From 00bd9a61ed6d67c728dfe9cfcdf9b592ec1be7fb Mon Sep 17 00:00:00 2001 From: Matthew Farrellee Date: Tue, 26 Aug 2025 15:58:44 -0400 Subject: [PATCH] chore: Add example notebook for Langchain + LLAMAStack integration (#3228) (#3259) --- .../langchain/Llama_Stack_LangChain.ipynb | 946 ------------------ 1 file changed, 946 deletions(-) delete mode 100644 docs/notebooks/langchain/Llama_Stack_LangChain.ipynb diff --git a/docs/notebooks/langchain/Llama_Stack_LangChain.ipynb b/docs/notebooks/langchain/Llama_Stack_LangChain.ipynb deleted file mode 100644 index ed918ff50..000000000 --- a/docs/notebooks/langchain/Llama_Stack_LangChain.ipynb +++ /dev/null @@ -1,946 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "id": "1ztegmwm4sp", - "metadata": {}, - "source": [ - "## LlamaStack + LangChain Integration Tutorial\n", - "\n", - "This notebook demonstrates how to integrate **LlamaStack** with **LangChain** to build a complete RAG (Retrieval-Augmented Generation) system.\n", - "\n", - "### Overview\n", - "\n", - "- **LlamaStack**: Provides the infrastructure for running LLMs and vector databases\n", - "- **LangChain**: Provides the framework for chaining operations and prompt templates\n", - "- **Integration**: Uses LlamaStack's OpenAI-compatible API with LangChain\n", - "\n", - "### What You'll See\n", - "\n", - "1. Setting up LlamaStack server with Together AI provider\n", - "2. Creating and managing vector databases\n", - "3. Building RAG chains with LangChain + LLAMAStack\n", - "4. Querying the chain for relevant information\n", - "\n", - "### Prerequisites\n", - "\n", - "- Together AI API key\n", - "\n", - "---\n", - "\n", - "### 1. Installation and Setup" - ] - }, - { - "cell_type": "markdown", - "id": "2ktr5ls2cas", - "metadata": {}, - "source": [ - "#### Install Required Dependencies\n", - "\n", - "First, we install all the necessary packages for LangChain and FastAPI integration." - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "id": "5b6a6a17-b931-4bea-8273-0d6e5563637a", - "metadata": { - "scrolled": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Requirement already satisfied: fastapi in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.115.14)\n", - "Requirement already satisfied: uvicorn in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.29.0)\n", - "Requirement already satisfied: langchain>=0.2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.3.27)\n", - "Requirement already satisfied: langchain-openai in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.3.30)\n", - "Requirement already satisfied: langchain-community in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.3.27)\n", - "Requirement already satisfied: langchain-text-splitters in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.3.9)\n", - "Requirement already satisfied: faiss-cpu in /Users/swapna942/miniconda3/lib/python3.12/site-packages (1.11.0)\n", - "Requirement already satisfied: starlette<0.47.0,>=0.40.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from fastapi) (0.46.2)\n", - "Requirement already satisfied: pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from fastapi) (2.11.7)\n", - "Requirement already satisfied: typing-extensions>=4.8.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from fastapi) (4.14.1)\n", - "Requirement already satisfied: annotated-types>=0.6.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4->fastapi) (0.7.0)\n", - "Requirement already satisfied: pydantic-core==2.33.2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4->fastapi) (2.33.2)\n", - "Requirement already satisfied: typing-inspection>=0.4.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from pydantic!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0,>=1.7.4->fastapi) (0.4.1)\n", - "Requirement already satisfied: anyio<5,>=3.6.2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from starlette<0.47.0,>=0.40.0->fastapi) (4.10.0)\n", - "Requirement already satisfied: idna>=2.8 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from anyio<5,>=3.6.2->starlette<0.47.0,>=0.40.0->fastapi) (3.10)\n", - "Requirement already satisfied: sniffio>=1.1 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from anyio<5,>=3.6.2->starlette<0.47.0,>=0.40.0->fastapi) (1.3.1)\n", - "Requirement already satisfied: click>=7.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from uvicorn) (8.2.1)\n", - "Requirement already satisfied: h11>=0.8 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from uvicorn) (0.16.0)\n", - "Requirement already satisfied: langchain-core<1.0.0,>=0.3.72 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain>=0.2) (0.3.74)\n", - "Requirement already satisfied: langsmith>=0.1.17 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain>=0.2) (0.4.14)\n", - "Requirement already satisfied: SQLAlchemy<3,>=1.4 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain>=0.2) (2.0.41)\n", - "Requirement already satisfied: requests<3,>=2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain>=0.2) (2.32.4)\n", - "Requirement already satisfied: PyYAML>=5.3 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain>=0.2) (6.0.2)\n", - "Requirement already satisfied: tenacity!=8.4.0,<10.0.0,>=8.1.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-core<1.0.0,>=0.3.72->langchain>=0.2) (9.1.2)\n", - "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-core<1.0.0,>=0.3.72->langchain>=0.2) (1.33)\n", - "Requirement already satisfied: packaging>=23.2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-core<1.0.0,>=0.3.72->langchain>=0.2) (24.2)\n", - "Requirement already satisfied: jsonpointer>=1.9 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from jsonpatch<2.0,>=1.33->langchain-core<1.0.0,>=0.3.72->langchain>=0.2) (2.1)\n", - "Requirement already satisfied: charset_normalizer<4,>=2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from requests<3,>=2->langchain>=0.2) (3.3.2)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from requests<3,>=2->langchain>=0.2) (2.5.0)\n", - "Requirement already satisfied: certifi>=2017.4.17 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from requests<3,>=2->langchain>=0.2) (2025.8.3)\n", - "Requirement already satisfied: openai<2.0.0,>=1.99.9 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-openai) (1.100.2)\n", - "Requirement already satisfied: tiktoken<1,>=0.7 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-openai) (0.9.0)\n", - "Requirement already satisfied: distro<2,>=1.7.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from openai<2.0.0,>=1.99.9->langchain-openai) (1.9.0)\n", - "Requirement already satisfied: httpx<1,>=0.23.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from openai<2.0.0,>=1.99.9->langchain-openai) (0.28.1)\n", - "Requirement already satisfied: jiter<1,>=0.4.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from openai<2.0.0,>=1.99.9->langchain-openai) (0.10.0)\n", - "Requirement already satisfied: tqdm>4 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from openai<2.0.0,>=1.99.9->langchain-openai) (4.67.1)\n", - "Requirement already satisfied: httpcore==1.* in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from httpx<1,>=0.23.0->openai<2.0.0,>=1.99.9->langchain-openai) (1.0.9)\n", - "Requirement already satisfied: regex>=2022.1.18 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from tiktoken<1,>=0.7->langchain-openai) (2024.11.6)\n", - "Requirement already satisfied: aiohttp<4.0.0,>=3.8.3 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-community) (3.12.13)\n", - "Requirement already satisfied: dataclasses-json<0.7,>=0.5.7 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-community) (0.6.7)\n", - "Requirement already satisfied: pydantic-settings<3.0.0,>=2.4.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-community) (2.10.1)\n", - "Requirement already satisfied: httpx-sse<1.0.0,>=0.4.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-community) (0.4.1)\n", - "Requirement already satisfied: numpy>=1.26.2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langchain-community) (2.3.1)\n", - "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (2.6.1)\n", - "Requirement already satisfied: aiosignal>=1.1.2 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (1.4.0)\n", - "Requirement already satisfied: attrs>=17.3.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (25.3.0)\n", - "Requirement already satisfied: frozenlist>=1.1.1 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (1.7.0)\n", - "Requirement already satisfied: multidict<7.0,>=4.5 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (6.6.3)\n", - "Requirement already satisfied: propcache>=0.2.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (0.3.2)\n", - "Requirement already satisfied: yarl<2.0,>=1.17.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from aiohttp<4.0.0,>=3.8.3->langchain-community) (1.20.1)\n", - "Requirement already satisfied: marshmallow<4.0.0,>=3.18.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from dataclasses-json<0.7,>=0.5.7->langchain-community) (3.26.1)\n", - "Requirement already satisfied: typing-inspect<1,>=0.4.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from dataclasses-json<0.7,>=0.5.7->langchain-community) (0.9.0)\n", - "Requirement already satisfied: python-dotenv>=0.21.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from pydantic-settings<3.0.0,>=2.4.0->langchain-community) (1.1.1)\n", - "Requirement already satisfied: mypy-extensions>=0.3.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from typing-inspect<1,>=0.4.0->dataclasses-json<0.7,>=0.5.7->langchain-community) (1.1.0)\n", - "Requirement already satisfied: orjson>=3.9.14 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langsmith>=0.1.17->langchain>=0.2) (3.10.18)\n", - "Requirement already satisfied: requests-toolbelt>=1.0.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langsmith>=0.1.17->langchain>=0.2) (1.0.0)\n", - "Requirement already satisfied: zstandard>=0.23.0 in /Users/swapna942/miniconda3/lib/python3.12/site-packages (from langsmith>=0.1.17->langchain>=0.2) (0.23.0)\n" - ] - } - ], - "source": [ - "!pip install fastapi uvicorn \"langchain>=0.2\" langchain-openai \\\n", - " langchain-community langchain-text-splitters \\\n", - " faiss-cpu" - ] - }, - { - "cell_type": "markdown", - "id": "wmt9jvqzh7n", - "metadata": {}, - "source": [ - "### 2. LlamaStack Server Setup\n", - "\n", - "#### Build and Start LlamaStack Server\n", - "\n", - "This section sets up the LlamaStack server with:\n", - "- **Together AI** as the inference provider\n", - "- **FAISS** as the vector database\n", - "- **Sentence Transformers** for embeddings\n", - "\n", - "The server runs on `localhost:8321` and provides OpenAI-compatible endpoints." - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "dd2dacf3-ec8b-4cc7-8ff4-b5b6ea4a6e9e", - "metadata": { - "scrolled": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Requirement already satisfied: uv in /Users/swapna942/miniconda3/lib/python3.12/site-packages (0.7.20)\n", - "Environment '/Users/swapna942/llama-stack/.venv' already exists, re-using it.\n", - "Virtual environment /Users/swapna942/llama-stack/.venv is already active\n", - "\u001b[2mAudited \u001b[1m1 package\u001b[0m \u001b[2min 86ms\u001b[0m\u001b[0m\n", - "Installing pip dependencies\n", - "\u001b[2K\u001b[2mResolved \u001b[1m178 packages\u001b[0m \u001b[2min 462ms\u001b[0m\u001b[0m \u001b[0m\n", - "\u001b[2mUninstalled \u001b[1m2 packages\u001b[0m \u001b[2min 28ms\u001b[0m\u001b[0m\n", - "\u001b[2K\u001b[2mInstalled \u001b[1m2 packages\u001b[0m \u001b[2min 5ms\u001b[0m\u001b[0m \u001b[0m\n", - " \u001b[31m-\u001b[39m \u001b[1mprotobuf\u001b[0m\u001b[2m==5.29.5\u001b[0m\n", - " \u001b[32m+\u001b[39m \u001b[1mprotobuf\u001b[0m\u001b[2m==5.29.4\u001b[0m\n", - " \u001b[31m-\u001b[39m \u001b[1mruff\u001b[0m\u001b[2m==0.12.5\u001b[0m\n", - " \u001b[32m+\u001b[39m \u001b[1mruff\u001b[0m\u001b[2m==0.9.10\u001b[0m\n", - "Installing special provider module: torch torchvision --index-url https://download.pytorch.org/whl/cpu\n", - "\u001b[2mAudited \u001b[1m2 packages\u001b[0m \u001b[2min 5ms\u001b[0m\u001b[0m\n", - "Installing special provider module: sentence-transformers --no-deps\n", - "\u001b[2mAudited \u001b[1m1 package\u001b[0m \u001b[2min 9ms\u001b[0m\u001b[0m\n", - "\u001b[32mBuild Successful!\u001b[0m\n", - "\u001b[34mYou can find the newly-built distribution here: /Users/swapna942/.llama/distributions/starter/starter-run.yaml\u001b[0m\n", - "\u001b[32mYou can run the new Llama Stack distro via: \u001b[34mllama stack run /Users/swapna942/.llama/distributions/starter/starter-run.yaml --image-type venv\u001b[0m\u001b[0m\n" - ] - } - ], - "source": [ - "import os\n", - "import subprocess\n", - "import time\n", - "\n", - "!pip install uv\n", - "\n", - "if \"UV_SYSTEM_PYTHON\" in os.environ:\n", - " del os.environ[\"UV_SYSTEM_PYTHON\"]\n", - "\n", - "# this command installs all the dependencies needed for the llama stack server with the together inference provider\n", - "!uv run --with llama-stack llama stack build --distro starter --image-type venv\n", - "\n", - "\n", - "def run_llama_stack_server_background():\n", - " log_file = open(\"llama_stack_server.log\", \"w\")\n", - " process = subprocess.Popen(\n", - " \"uv run --with llama-stack llama stack run /Users/swapna942/.llama/distributions/starter/starter-run.yaml --image-type venv\",\n", - " shell=True,\n", - " stdout=log_file,\n", - " stderr=log_file,\n", - " text=True,\n", - " )\n", - "\n", - " print(f\"Starting Llama Stack server with PID: {process.pid}\")\n", - " return process\n", - "\n", - "\n", - "def wait_for_server_to_start():\n", - " import requests\n", - " from requests.exceptions import ConnectionError\n", - "\n", - " url = \"http://0.0.0.0:8321/v1/health\"\n", - " max_retries = 30\n", - " retry_interval = 1\n", - "\n", - " print(\"Waiting for server to start\", end=\"\")\n", - " for _ in range(max_retries):\n", - " try:\n", - " response = requests.get(url)\n", - " if response.status_code == 200:\n", - " print(\"\\nServer is ready!\")\n", - " return True\n", - " except ConnectionError:\n", - " print(\".\", end=\"\", flush=True)\n", - " time.sleep(retry_interval)\n", - "\n", - " print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n", - " return False\n", - "\n", - "\n", - "# use this helper if needed to kill the server\n", - "def kill_llama_stack_server():\n", - " # Kill any existing llama stack server processes\n", - " os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "28bd8dbd-4576-4e76-813f-21ab94db44a2", - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Starting Llama Stack server with PID: 99016\n", - "Waiting for server to start....\n", - "Server is ready!\n" - ] - } - ], - "source": [ - "server_process = run_llama_stack_server_background()\n", - "assert wait_for_server_to_start()" - ] - }, - { - "cell_type": "markdown", - "id": "gr9cdcg4r7n", - "metadata": {}, - "source": [ - "#### Install LlamaStack Client\n", - "\n", - "Install the client library to interact with the LlamaStack server." - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "487d2dbc-d071-400e-b4f0-dcee58f8dc95", - "metadata": { - "scrolled": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Requirement already satisfied: llama_stack_client in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (0.2.17)\n", - "Requirement already satisfied: anyio<5,>=3.5.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (4.9.0)\n", - "Requirement already satisfied: click in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (8.2.1)\n", - "Requirement already satisfied: distro<2,>=1.7.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (1.9.0)\n", - "Requirement already satisfied: fire in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (0.7.0)\n", - "Requirement already satisfied: httpx<1,>=0.23.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (0.28.1)\n", - "Requirement already satisfied: pandas in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (2.3.1)\n", - "Requirement already satisfied: prompt-toolkit in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (3.0.51)\n", - "Requirement already satisfied: pyaml in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (25.7.0)\n", - "Requirement already satisfied: pydantic<3,>=1.9.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (2.11.7)\n", - "Requirement already satisfied: requests in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (2.32.4)\n", - "Requirement already satisfied: rich in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (14.1.0)\n", - "Requirement already satisfied: sniffio in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (1.3.1)\n", - "Requirement already satisfied: termcolor in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (3.1.0)\n", - "Requirement already satisfied: tqdm in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (4.67.1)\n", - "Requirement already satisfied: typing-extensions<5,>=4.7 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from llama_stack_client) (4.14.1)\n", - "Requirement already satisfied: idna>=2.8 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from anyio<5,>=3.5.0->llama_stack_client) (3.10)\n", - "Requirement already satisfied: certifi in /opt/homebrew/opt/certifi/lib/python3.13/site-packages (from httpx<1,>=0.23.0->llama_stack_client) (2025.8.3)\n", - "Requirement already satisfied: httpcore==1.* in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from httpx<1,>=0.23.0->llama_stack_client) (1.0.9)\n", - "Requirement already satisfied: h11>=0.16 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from httpcore==1.*->httpx<1,>=0.23.0->llama_stack_client) (0.16.0)\n", - "Requirement already satisfied: annotated-types>=0.6.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pydantic<3,>=1.9.0->llama_stack_client) (0.7.0)\n", - "Requirement already satisfied: pydantic-core==2.33.2 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pydantic<3,>=1.9.0->llama_stack_client) (2.33.2)\n", - "Requirement already satisfied: typing-inspection>=0.4.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pydantic<3,>=1.9.0->llama_stack_client) (0.4.1)\n", - "Requirement already satisfied: numpy>=1.26.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pandas->llama_stack_client) (2.3.2)\n", - "Requirement already satisfied: python-dateutil>=2.8.2 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pandas->llama_stack_client) (2.9.0.post0)\n", - "Requirement already satisfied: pytz>=2020.1 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pandas->llama_stack_client) (2025.2)\n", - "Requirement already satisfied: tzdata>=2022.7 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pandas->llama_stack_client) (2025.2)\n", - "Requirement already satisfied: six>=1.5 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from python-dateutil>=2.8.2->pandas->llama_stack_client) (1.17.0)\n", - "Requirement already satisfied: wcwidth in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from prompt-toolkit->llama_stack_client) (0.2.13)\n", - "Requirement already satisfied: PyYAML in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from pyaml->llama_stack_client) (6.0.2)\n", - "Requirement already satisfied: charset_normalizer<4,>=2 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from requests->llama_stack_client) (3.4.2)\n", - "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from requests->llama_stack_client) (2.5.0)\n", - "Requirement already satisfied: markdown-it-py>=2.2.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from rich->llama_stack_client) (4.0.0)\n", - "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from rich->llama_stack_client) (2.19.2)\n", - "Requirement already satisfied: mdurl~=0.1 in /opt/homebrew/Cellar/jupyterlab/4.4.5/libexec/lib/python3.13/site-packages (from markdown-it-py>=2.2.0->rich->llama_stack_client) (0.1.2)\n" - ] - }, - { - "data": { - "text/plain": [ - "0" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "import sys\n", - "\n", - "# Install directly to the current Python environment\n", - "subprocess.check_call([sys.executable, \"-m\", \"pip\", \"install\", \"llama_stack_client\"])" - ] - }, - { - "cell_type": "markdown", - "id": "0j5hag7l9x89", - "metadata": {}, - "source": [ - "### 3. Initialize LlamaStack Client\n", - "\n", - "Create a client connection to the LlamaStack server with API keys for different providers:\n", - "\n", - "- **OpenAI API Key**: For OpenAI models\n", - "- **Gemini API Key**: For Google's Gemini models \n", - "- **Together API Key**: For Together AI models\n", - "\n" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "ab4eff97-4565-4c73-b1b3-0020a4c7e2a5", - "metadata": {}, - "outputs": [], - "source": [ - "from llama_stack_client import LlamaStackClient\n", - "\n", - "client = LlamaStackClient(\n", - " base_url=\"http://0.0.0.0:8321\",\n", - " provider_data={\"openai_api_key\": \"****\", \"gemini_api_key\": \"****\", \"together_api_key\": \"****\"},\n", - ")" - ] - }, - { - "cell_type": "markdown", - "id": "vwhexjy1e8o", - "metadata": {}, - "source": [ - "#### Explore Available Models and Safety Features\n", - "\n", - "Check what models and safety shields are available through your LlamaStack instance." - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "880443ef-ac3c-48b1-a80a-7dab5b25ac61", - "metadata": { - "scrolled": true - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: GET http://0.0.0.0:8321/v1/models \"HTTP/1.1 200 OK\"\n", - "INFO:httpx:HTTP Request: GET http://0.0.0.0:8321/v1/shields \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Available models:\n", - "- all-minilm\n", - "- ollama/all-minilm:l6-v2\n", - "- ollama/llama-guard3:1b\n", - "- ollama/llama-guard3:8b\n", - "- ollama/llama3.2:3b-instruct-fp16\n", - "- ollama/nomic-embed-text\n", - "- fireworks/accounts/fireworks/models/llama-v3p1-8b-instruct\n", - "- fireworks/accounts/fireworks/models/llama-v3p1-70b-instruct\n", - "- fireworks/accounts/fireworks/models/llama-v3p1-405b-instruct\n", - "- fireworks/accounts/fireworks/models/llama-v3p2-3b-instruct\n", - "- fireworks/accounts/fireworks/models/llama-v3p2-11b-vision-instruct\n", - "- fireworks/accounts/fireworks/models/llama-v3p2-90b-vision-instruct\n", - "- fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct\n", - "- fireworks/accounts/fireworks/models/llama4-scout-instruct-basic\n", - "- fireworks/accounts/fireworks/models/llama4-maverick-instruct-basic\n", - "- fireworks/nomic-ai/nomic-embed-text-v1.5\n", - "- fireworks/accounts/fireworks/models/llama-guard-3-8b\n", - "- fireworks/accounts/fireworks/models/llama-guard-3-11b-vision\n", - "- together/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo\n", - "- together/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\n", - "- together/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo\n", - "- together/meta-llama/Llama-3.2-3B-Instruct-Turbo\n", - "- together/meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo\n", - "- together/meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo\n", - "- together/meta-llama/Llama-3.3-70B-Instruct-Turbo\n", - "- together/togethercomputer/m2-bert-80M-8k-retrieval\n", - "- together/togethercomputer/m2-bert-80M-32k-retrieval\n", - "- together/meta-llama/Llama-4-Scout-17B-16E-Instruct\n", - "- together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8\n", - "- together/meta-llama/Llama-Guard-3-8B\n", - "- together/meta-llama/Llama-Guard-3-11B-Vision-Turbo\n", - "- bedrock/meta.llama3-1-8b-instruct-v1:0\n", - "- bedrock/meta.llama3-1-70b-instruct-v1:0\n", - "- bedrock/meta.llama3-1-405b-instruct-v1:0\n", - "- openai/gpt-3.5-turbo-0125\n", - "- openai/gpt-3.5-turbo\n", - "- openai/gpt-3.5-turbo-instruct\n", - "- openai/gpt-4\n", - "- openai/gpt-4-turbo\n", - "- openai/gpt-4o\n", - "- openai/gpt-4o-2024-08-06\n", - "- openai/gpt-4o-mini\n", - "- openai/gpt-4o-audio-preview\n", - "- openai/chatgpt-4o-latest\n", - "- openai/o1\n", - "- openai/o1-mini\n", - "- openai/o3-mini\n", - "- openai/o4-mini\n", - "- openai/text-embedding-3-small\n", - "- openai/text-embedding-3-large\n", - "- anthropic/claude-3-5-sonnet-latest\n", - "- anthropic/claude-3-7-sonnet-latest\n", - "- anthropic/claude-3-5-haiku-latest\n", - "- anthropic/voyage-3\n", - "- anthropic/voyage-3-lite\n", - "- anthropic/voyage-code-3\n", - "- gemini/gemini-1.5-flash\n", - "- gemini/gemini-1.5-pro\n", - "- gemini/gemini-2.0-flash\n", - "- gemini/gemini-2.0-flash-lite\n", - "- gemini/gemini-2.5-flash\n", - "- gemini/gemini-2.5-flash-lite\n", - "- gemini/gemini-2.5-pro\n", - "- gemini/text-embedding-004\n", - "- groq/llama3-8b-8192\n", - "- groq/llama-3.1-8b-instant\n", - "- groq/llama3-70b-8192\n", - "- groq/llama-3.3-70b-versatile\n", - "- groq/llama-3.2-3b-preview\n", - "- groq/meta-llama/llama-4-scout-17b-16e-instruct\n", - "- groq/meta-llama/llama-4-maverick-17b-128e-instruct\n", - "- sambanova/Meta-Llama-3.1-8B-Instruct\n", - "- sambanova/Meta-Llama-3.3-70B-Instruct\n", - "- sambanova/Llama-4-Maverick-17B-128E-Instruct\n", - "- sentence-transformers/all-MiniLM-L6-v2\n", - "----\n", - "Available shields (safety models):\n", - "code-scanner\n", - "llama-guard\n", - "----\n" - ] - } - ], - "source": [ - "print(\"Available models:\")\n", - "for m in client.models.list():\n", - " print(f\"- {m.identifier}\")\n", - "\n", - "print(\"----\")\n", - "print(\"Available shields (safety models):\")\n", - "for s in client.shields.list():\n", - " print(s.identifier)\n", - "print(\"----\")" - ] - }, - { - "cell_type": "markdown", - "id": "gojp7at31ht", - "metadata": {}, - "source": [ - "### 4. Vector Database Setup\n", - "\n", - "#### Register a Vector Database\n", - "\n", - "Create a FAISS vector database for storing document embeddings:\n", - "\n", - "- **Vector DB ID**: Unique identifier for the database\n", - "- **Provider**: FAISS (Facebook AI Similarity Search)\n", - "- **Embedding Model**: Sentence Transformers model for text embeddings\n", - "- **Dimensions**: 384-dimensional embeddings" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "id": "a16e2885-ae70-4fa6-9778-2433fa4dbfff", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/vector-dbs \"HTTP/1.1 200 OK\"\n", - "INFO:httpx:HTTP Request: GET http://0.0.0.0:8321/v1/vector-dbs \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Registered new vector DB: VectorDBRegisterResponse(embedding_dimension=384, embedding_model='sentence-transformers/all-MiniLM-L6-v2', identifier='acme_docs', provider_id='faiss', type='vector_db', provider_resource_id='acme_docs_v2', owner=None, source='via_register_api', vector_db_name=None)\n", - "Existing vector DBs: [VectorDBListResponseItem(embedding_dimension=384, embedding_model='sentence-transformers/all-MiniLM-L6-v2', identifier='acme_docs', provider_id='faiss', type='vector_db', provider_resource_id='acme_docs_v2', vector_db_name=None)]\n" - ] - } - ], - "source": [ - "# Register a new clean vector database\n", - "vector_db = client.vector_dbs.register(\n", - " vector_db_id=\"acme_docs\", # Use a new unique name\n", - " provider_id=\"faiss\",\n", - " provider_vector_db_id=\"acme_docs_v2\",\n", - " embedding_model=\"sentence-transformers/all-MiniLM-L6-v2\",\n", - " embedding_dimension=384,\n", - ")\n", - "print(\"Registered new vector DB:\", vector_db)\n", - "\n", - "# List all registered vector databases\n", - "dbs = client.vector_dbs.list()\n", - "print(\"Existing vector DBs:\", dbs)" - ] - }, - { - "cell_type": "markdown", - "id": "pcgjqzfr3eo", - "metadata": {}, - "source": [ - "#### Prepare Sample Documents\n", - "\n", - "Create LLAMA Stack Chunks for FAISS vector store" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "5a0a6619-c9fb-4938-8ff3-f84304eed91e", - "metadata": {}, - "outputs": [], - "source": [ - "from llama_stack_client.types.vector_io_insert_params import Chunk\n", - "\n", - "docs = [\n", - " (\"Acme ships globally in 3-5 business days.\", {\"title\": \"Shipping Policy\"}),\n", - " (\"Returns are accepted within 30 days of purchase.\", {\"title\": \"Returns Policy\"}),\n", - " (\"Support is available 24/7 via chat and email.\", {\"title\": \"Support\"}),\n", - "]\n", - "\n", - "# Convert to Chunk objects\n", - "chunks = []\n", - "for _, (content, metadata) in enumerate(docs):\n", - " # Transform metadata to required format with document_id from title\n", - " metadata = {\"document_id\": metadata[\"title\"]}\n", - " chunk = Chunk(\n", - " content=content, # Required[InterleavedContent]\n", - " metadata=metadata, # Required[Dict]\n", - " )\n", - " chunks.append(chunk)" - ] - }, - { - "cell_type": "markdown", - "id": "6bg3sm2ko5g", - "metadata": {}, - "source": [ - "#### Insert Documents into Vector Database\n", - "\n", - "Store the prepared documents in the FAISS vector database. This process:\n", - "1. Generates embeddings for each document\n", - "2. Stores embeddings with metadata\n", - "3. Enables semantic search capabilities" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "id": "0e8740d8-b809-44b9-915f-1e0200e3c3f1", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/vector-io/insert \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Documents inserted: None\n" - ] - } - ], - "source": [ - "# Insert chunks into FAISS vector store\n", - "\n", - "response = client.vector_io.insert(vector_db_id=\"acme_docs\", chunks=chunks)\n", - "print(\"Documents inserted:\", response)" - ] - }, - { - "cell_type": "markdown", - "id": "9061tmi1zpq", - "metadata": {}, - "source": [ - "#### Test Vector Search\n", - "\n", - "Query the vector database to verify it's working correctly. This performs semantic search to find relevant documents based on the query." - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "id": "4a5e010c-eeeb-4020-a957-74d6d1cba342", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/vector-io/query \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata : {'document_id': 'Shipping Policy'}\n", - "content : Acme ships globally in 3–5 business days.\n", - "metadata : {'document_id': 'Shipping Policy'}\n", - "content : Acme ships globally in 3–5 business days.\n", - "metadata : {'document_id': 'Returns Policy'}\n", - "content : Returns are accepted within 30 days of purchase.\n" - ] - } - ], - "source": [ - "# Query chunks from FAISS vector store\n", - "\n", - "query_chunk_response = client.vector_io.query(\n", - " vector_db_id=\"acme_docs\",\n", - " query=\"How long does Acme take to ship orders?\",\n", - ")\n", - "for chunk in query_chunk_response.chunks:\n", - " print(\"metadata\", \":\", chunk.metadata)\n", - " print(\"content\", \":\", chunk.content)" - ] - }, - { - "cell_type": "markdown", - "id": "usne6mbspms", - "metadata": {}, - "source": [ - "### 5. LangChain Integration\n", - "\n", - "#### Configure LangChain with LlamaStack\n", - "\n", - "Set up LangChain to use LlamaStack's OpenAI-compatible API:\n", - "\n", - "- **Base URL**: Points to LlamaStack's OpenAI endpoint\n", - "- **Headers**: Include Together AI API key for model access\n", - "- **Model**: Use Meta Llama 3.1 8B model via Together AI" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "id": "c378bd10-09c2-417c-bdfc-1e0a2dd19084", - "metadata": {}, - "outputs": [], - "source": [ - "import os\n", - "\n", - "from langchain_openai import ChatOpenAI\n", - "\n", - "# Point LangChain to Llamastack Server\n", - "os.environ[\"OPENAI_API_KEY\"] = \"dummy\"\n", - "os.environ[\"OPENAI_BASE_URL\"] = \"http://0.0.0.0:8321/v1/openai/v1\"\n", - "\n", - "# LLM from Llamastack together model\n", - "llm = ChatOpenAI(\n", - " model=\"together/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo\",\n", - " default_headers={\"X-LlamaStack-Provider-Data\": '{\"together_api_key\": \"***\"}'},\n", - ")" - ] - }, - { - "cell_type": "markdown", - "id": "5a4ddpcuk3l", - "metadata": {}, - "source": [ - "#### Test LLM Connection\n", - "\n", - "Verify that LangChain can successfully communicate with the LlamaStack server." - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "id": "f88ffb5a-657b-4916-9375-c6ddc156c25e", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/openai/v1/chat/completions \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "data": { - "text/plain": [ - "AIMessage(content=\"In the Andes, a gentle soul resides, \\nA llama's soft eyes, with kindness abide.\", additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 22, 'prompt_tokens': 50, 'total_tokens': 72, 'completion_tokens_details': None, 'prompt_tokens_details': None, 'cached_tokens': 0}, 'model_name': 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo', 'system_fingerprint': None, 'id': 'o86Jy3i-2j9zxn-972d7b27f8f22aaa', 'service_tier': None, 'finish_reason': 'stop', 'logprobs': None}, id='run--4797f8b9-a5f6-4730-aece-80c1fd88ac55-0', usage_metadata={'input_tokens': 50, 'output_tokens': 22, 'total_tokens': 72, 'input_token_details': {}, 'output_token_details': {}})" - ] - }, - "execution_count": 12, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "# Test llm with simple message\n", - "messages = [\n", - " {\"role\": \"system\", \"content\": \"You are a friendly assistant.\"},\n", - " {\"role\": \"user\", \"content\": \"Write a two-sentence poem about llama.\"},\n", - "]\n", - "llm.invoke(messages)" - ] - }, - { - "cell_type": "markdown", - "id": "0xh0jg6a0l4a", - "metadata": {}, - "source": [ - "### 6. Building the RAG Chain\n", - "\n", - "#### Create a Complete RAG Pipeline\n", - "\n", - "Build a LangChain pipeline that combines:\n", - "\n", - "1. **Vector Search**: Query LlamaStack's vector database\n", - "2. **Context Assembly**: Format retrieved documents\n", - "3. **Prompt Template**: Structure the input for the LLM\n", - "4. **LLM Generation**: Generate answers using context\n", - "5. **Output Parsing**: Extract the final response\n", - "\n", - "**Chain Flow**: `Query → Vector Search → Context + Question → LLM → Response`" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "9684427d-dcc7-4544-9af5-8b110d014c42", - "metadata": {}, - "outputs": [], - "source": [ - "# LangChain for prompt template and chaining + LLAMA Stack Client Vector DB and LLM chat completion\n", - "from langchain_core.output_parsers import StrOutputParser\n", - "from langchain_core.prompts import ChatPromptTemplate\n", - "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n", - "\n", - "\n", - "def join_docs(docs):\n", - " return \"\\n\\n\".join([f\"[{d.metadata.get('document_id')}] {d.content}\" for d in docs.chunks])\n", - "\n", - "\n", - "PROMPT = ChatPromptTemplate.from_messages(\n", - " [\n", - " (\"system\", \"You are a helpful assistant. Use the following context to answer.\"),\n", - " (\"user\", \"Question: {question}\\n\\nContext:\\n{context}\"),\n", - " ]\n", - ")\n", - "\n", - "vector_step = RunnableLambda(\n", - " lambda x: client.vector_io.query(\n", - " vector_db_id=\"acme_docs\",\n", - " query=x,\n", - " )\n", - ")\n", - "\n", - "chain = (\n", - " {\"context\": vector_step | RunnableLambda(join_docs), \"question\": RunnablePassthrough()}\n", - " | PROMPT\n", - " | llm\n", - " | StrOutputParser()\n", - ")" - ] - }, - { - "cell_type": "markdown", - "id": "0onu6rhphlra", - "metadata": {}, - "source": [ - "### 7. Testing the RAG System\n", - "\n", - "#### Example 1: Shipping Query" - ] - }, - { - "cell_type": "code", - "execution_count": 14, - "id": "03322188-9509-446a-a4a8-ce3bb83ec87c", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/vector-io/query \"HTTP/1.1 200 OK\"\n", - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/openai/v1/chat/completions \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "❓ How long does shipping take?\n", - "💡 According to the Shipping Policy, shipping from Acme takes 3-5 business days.\n" - ] - } - ], - "source": [ - "query = \"How long does shipping take?\"\n", - "response = chain.invoke(query)\n", - "print(\"❓\", query)\n", - "print(\"💡\", response)" - ] - }, - { - "cell_type": "markdown", - "id": "b7krhqj88ku", - "metadata": {}, - "source": [ - "#### Example 2: Returns Policy Query" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "id": "61995550-bb0b-46a8-a5d0-023207475d60", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/vector-io/query \"HTTP/1.1 200 OK\"\n", - "INFO:httpx:HTTP Request: POST http://0.0.0.0:8321/v1/openai/v1/chat/completions \"HTTP/1.1 200 OK\"\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "❓ Can I return a product after 40 days?\n", - "💡 Based on the provided returns policy, it appears that returns are only accepted within 30 days of purchase. Since you're asking about returning a product after 40 days, it would not be within the specified 30-day return window.\n", - "\n", - "Unfortunately, it seems that you would not be eligible for a return in this case. However, I would recommend reaching out to the support team via chat or email to confirm their policy and see if there are any exceptions or alternative solutions available.\n" - ] - } - ], - "source": [ - "query = \"Can I return a product after 40 days?\"\n", - "response = chain.invoke(query)\n", - "print(\"❓\", query)\n", - "print(\"💡\", response)" - ] - }, - { - "cell_type": "markdown", - "id": "h4w24fadvjs", - "metadata": {}, - "source": [ - "---\n", - "We have successfully built a RAG system that combines:\n", - "\n", - "- **LlamaStack** for infrastructure (LLM serving + vector database)\n", - "- **LangChain** for orchestration (prompts + chains)\n", - "- **Together AI** for high-quality language models\n", - "\n", - "### Key Benefits\n", - "\n", - "1. **Unified Infrastructure**: Single server for LLMs and vector databases\n", - "2. **OpenAI Compatibility**: Easy integration with existing LangChain code\n", - "3. **Multi-Provider Support**: Switch between different LLM providers\n", - "4. **Production Ready**: Built-in safety shields and monitoring\n", - "\n", - "### Next Steps\n", - "\n", - "- Add more sophisticated document processing\n", - "- Implement conversation memory\n", - "- Add safety filtering and monitoring\n", - "- Scale to larger document collections\n", - "- Integrate with web frameworks like FastAPI or Streamlit\n", - "\n", - "---\n", - "\n", - "##### 🔧 Cleanup\n", - "\n", - "Don't forget to stop the LlamaStack server when you're done:\n", - "\n", - "```python\n", - "kill_llama_stack_server()\n", - "```" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "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": "3.13.5" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -}