Skip to content

Commit

Permalink
Merge pull request #87 from cohere-ai/rag-connector
Browse files Browse the repository at this point in the history 
Add code for article on Chat RAG with connectors
  • Loading branch information
@mrmer1
mrmer1 authored Dec 13, 2023
2 parents 1aa33a5 + 2dd5dd8 commit e554831
Show file tree
Hide file tree
Showing 4 changed files with 310 additions and 1 deletion.
10 changes: 9 additions & 1 deletion README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -142,4 +142,12 @@ Learn how to build a chatbot using Cohere’s Chat, Embed, and Rerank endpoints.
">Notebook</a> | <a href="https://colab.research.google.com/github/cohere-ai/notebooks/blob/main/notebooks/RAG_Chatbot_with_Chat_Embed_Rerank.ipynb
">Colab</a>]

<img src="https://raw.githubusercontent.com/cohere-ai/notebooks/main/notebooks/images/rag-chatbot.png" style="width:100%; max-width:400px" alt="How to Build a RAG-Powered Chatbot with Chat, Embed, and Rerank" />
<img src="https://raw.githubusercontent.com/cohere-ai/notebooks/main/notebooks/images/rag-chatbot.png" style="width:100%; max-width:400px" alt="How to Build a RAG-Powered Chatbot with Chat, Embed, and Rerank" />

### 22. How to Build a RAG-Powered Chatbot with Connectors
Learn how to build a chatbot connectors using Cohere's build-your-own connectors framework.
[<a href="https://github.com/cohere-ai/notebooks/blob/main/notebooks/RAG_Chatbot_with_Connectors.ipynb.ipynb
">Notebook</a> | <a href="https://colab.research.google.com/github/cohere-ai/notebooks/blob/main/notebooks/RAG_Chatbot_with_Connectors.ipynb.ipynb
">Colab</a>]

<img src="https://raw.githubusercontent.com/cohere-ai/notebooks/main/notebooks/images/rag-chatbot-connector.png" style="width:100%; max-width:400px" alt="How to Build a RAG-Powered Chatbot with Connectors" />
1 change: 1 addition & 0 deletions examples/chat_rag_connector/demo
Submodule demo added at 83f4f4
300 changes: 300 additions & 0 deletions notebooks/RAG_Chatbot_with_Connectors.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,300 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import cohere\n",
"import os\n",
"import uuid\n",
"from typing import List, Dict\n",
"\n",
"COHERE_API_KEY = os.getenv(\"COHERE_API_KEY\")\n",
"co = cohere.Client(COHERE_API_KEY)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Define and process documents"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Documents processed successfully\n"
]
}
],
"source": [
"import requests\n",
"\n",
"# Define the sources for the documents\n",
"# As an example, we'll use LLM University's Module 1: What are Large Language Models?\n",
"# https://docs.cohere.com/docs/intro-large-language-models\n",
"\n",
"sources = [\n",
" {\n",
" \"title\": \"Text Embeddings\", \n",
" \"url\": \"https://docs.cohere.com/docs/text-embeddings\"},\n",
" {\n",
" \"title\": \"Similarity Between Words and Sentences\", \n",
" \"url\": \"https://docs.cohere.com/docs/similarity-between-words-and-sentences\"},\n",
" {\n",
" \"title\": \"The Attention Mechanism\", \n",
" \"url\": \"https://docs.cohere.com/docs/the-attention-mechanism\"},\n",
" {\n",
" \"title\": \"Transformer Models\", \n",
" \"url\": \"https://docs.cohere.com/docs/transformer-models\"} \n",
"]\n",
"\n",
"DEMO_CONNECTOR_API_KEY = \"YOUR_CONNECTOR_API_KEY\" # Replace with your connector API key\n",
"\n",
"headers = {\n",
" \"Authorization\": f\"Bearer {DEMO_CONNECTOR_API_KEY}\"\n",
"}\n",
"\n",
"response = requests.post(\"YOUR_API_URL/process\", # Replace with your API's URL\n",
" json={\"sources\": sources},\n",
" headers=headers)\n",
"\n",
"print(response.json()[\"message\"])"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Documents processed successfully\n"
]
}
],
"source": [
"import requests\n",
"\n",
"# Define the sources for the documents\n",
"# As an example, we'll use LLM University's Module 1: What are Large Language Models?\n",
"# https://docs.cohere.com/docs/intro-large-language-models\n",
"\n",
"sources = [\n",
" {\n",
" \"title\": \"Text Embeddings\", \n",
" \"url\": \"https://docs.cohere.com/docs/text-embeddings\"},\n",
" {\n",
" \"title\": \"Similarity Between Words and Sentences\", \n",
" \"url\": \"https://docs.cohere.com/docs/similarity-between-words-and-sentences\"},\n",
" {\n",
" \"title\": \"The Attention Mechanism\", \n",
" \"url\": \"https://docs.cohere.com/docs/the-attention-mechanism\"},\n",
" {\n",
" \"title\": \"Transformer Models\", \n",
" \"url\": \"https://docs.cohere.com/docs/transformer-models\"} \n",
"]\n",
"\n",
"DEMO_CONNECTOR_API_KEY = \"6qXN7O-FdR9Q-89nW5UpbvRAk9q8oTgtc0EJz98yAg4\" # Replace with your connector API key\n",
"\n",
"headers = {\n",
" \"Authorization\": f\"Bearer {DEMO_CONNECTOR_API_KEY}\"\n",
"}\n",
"\n",
"response = requests.post(\"https://demo-conn.onrender.com/process\", # Replace with your API's URL\n",
" json={\"sources\": sources},\n",
" headers=headers)\n",
"\n",
"print(response.json()[\"message\"])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Chatbot component"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"class Chatbot:\n",
" def __init__(self, connectors: List[str]):\n",
" self.conversation_id = str(uuid.uuid4())\n",
" self.connectors = [{\"id\": c} for c in connectors]\n",
"\n",
"\n",
" def generate_response(self, message: str):\n",
" response = co.chat(\n",
" message=message,\n",
" connectors=self.connectors,\n",
" conversation_id=self.conversation_id,\n",
" stream=True\n",
" )\n",
"\n",
" for event in response:\n",
" yield event"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### App component"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"class App:\n",
" def __init__(self, chatbot: Chatbot):\n",
" self.chatbot = chatbot\n",
" \n",
" def run(self):\n",
" while True:\n",
" # Get the user message\n",
" message = input(\"User: \")\n",
"\n",
" # Typing \"quit\" ends the conversation\n",
" if message.lower() == \"quit\":\n",
" print(\"Ending chat.\")\n",
" break\n",
" else:\n",
" print(f\"User: {message}\")\n",
"\n",
" # Get the chatbot response\n",
" response = self.chatbot.generate_response(message)\n",
"\n",
" # Print the chatbot response\n",
" print(\"Chatbot:\")\n",
" \n",
" documents = []\n",
" documents_flag = False\n",
" citations_flag = False\n",
" \n",
" for event in response:\n",
" # Documents\n",
" if event.event_type == \"search-results\":\n",
" documents_flag = True\n",
" documents = event.documents\n",
" \n",
" # Text\n",
" if event.event_type == \"text-generation\":\n",
" print(event.text, end=\"\") \n",
"\n",
" # Citations\n",
" if event.event_type == \"citation-generation\":\n",
" if not citations_flag:\n",
" print(\"\\n\\nCITATIONS:\")\n",
" citations_flag = True\n",
" print(event.citations)\n",
" \n",
" if documents_flag:\n",
" print(\"\\n\\nDOCUMENTS:\")\n",
" for d in documents:\n",
" print(f'{d[\"title\"]} ({d[\"id\"]}). URL: {d[\"url\"]}')\n",
"\n",
" print(f\"\\n{'-'*100}\\n\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Run chatbot"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"User: What is attention\n",
"Chatbot:\n",
"Attention is a technique used in language models to provide context to each word in a sentence or text, based on the other words. Attention plays a crucial role in transformer models, which can help improve large language models.\n",
"\n",
"CITATIONS:\n",
"[{'start': 60, 'end': 67, 'text': 'context', 'document_ids': ['demo-conn-tm17qr_0', 'demo-conn-tm17qr_1', 'demo-conn-tm17qr_2']}]\n",
"[{'start': 68, 'end': 102, 'text': 'to each word in a sentence or text', 'document_ids': ['demo-conn-tm17qr_1', 'demo-conn-tm17qr_2']}]\n",
"[{'start': 117, 'end': 129, 'text': 'other words.', 'document_ids': ['demo-conn-tm17qr_1']}]\n",
"[{'start': 148, 'end': 160, 'text': 'crucial role', 'document_ids': ['demo-conn-tm17qr_2']}]\n",
"[{'start': 164, 'end': 182, 'text': 'transformer models', 'document_ids': ['demo-conn-tm17qr_2']}]\n",
"[{'start': 199, 'end': 229, 'text': 'improve large language models.', 'document_ids': ['demo-conn-tm17qr_2']}]\n",
"\n",
"\n",
"DOCUMENTS:\n",
"Transformer Models (demo-conn-tm17qr_0). URL: https://docs.cohere.com/docs/transformer-models\n",
"Transformer Models (demo-conn-tm17qr_1). URL: https://docs.cohere.com/docs/transformer-models\n",
"Transformer Models (demo-conn-tm17qr_2). URL: https://docs.cohere.com/docs/transformer-models\n",
"\n",
"----------------------------------------------------------------------------------------------------\n",
"\n",
"Ending chat.\n"
]
}
],
"source": [
"# Define connectors\n",
"connectors = [\"demo-conn-tm17qr\"]\n",
"\n",
"# Create an instance of the Chatbot class by supplying the connectors\n",
"chatbot = Chatbot(connectors)\n",
"\n",
"# Create an instance of the App class with the Chatbot instance\n",
"app = App(chatbot)\n",
"\n",
"# Run the chatbot\n",
"app.run()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
Binary file added notebooks/images/rag-chatbot-connector.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit e554831

Please sign in to comment.