Create app.py

app.py

@@ -0,0 +1,138 @@
+import gradio as gr
+import random
+import time
+import pymongo
+import certifi
+import os
+from dotenv import load_dotenv
+
+
+import argparse
+from dataclasses import dataclass
+from langchain.vectorstores.chroma import Chroma
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain_openai.chat_models import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate
+
+from deep_translator import GoogleTranslator
+
+uri = "mongodb+srv://clementrof:t5fXqwpDQYFpvuCk@cluster0.rl5qhcj.mongodb.net/?retryWrites=true&w=majority"
+
+# Create a new client and connect to the server
+client = pymongo.MongoClient(uri, tlsCAFile=certifi.where())
+
+# Send a ping to confirm a successful connection
+try:
+    client.admin.command('ping')
+    print("Pinged your deployment. You successfully connected to MongoDB!")
+except Exception as e:
+    print(e)
+
+# Access your database
+db = client.get_database('camila')
+records = db.info
+
+# Load environment variables from .env
+load_dotenv()
+
+# Access the private key
+private_key = os.getenv("OPENAI_API_KEY")
+os.environ["OPENAI_API_KEY"] = "OPENAI_API_KEY"
+
+CHROMA_PATH = "ch_chatbot"
+
+
+####### F R ################
+PROMPT_TEMPLATE = """
+Réponds à la question en te basant sur le contexte suivant :
+
+{context}
+
+---
+
+Voici l'historique de cette conversation, utilise l'historique comme une mémoire:
+
+{memory}
+
+---
+
+Réponds à la question en se basant sur le contexte ci-dessus et parle de la même manière que le contexte. Ne dis pas que tu utilises le contexte pour répondre : {question}
+
+"""
+
+
+
+
+
+def message(question,memory):
+
+    # Prepare the DB.
+    embedding_function = OpenAIEmbeddings()
+    db = Chroma(persist_directory=CHROMA_PATH,
+                embedding_function=embedding_function)
+
+    # Search the DB.
+    results = db.similarity_search_with_relevance_scores(question, k=3)
+    if len(results) == 0 or results[0][1] < 0.7:
+        print("Unable to find matching results.")
+        return
+
+    context_text = "\n\n---\n\n".join(
+        [doc.page_content for doc, _score in results])
+    prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
+    prompt = prompt_template.format(context=context_text, memory=memory, question=question)
+    print(prompt)
+
+    model = ChatOpenAI()
+    response_text = model.invoke(prompt)
+    content = response_text.content
+    return content
+
+
+
+def Chat_call(question):
+    existing_user_doc = records.find_one({'ID': '1'})
+
+    message_log = []
+    messages = existing_user_doc['message']
+    if len(messages)>1:
+        messages = messages[-1:]
+
+    message_log.extend(messages)
+    # Convert each dictionary into a string representation
+    message_strings = [f"{message['role']}: {message['content']}" for message in message_log]
+    # Join the strings with newline characters
+    memory = '\n'.join(message_strings)
+            
+
+
+    response = message(question,memory)
+
+
+    records.update_one({'ID': '1'}, 
+    {'$push':{'message':  {'role': 'user', 'content': f'{question}'}}})
+    records.update_one({'ID': '1'}, 
+    {'$push':{'message': {'role': 'assistant', 'content': f'{response}'}}})
+
+   
+    return response
+
+
+
+
+with gr.Blocks() as demo:
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.ClearButton([msg, chatbot])
+
+    def respond(message, chat_history):
+        bot_message = Chat_call(message)
+        chat_history.append((message, bot_message))
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+if __name__ == "__main__":
+    demo.launch()
+
+