diff --git a/notebooks/en/agent_data_analyst.ipynb b/notebooks/en/agent_data_analyst.ipynb index 51ea24f7..94009260 100644 --- a/notebooks/en/agent_data_analyst.ipynb +++ b/notebooks/en/agent_data_analyst.ipynb @@ -42,17 +42,17 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ - "from smolagents import HfApiModel, CodeAgent\n", + "from smolagents import InferenceClientModel, CodeAgent\n", "from huggingface_hub import login\n", "import os\n", "\n", "login(os.getenv(\"HUGGINGFACEHUB_API_TOKEN\"))\n", "\n", - "model = HfApiModel(\"meta-llama/Llama-3.1-70B-Instruct\")\n", + "model = InferenceClientModel(\"meta-llama/Llama-3.1-70B-Instruct\")\n", "\n", "agent = CodeAgent(\n", " tools=[],\n", diff --git a/notebooks/en/agent_rag.ipynb b/notebooks/en/agent_rag.ipynb index 5b481939..a442f157 100644 --- a/notebooks/en/agent_rag.ipynb +++ b/notebooks/en/agent_rag.ipynb @@ -219,7 +219,7 @@ "- *`tools`*: a list of tools that the agent will be able to call.\n", "- *`model`*: the LLM that powers the agent.\n", "\n", - "Our `model` must be a callable that takes as input a list of [messages](https://huggingface.co/docs/transformers/main/chat_templating) and returns text. It also needs to accept a `stop_sequences` argument that indicates when to stop its generation. For convenience, we directly use the `HfApiModel` class provided in the package to get a LLM engine that calls our [Inference API](https://huggingface.co/docs/api-inference/en/index).\n", + "Our `model` must be a callable that takes as input a list of [messages](https://huggingface.co/docs/transformers/main/chat_templating) and returns text. It also needs to accept a `stop_sequences` argument that indicates when to stop its generation. For convenience, we directly use the `InferenceClientModel` class provided in the package to get a LLM engine that calls our [Inference API](https://huggingface.co/docs/api-inference/en/index).\n", "\n", "And we use [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct), served for free on Hugging Face's Inference API!\n", "\n", @@ -232,9 +232,9 @@ "metadata": {}, "outputs": [], "source": [ - "from smolagents import HfApiModel, ToolCallingAgent\n", + "from smolagents import InferenceClientModel, ToolCallingAgent\n", "\n", - "model = HfApiModel(\"meta-llama/Llama-3.1-70B-Instruct\")\n", + "model = InferenceClientModel(\"meta-llama/Llama-3.1-70B-Instruct\")\n", "\n", "retriever_tool = RetrieverTool(vectordb)\n", "agent = ToolCallingAgent(\n", @@ -263,7 +263,7 @@ "│ │\n", "│ How can I push a model to the Hub? │\n", "│ │\n", - "╰─ HfApiModel - meta-llama/Llama-3.1-70B-Instruct ────────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - meta-llama/Llama-3.1-70B-Instruct ────────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -271,7 +271,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mHow can I push a model to the Hub?\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - meta-llama/Llama-3.1-70B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - meta-llama/Llama-3.1-70B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, diff --git a/notebooks/en/agent_text_to_sql.ipynb b/notebooks/en/agent_text_to_sql.ipynb index 32e50f59..efb53fd2 100644 --- a/notebooks/en/agent_text_to_sql.ipynb +++ b/notebooks/en/agent_text_to_sql.ipynb @@ -160,7 +160,7 @@ "\n", "We use the `CodeAgent`, which is `transformers.agents`' main agent class: an agent that writes actions in code and can iterate on previous output according to the ReAct framework.\n", "\n", - "The `llm_engine` is the LLM that powers the agent system. `HfApiModel` allows you to call LLMs using Hugging Face's Inference API, either via Serverless or Dedicated endpoint, but you could also use any proprietary API: check out [this other cookbook](agent_change_llm) to learn how to adapt it." + "The `llm_engine` is the LLM that powers the agent system. `InferenceClientModel` allows you to call LLMs using Hugging Face's Inference API, either via Serverless or Dedicated endpoint, but you could also use any proprietary API: check out [this other cookbook](agent_change_llm) to learn how to adapt it." ] }, { @@ -169,11 +169,11 @@ "metadata": {}, "outputs": [], "source": [ - "from smolagents import CodeAgent, HfApiModel\n", + "from smolagents import CodeAgent, InferenceClientModel\n", "\n", "agent = CodeAgent(\n", " tools=[sql_engine],\n", - " model=HfApiModel(\"meta-llama/Meta-Llama-3-8B-Instruct\"),\n", + " model=InferenceClientModel(\"meta-llama/Meta-Llama-3-8B-Instruct\"),\n", ")" ] }, @@ -189,7 +189,7 @@ "│ │\n", "│ Can you give me the name of the client who got the most expensive receipt? │\n", "│ │\n", - "╰─ HfApiModel - meta-llama/Meta-Llama-3-8B-Instruct ──────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - meta-llama/Meta-Llama-3-8B-Instruct ──────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -197,7 +197,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mCan you give me the name of the client who got the most expensive receipt?\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - meta-llama/Meta-Llama-3-8B-Instruct \u001b[0m\u001b[38;2;212;183;2m─────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - meta-llama/Meta-Llama-3-8B-Instruct \u001b[0m\u001b[38;2;212;183;2m─────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, @@ -396,7 +396,7 @@ "│ │\n", "│ Which waiter got more total money from tips? │\n", "│ │\n", - "╰─ HfApiModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -404,7 +404,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mWhich waiter got more total money from tips?\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, @@ -740,7 +740,7 @@ "\n", "agent = CodeAgent(\n", " tools=[sql_engine],\n", - " model=HfApiModel(\"Qwen/Qwen2.5-72B-Instruct\"),\n", + " model=InferenceClientModel(\"Qwen/Qwen2.5-72B-Instruct\"),\n", ")\n", "\n", "agent.run(\"Which waiter got more total money from tips?\")" diff --git a/notebooks/en/agents.ipynb b/notebooks/en/agents.ipynb index 82616038..049d079b 100644 --- a/notebooks/en/agents.ipynb +++ b/notebooks/en/agents.ipynb @@ -95,7 +95,7 @@ "│ │\n", "│ Generate me a photo of the car that James bond drove in the latest movie. │\n", "│ │\n", - "╰─ HfApiModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -103,7 +103,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mGenerate me a photo of the car that James bond drove in the latest movie.\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, @@ -549,7 +549,7 @@ } ], "source": [ - "from smolagents import load_tool, CodeAgent, HfApiModel, DuckDuckGoSearchTool\n", + "from smolagents import load_tool, CodeAgent, InferenceClientModel, DuckDuckGoSearchTool\n", "\n", "# Import tool from Hub\n", "image_generation_tool = load_tool(\"m-ric/text-to-image\", trust_remote_code=True)\n", @@ -557,7 +557,7 @@ "\n", "search_tool = DuckDuckGoSearchTool()\n", "\n", - "model = HfApiModel(\"Qwen/Qwen2.5-72B-Instruct\")\n", + "model = InferenceClientModel(\"Qwen/Qwen2.5-72B-Instruct\")\n", "# Initialize the agent with both tools\n", "agent = CodeAgent(\n", " tools=[image_generation_tool, search_tool], model=model\n", @@ -796,9 +796,9 @@ "metadata": {}, "outputs": [], "source": [ - "from smolagents import HfApiModel, ToolCallingAgent\n", + "from smolagents import InferenceClientModel, ToolCallingAgent\n", "\n", - "model = HfApiModel(\"Qwen/Qwen2.5-72B-Instruct\")\n", + "model = InferenceClientModel(\"Qwen/Qwen2.5-72B-Instruct\")\n", "\n", "retriever_tool = RetrieverTool(vectordb=vectordb, all_sources=all_sources)\n", "agent = ToolCallingAgent(tools=[retriever_tool], model=model, verbose=0)\n", @@ -840,7 +840,7 @@ "│ python code: │\n", "│ {'code': '\\nnumbers=[0, 1, 2]\\n\\nfor i in range(4):\\n print(numbers(i))\\n'}. │\n", "│ │\n", - "╰─ HfApiModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -852,7 +852,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mpython code:\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m{'code': '\\nnumbers=[0, 1, 2]\\n\\nfor i in range(4):\\n print(numbers(i))\\n'}.\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, @@ -1086,7 +1086,7 @@ "source": [ "from smolagents import CodeAgent\n", "\n", - "agent = CodeAgent(tools=[], model=HfApiModel(\"Qwen/Qwen2.5-72B-Instruct\"))\n", + "agent = CodeAgent(tools=[], model=InferenceClientModel(\"Qwen/Qwen2.5-72B-Instruct\"))\n", "\n", "code = \"\"\"\n", "numbers=[0, 1, 2]\n", diff --git a/notebooks/en/multiagent_rag_system.ipynb b/notebooks/en/multiagent_rag_system.ipynb index f348aeee..60b41058 100644 --- a/notebooks/en/multiagent_rag_system.ipynb +++ b/notebooks/en/multiagent_rag_system.ipynb @@ -151,10 +151,10 @@ }, "outputs": [], "source": [ - "from smolagents import HfApiModel\n", + "from smolagents import InferenceClientModel\n", "\n", "model_id = \"Qwen/Qwen2.5-72B-Instruct\"\n", - "model = HfApiModel(model_id)" + "model = InferenceClientModel(model_id)" ] }, { diff --git a/notebooks/en/multiagent_web_assistant.ipynb b/notebooks/en/multiagent_web_assistant.ipynb index 79796577..08acef03 100644 --- a/notebooks/en/multiagent_web_assistant.ipynb +++ b/notebooks/en/multiagent_web_assistant.ipynb @@ -199,12 +199,12 @@ "from smolagents import (\n", " CodeAgent,\n", " ToolCallingAgent,\n", - " HfApiModel,\n", + " InferenceClientModel,\n", " ManagedAgent,\n", " DuckDuckGoSearchTool\n", ")\n", "\n", - "model = HfApiModel(model_id)\n", + "model = InferenceClientModel(model_id)\n", "\n", "web_agent = ToolCallingAgent(\n", " tools=[DuckDuckGoSearchTool(), visit_webpage],\n", @@ -277,7 +277,7 @@ "│ │\n", "│ How many years ago was Stripe founded? │\n", "│ │\n", - "╰─ HfApiModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -285,7 +285,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mHow many years ago was Stripe founded?\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, @@ -348,7 +348,7 @@ "│ manager can act upon this feedback. │\n", "│ {additional_prompting} │\n", "│ │\n", - "╰─ HfApiModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", + "╰─ InferenceClientModel - Qwen/Qwen2.5-72B-Instruct ────────────────────────────────────────────────────────────────────────╯\n", "\n" ], "text/plain": [ @@ -374,7 +374,7 @@ "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1mmanager can act upon this feedback.\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[1m{additional_prompting}\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", "\u001b[38;2;212;183;2m│\u001b[0m \u001b[38;2;212;183;2m│\u001b[0m\n", - "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m HfApiModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" + "\u001b[38;2;212;183;2m╰─\u001b[0m\u001b[38;2;212;183;2m InferenceClientModel - Qwen/Qwen2.5-72B-Instruct \u001b[0m\u001b[38;2;212;183;2m───────────────────────────────────────────────────────────────────────\u001b[0m\u001b[38;2;212;183;2m─╯\u001b[0m\n" ] }, "metadata": {}, diff --git a/notebooks/zh-CN/agents.ipynb b/notebooks/zh-CN/agents.ipynb index d9975ccf..e7b2d469 100644 --- a/notebooks/zh-CN/agents.ipynb +++ b/notebooks/zh-CN/agents.ipynb @@ -164,18 +164,18 @@ }, { "ename": "ImportError", - "evalue": "cannot import name 'HfApiModel' from 'transformers' (/Users/aymeric/.pyenv/versions/3.12.0/lib/python3.12/site-packages/transformers/__init__.py)", + "evalue": "cannot import name 'InferenceClientModel' from 'transformers' (/Users/aymeric/.pyenv/versions/3.12.0/lib/python3.12/site-packages/transformers/__init__.py)", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[0;32mIn[3], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Tool, load_tool, CodeAgent, HfApiModel\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m# Import tool from Hub\u001b[39;00m\n\u001b[1;32m 4\u001b[0m image_generation_tool \u001b[38;5;241m=\u001b[39m load_tool(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mm-ric/text-to-image\u001b[39m\u001b[38;5;124m\"\u001b[39m, trust_remote_code\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n", - "\u001b[0;31mImportError\u001b[0m: cannot import name 'HfApiModel' from 'transformers' (/Users/aymeric/.pyenv/versions/3.12.0/lib/python3.12/site-packages/transformers/__init__.py)" + "Cell \u001b[0;32mIn[3], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Tool, load_tool, CodeAgent, InferenceClientModel\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m# Import tool from Hub\u001b[39;00m\n\u001b[1;32m 4\u001b[0m image_generation_tool \u001b[38;5;241m=\u001b[39m load_tool(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mm-ric/text-to-image\u001b[39m\u001b[38;5;124m\"\u001b[39m, trust_remote_code\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n", + "\u001b[0;31mImportError\u001b[0m: cannot import name 'InferenceClientModel' from 'transformers' (/Users/aymeric/.pyenv/versions/3.12.0/lib/python3.12/site-packages/transformers/__init__.py)" ] } ], "source": [ - "from transformers import Tool, load_tool, CodeAgent, HfApiModel\n", + "from transformers import Tool, load_tool, CodeAgent, InferenceClientModel\n", "\n", "# Import tool from Hub\n", "image_generation_tool = load_tool(\"m-ric/text-to-image\", trust_remote_code=True)\n", @@ -186,7 +186,7 @@ "search_tool = Tool.from_langchain(load_tools([\"serpapi\"])[0])\n", "\n", "\n", - "model = HfApiModel(\"meta-llama/Llama-3.1-70B-Instruct\")\n", + "model = InferenceClientModel(\"meta-llama/Llama-3.1-70B-Instruct\")\n", "# Initialize the agent with both tools\n", "agent = CodeAgent(\n", " tools=[image_generation_tool, search_tool], model=model\n",