Skip to content

fix: update context window information #401

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

fix: update context window information #401

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
6 changes: 3 additions & 3 deletions docs-site/content/30.0/api/conversational-search-rag.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -507,10 +507,10 @@ Rewrite the follow-up question on top of a human-assistant conversation history

The generated standalone question will be used for semantic/hybrid search within the collection, and the results will then be forwarded to the LLM as context for answering the generated standalone question.

:::tip Context Window Limits
Although we retain the entire conversation history in Typesense, only the most recent 3000 tokens (approximately 1200 characters) of the conversation history will be sent for generating the standalone question due to the context limit.
:::tip Context Window Limits
Although the entire conversation history is stored in Typesense, only the most recent messages that fit within the configured ```max_bytes``` window are sent when generating the standalone question. Before selecting messages, we subtracts the number of bytes required by the system instructions; the remaining byte budget determines how many recent messages can be included.
Copy link
Member

@jasonbosco jasonbosco Nov 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

typo: "Before selecting messages, we subtracts"


Similar to the conversation history, only the top search results, limited to 3000 tokens, will be sent along with the standalone question.
Similarly, for retrieval, only the top search results whose combined size fits within the remaining ```max_bytes``` limit are included alongside the standalone question.
:::

## Managing Past Conversations
Expand Down