Open-source, secure environment with real-world tools for enterprise-grade agents.
Python agentaiai-agentai-agentscode-interpretercopilotdevelopmentdevtoolsgptgpt-4javascriptllmnextjsopenaipythonreactsoftwaretypescript
Add hugging face to the quickstart guide (#726)
Vasek Mlejnskyaf0773b74ddd
diff --git a/apps/web/src/app/(docs)/docs/quickstart/connect-llms/page.mdx b/apps/web/src/app/(docs)/docs/quickstart/connect-llms/page.mdxindex 4975f8e21..bba3e0f72 100644--- a/apps/web/src/app/(docs)/docs/quickstart/connect-llms/page.mdx+++ b/apps/web/src/app/(docs)/docs/quickstart/connect-llms/page.mdx@@ -13,6 +13,7 @@ If the LLM doesn't support tool use, you can, for example, prompt the LLM to out- [LangChain](#langchain)- [LlamaIndex](#llamaindex)- [Ollama](#ollama)+- [Hugging Face](#hugging-face)---@@ -503,7 +504,7 @@ from crewai import Agent, Task, Crew, LLMfrom e2b_code_interpreter import Sandbox# Update tool definition using the decorator-@tool("Python Interpreter")+@tool("Python Interpreter")def execute_python(code: str) -> str:"""Execute Python code and return the results.@@ -741,3 +742,63 @@ with Sandbox() as sandbox:print(result)```</CodeGroup>++---++## Hugging Face++Hugging Face offers support for serverless inference for models on their model hub with [Hugging Face's Inference API](https://huggingface.co/docs/inference-providers/en/index).++<Note>+Note that not every model on Hugging Face has native support for tool use and function calling.+</Note>++<CodeGroup>+```python+from huggingface_hub import InferenceClient+from e2b_code_interpreter import Sandbox+import re++# Not all models are capable of direct tools use - we need to extract the code block manually and prompting the LLM to generate the code.+def match_code_block(llm_response):+ pattern = re.compile(r'```python\n(.*?)\n```', re.DOTALL) # Match everything in between ```python and ```+ match = pattern.search(llm_response)+ if match:+ code = match.group(1)+ print(code)+ return code+ return ""+++system_prompt = """You are a helpful coding assistant that can execute python code in a Jupyter notebook. You are given tasks to complete and you run Python code to solve them.+Generally, you follow these rules:+- ALWAYS FORMAT YOUR RESPONSE IN MARKDOWN+- ALWAYS RESPOND ONLY WITH CODE IN CODE BLOCK LIKE THIS:+\`\`\`python+{code}+\`\`\`+"""+prompt = "Calculate how many r's are in the word 'strawberry.'"++# Initialize the client+client = InferenceClient(+ provider="hf-inference",+ api_key="HF_INFERENCE_API_KEY"+)++completion = client.chat.completions.create(+ model="Qwen/Qwen3-235B-A22B", # Or use any other model from Hugging Face+ messages=[+ {"role": "system", "content": system_prompt},+ {"role": "user", "content": prompt},+ ]+)++content = completion.choices[0].message.content+code = match_code_block(content)++with Sandbox() as sandbox:+ execution = sandbox.run_code(code)+ print(execution)+```+</CodeGroup>\ No newline at end of file