[PR #23140] [CLOSED] feat(firecrawl): migrate web retrieval to Firecrawl v2 #98086

New Issue

GiteaMirror · 2026-05-16T00:47:59-05:00

GiteaMirror commented

2026-05-16 00:47:59 -05:00

📋 Pull Request Information

Original PR: https://github.com/open-webui/open-webui/pull/23140
Author: @RomualdYT
Created: 3/27/2026
Status: ❌ Closed

Base: dev ← Head: firecrawl/v2webretrieval

📝 Commits (1)

6a04226 feat(firecrawl): migrate web retrieval to Firecrawl v2

📊 Changes

7 files changed (+853 additions, -155 deletions)

View changed files

📝 backend/open_webui/config.py (+24 -0)
📝 backend/open_webui/main.py (+8 -0)
📝 backend/open_webui/retrieval/web/firecrawl.py (+373 -19)
📝 backend/open_webui/retrieval/web/utils.py (+172 -84)
📝 backend/open_webui/routers/retrieval.py (+114 -27)
📝 src/lib/components/admin/Settings/WebSearch.svelte (+155 -20)
📝 uv.lock (+7 -5)

📄 Description

Pull Request Checklist

Note to first-time contributors: Please open a discussion post in Discussions to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request.

This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR.

Before submitting, make sure you've checked the following:

Target branch: Verify that the pull request targets the dev branch. PRs targeting main will be immediately closed.
Description: Provide a concise description of the changes made in this pull request down below.
Changelog: Ensure a changelog entry following the format of Keep a Changelog is added at the bottom of the PR description.
[] Documentation: Add docs in Open WebUI Docs Repository. Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps.
Dependencies: Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash.
Testing: Perform manual tests to verify the implemented fix/feature works as intended AND does not break any other functionality. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to make screenshots of the feature/fix and include them in the PR description.
Agentic AI Code: Confirm this Pull Request is not written by any AI Agent or has at least gone through additional human review AND manual testing. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR.
Code review: Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
Design & Architecture: Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes.
Git Hygiene: Keep PRs atomic (one logical change). Clean up commits and rebase on dev to ensure no unrelated commits (e.g. from main) are included. Push updates to the existing PR branch instead of closing and reopening.
Title Prefix: To clearly categorize this pull request, prefix the pull request title using one of the following:
- BREAKING CHANGE: Significant changes that may affect compatibility
- build: Changes that affect the build system or external dependencies
- ci: Changes to our continuous integration processes or workflows
- chore: Refactor, cleanup, or other non-functional code changes
- docs: Documentation update or addition
- feat: Introduces a new feature or enhancement to the codebase
- fix: Bug fix or error correction
- i18n: Internationalization or localization changes
- perf: Performance improvement
- refactor: Code restructuring for better maintainability, readability, or scalability
- style: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.)
- test: Adding missing tests or correcting existing tests
- WIP: Work in progress, a temporary label for incomplete or ongoing work

Changelog Entry

Description

Migrated the Firecrawl loader and web search integration to the Firecrawl v2 client APIs and optimized the retrieval flow for significantly improved interactive latency.
Replaced inefficient single-URL batch scraping with direct scrape calls while preserving batch processing for true multi-URL workloads...
Introduced a native Firecrawl search + scrapeOptions retrieval path to eliminate redundant fetch round-trips and return markdown content directly.
Centralized and normalized Firecrawl configuration (timeouts, cache, proxy, PDF parsing, and main-content-only extraction) for consistency and maintainability.
Added guarded fallbacks to ensure robustness when Firecrawl responses are incomplete or fail.
Exposed advanced Firecrawl loader settings in the admin panel for better control over retrieval behavior.
Updated and aligned Firecrawl SDK dependency to firecrawl-py 4.18.0.

Added

Native Firecrawl search + scrapeOptions retrieval path returning markdown directly from search results.
Admin-exposed advanced Firecrawl settings:
- Only Main Content
- Parse PDF
- Proxy Mode
- Cache Max Age (ms)
Centralized configuration layer for Firecrawl request options.

Changed

Switched single-URL fetch flow from batch_scrape to scrape for improved latency.
Retained batch_scrape only for multi-URL workloads where batching is beneficial.
Migrated the Firecrawl integration from the legacy client usage to Firecrawl v2 (Firecrawl / AsyncFirecrawl).
Unified handling of timeout, cache, proxy, and parsing options across all Firecrawl calls.
Improved retrieval pipeline to reduce unnecessary network round-trips.
Updated the locked Firecrawl dependency to firecrawl-py==4.18.0.

Deprecated

Implicit use of batch_scrape for single-URL fetches.

Removed

Redundant secondary fetch step after Firecrawl search results (now handled directly via scrapeOptions).

Fixed

Fixed the main Firecrawl fetch_url latency issue caused by routing single-URL fetches through batch_scrape.
Fixed the Firecrawl web retrieval flow so it better matches current Firecrawl API usage and SDK expectations.
Fixed configuration round-tripping for the new Firecrawl loader settings in the admin UI.
Fixed the Firecrawl integration wiring to avoid import issues during application startup.

Security

No direct security changes.
Improved resilience via stricter fallback handling for external API responses.

Breaking Changes

BREAKING CHANGE: Firecrawl integration now relies on v2 client APIs and updated SDK (

Additional Information

The Firecrawl-native retrieval path keeps guarded fallbacks when native Firecrawl search results fail or come back incomplete. This is intentional to reduce regression risk while still making the normal path much faster.
The default Firecrawl loader profile introduced here is:
- only main content = true
- parse PDF = true
- proxy mode = basic
- cache max age = 3600000 ms
FIRECRAWL_TIMEOUT remains configured in seconds in the admin UI for compatibility, and is converted at the Firecrawl integration boundary based on the SDK call being used.
The dependency lock was aligned to firecrawl-py==4.18.0 to match the implementation and current Firecrawl v2 usage.
Validation performed so far:
- backend Firecrawl-related Python modules compile successfully with python -m py_compile
- self-review completed on the Firecrawl loader, retrieval flow, and admin settings wiring
- configure WEB_LOADER_ENGINE=firecrawl
- verified that single-URL fetch_url requests are noticeably faster than before
- verified that multi-URL retrieval still uses Firecrawl batch mode correctly
- verified that WEB_SEARCH_ENGINE=firecrawl with BYPASS_WEB_SEARCH_WEB_LOADER=false uses the native Firecrawl search path
- verified that BYPASS_WEB_SEARCH_WEB_LOADER=true keeps the previous behavior
- verified that Parse PDF disabled does not inject empty/unusable PDF content
- verified that the new Firecrawl admin settings persist after save/reload

Screenshots or Videos

N/A — backend-only change with no UI impact.

Contributor License Agreement

By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.

Note

Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/open-webui/open-webui/pull/23140 **Author:** [@RomualdYT](https://github.com/RomualdYT) **Created:** 3/27/2026 **Status:** ❌ Closed **Base:** `dev` ← **Head:** `firecrawl/v2webretrieval` --- ### 📝 Commits (1) - [`6a04226`](https://github.com/open-webui/open-webui/commit/6a04226daeef271a9dece23d293816cc0a4fd905) feat(firecrawl): migrate web retrieval to Firecrawl v2 ### 📊 Changes **7 files changed** (+853 additions, -155 deletions) <details> <summary>View changed files</summary> 📝 `backend/open_webui/config.py` (+24 -0) 📝 `backend/open_webui/main.py` (+8 -0) 📝 `backend/open_webui/retrieval/web/firecrawl.py` (+373 -19) 📝 `backend/open_webui/retrieval/web/utils.py` (+172 -84) 📝 `backend/open_webui/routers/retrieval.py` (+114 -27) 📝 `src/lib/components/admin/Settings/WebSearch.svelte` (+155 -20) 📝 `uv.lock` (+7 -5) </details> ### 📄 Description  # Pull Request Checklist ### Note to first-time contributors: Please open a discussion post in [Discussions](https://github.com/open-webui/open-webui/discussions) to discuss your idea/fix with the community before creating a pull request, and describe your changes before submitting a pull request. This is to ensure large feature PRs are discussed with the community first, before starting work on it. If the community does not want this feature or it is not relevant for Open WebUI as a project, it can be identified in the discussion before working on the feature and submitting the PR. **Before submitting, make sure you've checked the following:** - [x] **Target branch:** Verify that the pull request targets the `dev` branch. **PRs targeting `main` will be immediately closed.** - [x] **Description:** Provide a concise description of the changes made in this pull request down below. - [x] **Changelog:** Ensure a changelog entry following the format of [Keep a Changelog](https://keepachangelog.com/) is added at the bottom of the PR description. - [] **Documentation:** Add docs in [Open WebUI Docs Repository](https://github.com/open-webui/docs). Document user-facing behavior, environment variables, public APIs/interfaces, or deployment steps. - [x] **Dependencies:** Are there any new or upgraded dependencies? If so, explain why, update the changelog/docs, and include any compatibility notes. Actually run the code/function that uses updated library to ensure it doesn't crash. - [x] **Testing:** Perform manual tests to **verify the implemented fix/feature works as intended AND does not break any other functionality**. Include reproducible steps to demonstrate the issue before the fix. Test edge cases (URL encoding, HTML entities, types). Take this as an opportunity to **make screenshots of the feature/fix and include them in the PR description**. - [x] **Agentic AI Code:** Confirm this Pull Request is **not written by any AI Agent** or has at least **gone through additional human review AND manual testing**. If any AI Agent is the co-author of this PR, it may lead to immediate closure of the PR. - [x] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards? - [x] **Design & Architecture:** Prefer smart defaults over adding new settings; use local state for ephemeral UI logic. Open a Discussion for major architectural or UX changes. - [x] **Git Hygiene:** Keep PRs atomic (one logical change). Clean up commits and rebase on `dev` to ensure no unrelated commits (e.g. from `main`) are included. Push updates to the existing PR branch instead of closing and reopening. - [x] **Title Prefix:** To clearly categorize this pull request, prefix the pull request title using one of the following: - **BREAKING CHANGE**: Significant changes that may affect compatibility - **build**: Changes that affect the build system or external dependencies - **ci**: Changes to our continuous integration processes or workflows - **chore**: Refactor, cleanup, or other non-functional code changes - **docs**: Documentation update or addition - **feat**: Introduces a new feature or enhancement to the codebase - **fix**: Bug fix or error correction - **i18n**: Internationalization or localization changes - **perf**: Performance improvement - **refactor**: Code restructuring for better maintainability, readability, or scalability - **style**: Changes that do not affect the meaning of the code (white space, formatting, missing semi-colons, etc.) - **test**: Adding missing tests or correcting existing tests - **WIP**: Work in progress, a temporary label for incomplete or ongoing work # Changelog Entry ### Description - Migrated the Firecrawl loader and web search integration to the Firecrawl v2 client APIs and optimized the retrieval flow for significantly improved interactive latency. - Replaced inefficient single-URL batch scraping with direct scrape calls while preserving batch processing for true multi-URL workloads... - Introduced a native Firecrawl search + scrapeOptions retrieval path to eliminate redundant fetch round-trips and return markdown content directly. - Centralized and normalized Firecrawl configuration (timeouts, cache, proxy, PDF parsing, and main-content-only extraction) for consistency and maintainability. - Added guarded fallbacks to ensure robustness when Firecrawl responses are incomplete or fail. - Exposed advanced Firecrawl loader settings in the admin panel for better control over retrieval behavior. - Updated and aligned Firecrawl SDK dependency to firecrawl-py 4.18.0. ### Added - Native Firecrawl search + scrapeOptions retrieval path returning markdown directly from search results. - Admin-exposed advanced Firecrawl settings: - `Only Main Content` - `Parse PDF` - `Proxy Mode` - `Cache Max Age (ms)` - Centralized configuration layer for Firecrawl request options. ### Changed - Switched single-URL fetch flow from `batch_scrape` to `scrape` for improved latency. - Retained `batch_scrape` only for multi-URL workloads where batching is beneficial. - Migrated the Firecrawl integration from the legacy client usage to Firecrawl v2 (`Firecrawl` / `AsyncFirecrawl`). - Unified handling of timeout, cache, proxy, and parsing options across all Firecrawl calls. - Improved retrieval pipeline to reduce unnecessary network round-trips. - Updated the locked Firecrawl dependency to `firecrawl-py==4.18.0`. ### Deprecated - Implicit use of `batch_scrape` for single-URL fetches. ### Removed - Redundant secondary fetch step after Firecrawl search results (now handled directly via scrapeOptions). ### Fixed - Fixed the main Firecrawl `fetch_url` latency issue caused by routing single-URL fetches through `batch_scrape`. - Fixed the Firecrawl web retrieval flow so it better matches current Firecrawl API usage and SDK expectations. - Fixed configuration round-tripping for the new Firecrawl loader settings in the admin UI. - Fixed the Firecrawl integration wiring to avoid import issues during application startup. ### Security - No direct security changes. - Improved resilience via stricter fallback handling for external API responses. ### Breaking Changes - **BREAKING CHANGE**: Firecrawl integration now relies on v2 client APIs and updated SDK ( --- ### Additional Information - The Firecrawl-native retrieval path keeps guarded fallbacks when native Firecrawl search results fail or come back incomplete. This is intentional to reduce regression risk while still making the normal path much faster. - The default Firecrawl loader profile introduced here is: - `only main content = true` - `parse PDF = true` - `proxy mode = basic` - `cache max age = 3600000 ms` - `FIRECRAWL_TIMEOUT` remains configured in seconds in the admin UI for compatibility, and is converted at the Firecrawl integration boundary based on the SDK call being used. - The dependency lock was aligned to `firecrawl-py==4.18.0` to match the implementation and current Firecrawl v2 usage. - Validation performed so far: - backend Firecrawl-related Python modules compile successfully with `python -m py_compile` - self-review completed on the Firecrawl loader, retrieval flow, and admin settings wiring - configure `WEB_LOADER_ENGINE=firecrawl` - verified that single-URL `fetch_url` requests are noticeably faster than before - verified that multi-URL retrieval still uses Firecrawl batch mode correctly - verified that `WEB_SEARCH_ENGINE=firecrawl` with `BYPASS_WEB_SEARCH_WEB_LOADER=false` uses the native Firecrawl search path - verified that `BYPASS_WEB_SEARCH_WEB_LOADER=true` keeps the previous behavior - verified that `Parse PDF` disabled does not inject empty/unusable PDF content - verified that the new Firecrawl admin settings persist after save/reload ### Screenshots or Videos N/A — backend-only change with no UI impact. ### Contributor License Agreement  - [X] By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms. > [!NOTE] > Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

GiteaMirror added the pull-request label 2026-05-16 00:47:59 -05:00

GiteaMirror closed this issue

2026-05-16 00:48:02 -05:00

Sign in to join this conversation.

Branches Tags

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/open-webui#98086