Skip to content

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Doc: Fcalling notes (#930)

Kilian Lierete1b869fa7c5d
diff --git a/docs/faq.md b/docs/faq.md
index 88130100..f0cd2638 100644
--- a/docs/faq.md
+++ b/docs/faq.md
@@ -4,6 +4,13 @@
Probably all of them! There's even a few for testing. See [models](installation/keys.md).
+> What can I do if my model doesn't support function calling?
+
+You can configure how to parse the model's response by choosing your `parse_function`.
+The default now is `function_calling`, but you can choose to `thought_action`.
+More information in the [reference](reference/parsers.md).
+There are also some config example in our [config folder](https://github.com/SWE-agent/SWE-agent/tree/main/config).
+
> What's up with all the output files?
You're probably most interested in the `*.traj` files, which contain complete records of SWE-agent's thought process and actions. See [output files](usage/trajectories.md) for more information.
diff --git a/docs/installation/keys.md b/docs/installation/keys.md
index 69430f53..fde8cd0a 100644
--- a/docs/installation/keys.md
+++ b/docs/installation/keys.md
@@ -34,6 +34,14 @@ Here are a few options for `--agent.model.name`:
| `gpt-4o` | `OPENAI_API_KEY` | |
| `o1-preview` | `OPENAI_API_KEY` | You might need to set temperature and sampling to the supported values. |
+!!! hint "Parsers"
+
+ The default config uses function calling to retrieve actions from the model response.
+ If your model doesn't support function calling, you can use the `thought_action` parser.
+ See [our API docs](../reference/parsers.md) for more details.
+ Remember to document the tools in your prompt as the model will not be able to see the function signature
+ like with function calling.
+
## Model options
See [our API docs](../reference/model_config.md) for more details.