Skip to content

docs(agent): add guidance on output size limits for large result sets #735

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
firecrawl-spring wants to merge 1 commit into
base: main
Choose a base branch
from
Open

docs(agent): add guidance on output size limits for large result sets #735

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: 4 additions & 0 deletions features/agent.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,6 +186,10 @@ Pass the `model` parameter to select which model to use:
- **Data Gathering**: "Extract contact information from company websites"
- **Content Summarization**: "Summarize the latest blog posts about web scraping"

## Large Result Sets

A single agent run can typically return around **100–200 rows** of structured tabular data. This is due to the output token capacity of the underlying language model, not a plan restriction. If your task requires more data, split it into multiple focused agent runs — for example, one run per geographic region or category — and merge the results on your end. Keeping your schema consistent across runs makes combining the output straightforward.

## CSV Upload in Agent Playground

The [Agent Playground](https://www.firecrawl.dev/app/agent) supports CSV upload for batch processing. Your CSV can contain one or more columns of input data. For example, a single column of company names, or multiple columns such as company name, product, and website URL. Each row represents one item for the agent to process.
Expand Down