UPdate

.gitignore

@@ -1,4 +1,3 @@
-chroma_db/*
 __pycache__/*
 .venv
 .env

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

README.md

@@ -1,10 +1,10 @@
 ---
-title: PDF Chatbot
+title: GAIA Chatbot - level 3
 emoji: 👁
 colorFrom: red
 colorTo: purple
 sdk: gradio
-sdk_version: 5.6.0
+sdk_version: 5.13.1
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,7 +1,12 @@
 import os
-__import__('pysqlite3')
-import sys
-sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
+# Try to import pysqlite3 for environments like Hugging Face Spaces
+try:
+    __import__('pysqlite3')
+    import sys
+    sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
+except ImportError:
+    # pysqlite3 not available, use standard sqlite3 (works on most environments)
+    pass
 from dotenv import load_dotenv
 import json
 import gradio as gr
@@ -20,11 +25,12 @@ from llama_index.vector_stores.chroma import ChromaVectorStore
 
 load_dotenv()
 
-title = "AgreenDefi Gaia 8x22b PDF Demo"
+title = "Gaia Mistral 8x22b Chat RAG PDF Demo"
 description = "Example of an assistant with Gradio, RAG from PDF documents and Mistral AI via its API"
 placeholder = (
     "Vous pouvez me posez une question sur ce contexte, appuyer sur Entrée pour valider"
 )
+placeholder_url = "Extract text from this url"
 llm_model = "open-mixtral-8x22b"
 
 env_api_key = os.environ.get("MISTRAL_API_KEY")
@@ -82,36 +88,37 @@ def load_file(files):
         for doc in documents:
             index.insert(doc)
 
-        return (
+    return (
             gr.Textbox(visible=False),
             gr.Textbox(value=f"Document encoded ! You can ask questions", visible=True),
             get_documents_in_db(),
         )
 
 
-def load_document(input_file):
-    file_name = input_file.name.split("/")[-1]
-    return gr.Textbox(value=f"Document loaded: {file_name}", visible=True)
+def load_document(input_files):
+    for input_file in input_files:
+        file_name = input_file.name.split("/")[-1]
+        return gr.Textbox(value=f"Document loaded: {file_name}", visible=True)
 
 
 with gr.Blocks() as demo:
     gr.Markdown(
-        """ # Bienvenue sur la démo AgreenDefi PDF 
+        """ # Welcome to Gaia Level 3 Demo 
     
-        Ajouter un fichier avant de poser une question sur le tchat.
-        Cette démo vous permet d'interagir entre des fichiers PDF et Mistral AI via son API.
-        Mistral va répondre à vos questions par rapport au document.
+        Add a file before interacting with the Chat.
+        This demo allows you to interact with a pdf file and then ask questions to Mistral APIs.
+        Mistral will answer with the context extracted from your uploaded file.
 
         *The files will stay in the database unless there is 48h of inactivty or you re-build the space.*
         """
     )
 
-    gr.Markdown(""" ### 1 / Préparer les données """)
+    gr.Markdown(""" ### 1 / Extract data from PDF """)
 
     with gr.Row():
         with gr.Column():
             input_file = gr.File(
-                label="Charger des fichiers pdf",
+                label="Load a pdf",
                 file_types=[".pdf"],
                 file_count="multiple",
                 type="filepath",
@@ -123,33 +130,31 @@ with gr.Blocks() as demo:
 
             input_file.upload(
                 fn=load_document,
-                inputs=[
-                    input_file,
-                ],
+                inputs=input_file,
                 outputs=[file_msg],
                 concurrency_limit=20,
             )
 
             help_msg = gr.Markdown(
-                value="Quan le document est chargé, Appuyer sur Encode pour l'ajouter dans la base de données."
+                value="Once the document is loaded, press the Encode button below to add it to the db."
             )
 
-            file_btn = gr.Button(value="Encoder les fichiers ✅", interactive=True)
+            file_btn = gr.Button(value="Encode file ✅", interactive=True)
             btn_msg = gr.Textbox(container=False, visible=False)
 
             with gr.Row():
                 db_list = gr.Markdown(value=get_documents_in_db)
-                delete_btn = gr.Button(value="Vider la base 🗑️", interactive=True, scale=0)
+                delete_btn = gr.Button(value="Empty db 🗑️", interactive=True, scale=0)
 
             file_btn.click(
                 load_file,
-                inputs=[input_file],
+                inputs=input_file,
                 outputs=[file_msg, btn_msg, db_list],
                 show_progress="full",
             )
             delete_btn.click(empty_db, outputs=[db_list], show_progress="minimal")
 
-    gr.Markdown(""" ### 2 / Poser une question selon le contexte """)
+    gr.Markdown(""" ### 2 / Ask a question about this context """)
 
     chatbot = gr.Chatbot()
     msg = gr.Textbox(placeholder=placeholder)
@@ -164,4 +169,4 @@ with gr.Blocks() as demo:
 
 demo.title = title
 
-demo.launch()
+demo.launch(share=True)

requirements.txt

@@ -1,10 +1,12 @@
-pypdf
-mistralai
-gradio
-pysqlite3-binary
-chromadb
-llama-index
-llama-index-readers-web
+pypdf==4.3.1
+mistralai==1.0.1
+gradio==4.44.0
+python-dotenv==1.0.1
+huggingface-hub==0.36.0
+# sqlite3
+# pysqlite3-binary
+chromadb==0.5.5
+llama-index==0.10.68
 llama-index-readers-file
 llama-index-llms-mistralai
 llama-index-embeddings-mistralai