Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix markdown for long context user guide #2351

Merged
merged 1 commit into from
Apr 11, 2024
Merged

fix markdown for long context user guide #2351

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions website/docs/topics/long_contexts.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@ Why do we need to handle long contexts? The problem arises from several constrai

The `TransformMessages` capability is designed to modify incoming messages before they are processed by the LLM agent. This can include limiting the number of messages, truncating messages to meet token limits, and more.

````{=mdx}
:::info Requirements
Install `pyautogen`:
```bash
Expand All @@ -21,7 +20,6 @@ pip install pyautogen

For more information, please refer to the [installation guide](/docs/installation/).
:::
````

### Exploring and Understanding Transformations

Expand Down Expand Up @@ -114,11 +112,9 @@ user_proxy = autogen.UserProxyAgent(
)
```

```{=mdx}
:::tip
Learn more about configuring LLMs for agents [here](/docs/topics/llm_configuration).
:::
```

We first need to write the `test` function that creates a very long chat history by exchanging messages between an assistant and a user proxy agent, and then attempts to initiate a new chat without clearing the history, potentially triggering an error due to token limits.

Expand Down
Loading