KeyArgo
/
smolagents
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update guided_tour.md

This commit is contained in:
Aymeric Roucher 2025-01-06 15:05:54 +01:00 committed by GitHub
parent 82c374aa30
commit a6a4f48d2e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/source/en/guided_tour.md
View File

@ -23,15 +23,12 @@ In this guided visit, you will learn how to build an agent, how to run it, and h
To initialize a minimal agent, you need at least these two arguments: To initialize a minimal agent, you need at least these two arguments:
- An text-generation model to power your agent - because the agent is different from a simple LLM, it is a system that uses a LLM as its engine. - `model`, a text-generation model to power your agent - because the agent is different from a simple LLM, it is a system that uses a LLM as its engine. You can use any of these options:
- A list of tools - tools the agent can use to solve the task. - [`TransformersModel`] takes a pre-initialized `transformers` pipeline to run inference on your local machine using `transformers`.
- [`HfApiModel`] leverages a `huggingface_hub.InferenceClient` under the hood.
- [`LiteLLMModel`] lets you call 100+ different models through [LiteLLM](https://docs.litellm.ai/)!
For your model, you can use any of these options: - `tools`, A list of `Tools` that the agent can use to solve the task. It can be an empty list. You can also add the default toolbox on top of your `tools` list by defining the optional argument `add_base_tools=True`.
- [`TransformersModel`] takes a pre-initialized `transformers` pipeline to run inference on your local machine using `transformers`.
- [`HfApiModel`] leverages a `huggingface_hub.InferenceClient` under the hood.
- We also provide [`LiteLLMModel`], which lets you call 100+ different models through [LiteLLM](https://docs.litellm.ai/)!
You will also need a `tools` argument which accepts a list of `Tools` - it can be an empty list. You can also add the default toolbox on top of your `tools` list by defining the optional argument `add_base_tools=True`.
Once you have these two arguments, `tools` and `model`, you can create an agent and run it. Once you have these two arguments, `tools` and `model`, you can create an agent and run it.
@ -336,4 +333,4 @@ You can also use this `reset=False` argument to keep the conversation going in a
For more in-depth usage, you will then want to check out our tutorials: For more in-depth usage, you will then want to check out our tutorials:
- [the explanation of how our code agents work](./tutorials/secure_code_execution) - [the explanation of how our code agents work](./tutorials/secure_code_execution)
- [this guide on how to build good agents](./tutorials/building_good_agents). - [this guide on how to build good agents](./tutorials/building_good_agents).
- [the in-depth guide for tool usage](./tutorials/building_good_agents). - [the in-depth guide for tool usage](./tutorials/building_good_agents).