{ "cells": [ { "cell_type": "markdown", "metadata": { "vscode": { "languageId": "plaintext" } }, "source": [ "# Agents dans LlamaIndex\n", "\n", "Ce notebook fait parti du cours sur les agents d'Hugging Face, un cours gratuit qui vous guidera, du **niveau débutant à expert**, pour comprendre, utiliser et construire des agents.\n", "\n", "![Agents course share](https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/share.png)\n", "\n", "## Installons les dépendances\n", "\n", "Nous allons installer les dépendances pour cette unité." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip install llama-index llama-index-vector-stores-chroma llama-index-llms-huggingface-api llama-index-embeddings-huggingface -U -q" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Nous allons également nous connecter au Hugging Face Hub pour avoir accès à l'API d'inférence." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from huggingface_hub import login\n", "\n", "login()" ] }, { "cell_type": "markdown", "metadata": { "vscode": { "languageId": "plaintext" } }, "source": [ "## Initialisation des agents\n", "\n", "Commençons par initialiser un agent. Nous allons utiliser la classe de base `AgentWorkflow` pour créer un agent." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n", "from llama_index.core.agent.workflow import AgentWorkflow, ToolCallResult, AgentStream\n", "\n", "\n", "def add(a: int, b: int) -> int:\n", " \"\"\"Add two numbers\"\"\"\n", " return a + b\n", "\n", "\n", "def subtract(a: int, b: int) -> int:\n", " \"\"\"Subtract two numbers\"\"\"\n", " return a - b\n", "\n", "\n", "def multiply(a: int, b: int) -> int:\n", " \"\"\"Multiply two numbers\"\"\"\n", " return a * b\n", "\n", "\n", "def divide(a: int, b: int) -> int:\n", " \"\"\"Divide two numbers\"\"\"\n", " return a / b\n", "\n", "\n", "llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n", "\n", "agent = AgentWorkflow.from_tools_or_functions(\n", " tools_or_functions=[subtract, multiply, divide, add],\n", " llm=llm,\n", " system_prompt=\"You are a math agent that can add, subtract, multiply, and divide numbers using provided tools.\",\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Ensuite, nous pouvons exécuter l'agent et obtenir la réponse et le raisonnement qui sous-tend les appels à l'outil." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "handler = agent.run(\"What is (2 + 2) * 2?\")\n", "async for ev in handler.stream_events():\n", " if isinstance(ev, ToolCallResult):\n", " print(\"\")\n", " print(\"Called tool: \", ev.tool_name, ev.tool_kwargs, \"=>\", ev.tool_output)\n", " elif isinstance(ev, AgentStream): # montrer le processus de réflexion\n", " print(ev.delta, end=\"\", flush=True)\n", "\n", "resp = await handler\n", "resp" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "De la même manière, nous pouvons transmettre l'état et le contexte à l'agent." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "AgentOutput(response=ChatMessage(role=, additional_kwargs={}, blocks=[TextBlock(block_type='text', text='Your name is Bob.')]), tool_calls=[], raw={'id': 'chatcmpl-B5sDHfGpSwsVyzvMVH8EWokYwdIKT', 'choices': [{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None}, 'finish_reason': 'stop', 'index': 0, 'logprobs': None}], 'created': 1740739735, 'model': 'gpt-4o-2024-08-06', 'object': 'chat.completion.chunk', 'service_tier': 'default', 'system_fingerprint': 'fp_eb9dce56a8', 'usage': None}, current_agent_name='Agent')" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from llama_index.core.workflow import Context\n", "\n", "ctx = Context(agent)\n", "\n", "response = await agent.run(\"My name is Bob.\", ctx=ctx)\n", "response = await agent.run(\"What was my name again?\", ctx=ctx)\n", "response" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Création d'agents de RAG avec QueryEngineTools\n", "\n", "Réutilisons maintenant le `QueryEngine` que nous avons défini dans [l'unité précédente sur les outils](/tools.ipynb) et convertissons-le en un `QueryEngineTool`. Nous allons le passer à la classe `AgentWorkflow` pour créer un agent de RAG." ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [], "source": [ "import chromadb\n", "\n", "from llama_index.core import VectorStoreIndex\n", "from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n", "from llama_index.embeddings.huggingface import HuggingFaceEmbedding\n", "from llama_index.core.tools import QueryEngineTool\n", "from llama_index.vector_stores.chroma import ChromaVectorStore\n", "\n", "# Créer un vector store\n", "db = chromadb.PersistentClient(path=\"./alfred_chroma_db\")\n", "chroma_collection = db.get_or_create_collection(\"alfred\")\n", "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n", "\n", "# Créer un moteur de recherche\n", "embed_model = HuggingFaceEmbedding(model_name=\"BAAI/bge-small-en-v1.5\")\n", "llm = HuggingFaceInferenceAPI(model_name=\"Qwen/Qwen2.5-Coder-32B-Instruct\")\n", "index = VectorStoreIndex.from_vector_store(\n", " vector_store=vector_store, embed_model=embed_model\n", ")\n", "query_engine = index.as_query_engine(llm=llm)\n", "query_engine_tool = QueryEngineTool.from_defaults(\n", " query_engine=query_engine,\n", " name=\"personas\",\n", " description=\"descriptions for various types of personas\",\n", " return_direct=False,\n", ")\n", "\n", "# Créer un agent de RAG\n", "query_engine_agent = AgentWorkflow.from_tools_or_functions(\n", " tools_or_functions=[query_engine_tool],\n", " llm=llm,\n", " system_prompt=\"You are a helpful assistant that has access to a database containing persona descriptions. \",\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Et nous pouvons une fois de plus obtenir la réponse et le raisonnement derrière les appels d'outils." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "handler = query_engine_agent.run(\n", " \"Search the database for 'science fiction' and return some persona descriptions.\"\n", ")\n", "async for ev in handler.stream_events():\n", " if isinstance(ev, ToolCallResult):\n", " print(\"\")\n", " print(\"Called tool: \", ev.tool_name, ev.tool_kwargs, \"=>\", ev.tool_output)\n", " elif isinstance(ev, AgentStream): # montrer le processus de réflexion\n", " print(ev.delta, end=\"\", flush=True)\n", "\n", "resp = await handler\n", "resp" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Créer des systèmes multi-agents\n", "\n", "Nous pouvons également créer des systèmes multi-agents en passant plusieurs agents à la classe `AgentWorkflow`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from llama_index.core.agent.workflow import (\n", " AgentWorkflow,\n", " ReActAgent,\n", ")\n", "\n", "\n", "# Définir quelques outils\n", "def add(a: int, b: int) -> int:\n", " \"\"\"Add two numbers.\"\"\"\n", " return a + b\n", "\n", "\n", "def subtract(a: int, b: int) -> int:\n", " \"\"\"Subtract two numbers.\"\"\"\n", " return a - b\n", "\n", "\n", "# Créer les configurations de l'agent\n", "# NOTE : nous pouvons utiliser FunctionAgent ou ReActAgent ici.\n", "# FunctionAgent fonctionne pour les LLM avec une API d'appel de fonction.\n", "# ReActAgent fonctionne pour n'importe quel LLM.\n", "calculator_agent = ReActAgent(\n", " name=\"calculator\",\n", " description=\"Performs basic arithmetic operations\",\n", " system_prompt=\"You are a calculator assistant. Use your tools for any math operation.\",\n", " tools=[add, subtract],\n", " llm=llm,\n", ")\n", "\n", "query_agent = ReActAgent(\n", " name=\"info_lookup\",\n", " description=\"Looks up information about XYZ\",\n", " system_prompt=\"Use your tool to query a RAG system to answer information about XYZ\",\n", " tools=[query_engine_tool],\n", " llm=llm,\n", ")\n", "\n", "# Créer et exécuter le workflow\n", "agent = AgentWorkflow(agents=[calculator_agent, query_agent], root_agent=\"calculator\")\n", "\n", "# Exécuter le système\n", "handler = agent.run(user_msg=\"Can you add 5 and 3?\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "async for ev in handler.stream_events():\n", " if isinstance(ev, ToolCallResult):\n", " print(\"\")\n", " print(\"Called tool: \", ev.tool_name, ev.tool_kwargs, \"=>\", ev.tool_output)\n", " elif isinstance(ev, AgentStream): # showing the thought process\n", " print(ev.delta, end=\"\", flush=True)\n", "\n", "resp = await handler\n", "resp" ] } ], "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": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 4 }