximum = 4096, value=1024, step=32, label="Max Tokens", info="Model max tokens", interactive=True)
                 with gr.Row():
@@ -327,9 +327,9 @@ def demo():
             with gr.Row():
                 llm_progress = gr.Textbox(value="None",label="QA chain initialization")
             with gr.Row():
-                qachain_btn = gr.Button("Initialize Question Answering chain")
+                qachain_btn = gr.Button("Initialize question-answering chain...")
 
-        with gr.Tab("Step 4 - Chatbot"):
+        with gr.Tab("Step 3 - Conversation with chatbot"):
             chatbot = gr.Chatbot(height=300)
             with gr.Accordion("Advanced - Document references", open=False):
                 with gr.Row():
@@ -342,10 +342,10 @@ def demo():
                     doc_source3 = gr.Textbox(label="Reference 3", lines=2, container=True, scale=20)
                     source3_page = gr.Number(label="Page", scale=1)
             with gr.Row():
-                msg = gr.Textbox(placeholder="Type message (e.g. 'What is this document about?')", container=True)
+                msg = gr.Textbox(placeholder="Type message", container=True)
             with gr.Row():
-                submit_btn = gr.Button("Submit message")
-                clear_btn = gr.ClearButton([msg, chatbot], value="Clear conversation")
+                submit_btn = gr.Button("Submit")
+                clear_btn = gr.ClearButton([msg, chatbot])
             
         # Preprocessing events
         #upload_btn.upload(upload_file, inputs=[upload_btn], outputs=[document])