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

Minor grammar correction (#528)

This commit is contained in:
Sean Callan 2025-02-08 15:33:38 -05:00 committed by GitHub
parent fe92c82cb8
commit 63adfcd836
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/en/conceptual_guides/intro_agents.md
View File

@ -68,7 +68,7 @@ If that deterministic workflow fits all queries, by all means just code everythi
But what if the workflow can't be determined that well in advance? But what if the workflow can't be determined that well in advance?
For instance, a user wants to ask : `"I can come on Monday, but I forgot my passport so risk being delayed to Wednesday, is it possible to take me and my stuff to surf on Tuesday morning, with a cancellation insurance?"` This question hinges on many factors, and probably none of the predetermined criteria above will suffice for this request. For instance, a user wants to ask: `"I can come on Monday, but I forgot my passport so risk being delayed to Wednesday, is it possible to take me and my stuff to surf on Tuesday morning, with a cancellation insurance?"` This question hinges on many factors, and probably none of the predetermined criteria above will suffice for this request.
If the pre-determined workflow falls short too often, that means you need more flexibility. If the pre-determined workflow falls short too often, that means you need more flexibility.
@ -106,7 +106,7 @@ In a multi-step agent, at each step, the LLM can write an action, in the form of
The reason for this simply that *we crafted our code languages specifically to be the best possible way to express actions performed by a computer*. If JSON snippets were a better expression, JSON would be the top programming language and programming would be hell on earth. The reason for this simply that *we crafted our code languages specifically to be the best possible way to express actions performed by a computer*. If JSON snippets were a better expression, JSON would be the top programming language and programming would be hell on earth.
The figure below, taken from [Executable Code Actions Elicit Better LLM Agents](https://huggingface.co/papers/2402.01030), illustrate some advantages of writing actions in code: The figure below, taken from [Executable Code Actions Elicit Better LLM Agents](https://huggingface.co/papers/2402.01030), illustrates some advantages of writing actions in code:
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/code_vs_json_actions.png"> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/code_vs_json_actions.png">
@ -115,4 +115,4 @@ Writing actions in code rather than JSON-like snippets provides better:
- **Composability:** could you nest JSON actions within each other, or define a set of JSON actions to re-use later, the same way you could just define a python function? - **Composability:** could you nest JSON actions within each other, or define a set of JSON actions to re-use later, the same way you could just define a python function?
- **Object management:** how do you store the output of an action like `generate_image` in JSON? - **Object management:** how do you store the output of an action like `generate_image` in JSON?
- **Generality:** code is built to express simply anything you can have a computer do. - **Generality:** code is built to express simply anything you can have a computer do.
- **Representation in LLM training data:** plenty of quality code actions is already included in LLMs’ training data which means they’re already trained for this! - **Representation in LLM training data:** plenty of quality code actions are already included in LLMs’ training data which means they’re already trained for this!