feat: 🎸 telegram

README.md

@@ -35,13 +35,6 @@ Quivr, your second brain, utilizes the power of GenerativeAI to store and retrie
 
 https://github.com/StanGirard/quivr/assets/19614572/a6463b73-76c7-4bc0-978d-70562dca71f5
 
-## Disclaimer ⚠️
-
-For a little while, Quivr will be only compatible with OpenAI API.
-
-If you want to use a Local LLM please refer to [v0.0.46](https://github.com/StanGirard/quivr/releases/tag/v0.0.46).
-
-This is due to us preparing a big feature and needing to clean the code a bit.
 
 ## Getting Started 🚀
 
@@ -112,8 +105,6 @@ Additionally, you'll need a [Supabase](https://supabase.com/) account for:
 
   > _The `NEXT_PUBLIC_BACKEND_URL` is set to localhost:5050 for the docker. Update it if you are running the backend on a different machine._
 
-  > _To activate vertexAI with PaLM from GCP follow the instructions [here](https://python.langchain.com/en/latest/modules/models/llms/integrations/google_vertex_ai_palm.html) and update `backend/.env`- It is an advanced feature, please be expert in GCP before trying to use it_
-
   - Change variables in `backend/.env`
   - Change variables in `frontend/.env`
 

connectors/telegram_bot/.env.example

@@ -0,0 +1,5 @@
+TELEGRAM_BOT_TOKEN=XXXX
+QUIVR_TOKEN=XXXX
+QUIVR_CHAT_ID=1XXXX
+QUIVR_BRAIN_ID=XXXX
+QUIVR_URL=XXXX

connectors/telegram_bot/main.py

@@ -0,0 +1,73 @@
+import logging
+import os
+
+import requests
+from dotenv import load_dotenv
+from telegram import Update
+from telegram.ext import (
+    ApplicationBuilder,
+    CommandHandler,
+    ContextTypes,
+    MessageHandler,
+    filters,
+)
+
+load_dotenv()  # Load variables from .env file
+
+logging.basicConfig(
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s", level=logging.INFO
+)
+
+telegram_bot_token = os.getenv("TELEGRAM_BOT_TOKEN", "")
+quivr_token = os.getenv("QUIVR_TOKEN", "")
+quivr_chat_id = os.getenv("QUIVR_CHAT_ID", "")
+quivr_brain_id = os.getenv("QUIVR_BRAIN_ID", "")
+quivr_url = (
+    os.getenv("QUIVR_URL", "https://api.quivr.app")
+    + f"/chat/{quivr_chat_id}/question?brain_id={quivr_brain_id}"
+)
+
+headers = {
+    "Content-Type": "application/json",
+    "Authorization": "Bearer " + quivr_token,
+}
+
+
+async def start(update: Update, context: ContextTypes.DEFAULT_TYPE):
+    await context.bot.send_message(
+        chat_id=update.effective_chat.id,
+        text="I'm Quiv's bot and can answer any question. Please ask your question.",
+    )
+
+
+async def handle_message(update: Update, context: ContextTypes.DEFAULT_TYPE):
+    user_message = update.message.text
+    response = requests.post(
+        quivr_url, headers=headers, json={"question": user_message}
+    )
+    if response.status_code == 200:
+        quivr_response = response.json().get(
+            "assistant", "Sorry, I couldn't understand that."
+        )
+        await context.bot.send_message(
+            chat_id=update.effective_chat.id, text=quivr_response
+        )
+    else:
+        # Log or print the response for debugging
+        print(f"Error: {response.status_code}, {response.text}")
+        await context.bot.send_message(
+            chat_id=update.effective_chat.id,
+            text=f"Sorry, there was an error processing your request. {response.text}",
+        )
+
+
+if __name__ == "__main__":
+    application = ApplicationBuilder().token(telegram_bot_token).build()
+
+    start_handler = CommandHandler("start", start)
+    message_handler = MessageHandler(filters.TEXT & (~filters.COMMAND), handle_message)
+
+    application.add_handler(start_handler)
+    application.add_handler(message_handler)
+
+    application.run_polling()

docs/docs/Developers/connectors/_category_.json

@@ -0,0 +1,8 @@
+{
+  "label": "📲 Connect Quivr to ...",
+  "position": 3,
+  "link": {
+    "type": "generated-index",
+    "description": "Connect Quivr to anything"
+  }
+}

docs/docs/Developers/connectors/telegram.md

@@ -0,0 +1,34 @@
+---
+title: Telegram
+---
+
+## Load a Telegram chat
+
+- You can export your Telegram chat history using the [Telegram Desktop](https://desktop.telegram.org/) app.
+- Go to Settings > Advanced > Export Telegram data
+- Select the chat you want to export
+- Select the format `Machine-readable JSON`
+- Click `Export`
+- Rename the `json` to `<yourname>.telegram`
+- Go to [Quivr.app](https://quivr.app/) and upload the file to a brain
+- You can now search your Telegram chat history!
+
+## Create a telegram bot
+
+- Go to [BotFather](https://t.me/botfather) and create a new bot
+- Copy the token
+- Go to `/connectors/telegram` and copy-paste the .env.example file
+- `TELEGRAM_BOT_TOKEN` The token you copied from BotFather
+- `QUIVR_TOKEN` The API Key of Quivr you can find in your profile
+- `QUIVR_CHAT_ID` Create a new chat in Quivr and copy the ID from the URL
+- `QUIVR_BRAIN_ID` Copy the id of the brain on which you want to ask question to
+- `QUIVR_URL` The URL of the **API** of the Quivr instance you want to use
+
+Enjoy ! 🎉
+
+<div style={{ textAlign: 'center' }}>
+  <video width="640" height="480" controls>
+    <source src="https://quivr-cms.s3.eu-west-3.amazonaws.com/quivr_telegram_bot_283a935f26.mp4" type="video/mp4"/>
+    Your browser does not support the video tag.
+  </video>
+</div>

docs/docs/Developers/run_fully_local.md

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 3
+sidebar_position: 4
 title: 📍 Run Quivr fully locally
 ---