Skip to content

fix(web): parallelize firecrawl extract fanout #47611

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
LeonSGP43 wants to merge 1 commit into
base: main
Choose a base branch
from
+101 −72
Open

fix(web): parallelize firecrawl extract fanout #47611

Show file tree
Hide file tree
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
132 changes: 60 additions & 72 deletions plugins/web/firecrawl/provider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,9 +420,9 @@ def search(self, query: str, limit: int = 5) -> Dict[str, Any]:
async def extract(self, urls: List[str], **kwargs: Any) -> List[Dict[str, Any]]:
"""Extract content from one or more URLs via Firecrawl.

Async; each URL is scraped in a background thread with a 60s
timeout. After scraping, the final URL (post-redirect) is
re-checked against website-access policy.
Async; URLs are scraped concurrently in background threads with a
60s per-URL timeout. After scraping, the final URL (post-redirect)
is re-checked against website-access policy.

Accepted kwargs (others ignored for forward compat):
- ``format``: ``"markdown"`` or ``"html"``; default is both
Expand Down Expand Up @@ -450,12 +450,12 @@ async def extract(self, urls: List[str], **kwargs: Any) -> List[Dict[str, Any]]:
# module level (lazy-friendly because the website_policy import is
# cheap) so monkeypatching it in tests works as expected.

results: List[Dict[str, Any]] = []
concurrency_limit = min(max(len(urls), 1), 4)
scrape_slots = asyncio.Semaphore(concurrency_limit)

for url in urls:
async def extract_one(url: str) -> Dict[str, Any]:
if _is_interrupted():
results.append({"url": url, "error": "Interrupted", "title": ""})
continue
return {"url": url, "error": "Interrupted", "title": ""}

# Pre-scrape website policy gate
blocked = check_website_access(url)
Expand All @@ -465,36 +465,33 @@ async def extract(self, urls: List[str], **kwargs: Any) -> List[Dict[str, Any]]:
blocked["host"],
blocked["rule"],
)
results.append(
{
"url": url,
"title": "",
"content": "",
"error": blocked["message"],
"blocked_by_policy": {
"host": blocked["host"],
"rule": blocked["rule"],
"source": blocked["source"],
},
}
)
continue
return {
"url": url,
"title": "",
"content": "",
"error": blocked["message"],
"blocked_by_policy": {
"host": blocked["host"],
"rule": blocked["rule"],
"source": blocked["source"],
},
}

try:
logger.info("Firecrawl scraping: %s", url)
try:
scrape_result = await asyncio.wait_for(
asyncio.to_thread(
_get_firecrawl_client().scrape,
url=url,
formats=formats,
),
timeout=60,
)
except asyncio.TimeoutError:
logger.warning("Firecrawl scrape timed out for %s", url)
results.append(
{
async with scrape_slots:
logger.info("Firecrawl scraping: %s", url)
try:
scrape_result = await asyncio.wait_for(
asyncio.to_thread(
_get_firecrawl_client().scrape,
url=url,
formats=formats,
),
timeout=60,
)
except asyncio.TimeoutError:
logger.warning("Firecrawl scrape timed out for %s", url)
return {
"url": url,
"title": "",
"content": "",
Expand All @@ -503,8 +500,6 @@ async def extract(self, urls: List[str], **kwargs: Any) -> List[Dict[str, Any]]:
"or unresponsive. Try browser_navigate instead."
),
}
)
continue

scrape_payload = _extract_scrape_payload(scrape_result)
metadata = scrape_payload.get("metadata", {})
Expand All @@ -531,50 +526,43 @@ async def extract(self, urls: List[str], **kwargs: Any) -> List[Dict[str, Any]]:
final_blocked["host"],
final_blocked["rule"],
)
results.append(
{
"url": final_url,
"title": title,
"content": "",
"raw_content": "",
"error": final_blocked["message"],
"blocked_by_policy": {
"host": final_blocked["host"],
"rule": final_blocked["rule"],
"source": final_blocked["source"],
},
}
)
continue
return {
"url": final_url,
"title": title,
"content": "",
"raw_content": "",
"error": final_blocked["message"],
"blocked_by_policy": {
"host": final_blocked["host"],
"rule": final_blocked["rule"],
"source": final_blocked["source"],
},
}

# Choose markdown vs html according to the requested format
if format == "markdown" or (format is None and content_markdown):
chosen_content = content_markdown
else:
chosen_content = content_html or content_markdown or ""

results.append(
{
"url": final_url,
"title": title,
"content": chosen_content,
"raw_content": chosen_content,
"metadata": metadata,
}
)
return {
"url": final_url,
"title": title,
"content": chosen_content,
"raw_content": chosen_content,
"metadata": metadata,
}
except Exception as scrape_err: # noqa: BLE001
logger.debug("Firecrawl scrape failed for %s: %s", url, scrape_err)
results.append(
{
"url": url,
"title": "",
"content": "",
"raw_content": "",
"error": str(scrape_err),
}
)

return results
return {
"url": url,
"title": "",
"content": "",
"raw_content": "",
"error": str(scrape_err),
}

return await asyncio.gather(*(extract_one(url) for url in urls))

def get_setup_schema(self) -> Dict[str, Any]:
return {
Expand Down
41 changes: 41 additions & 0 deletions tests/plugins/web/test_web_search_provider_plugins.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@

import asyncio
import inspect
import time

import pytest

Expand Down Expand Up @@ -353,6 +354,46 @@ def test_firecrawl_extract_is_async(self) -> None:
assert p is not None
assert inspect.iscoroutinefunction(p.extract) is True

def test_firecrawl_extract_scrapes_multiple_urls_concurrently(
self,
monkeypatch: pytest.MonkeyPatch,
) -> None:
from plugins.web.firecrawl.provider import FirecrawlWebSearchProvider

class DummyClient:
def scrape(self, *, url, formats):
time.sleep(0.20)
return {
"metadata": {
"title": f"title:{url}",
"sourceURL": url,
},
"markdown": f"markdown:{url}",
}

monkeypatch.setattr(
"plugins.web.firecrawl.provider._get_firecrawl_client",
lambda: DummyClient(),
)
monkeypatch.setattr(
"plugins.web.firecrawl.provider.check_website_access",
lambda url: None,
)

provider = FirecrawlWebSearchProvider()
urls = ["https://example.com/one", "https://example.com/two"]

started = time.monotonic()
results = asyncio.run(provider.extract(urls, format="markdown"))
elapsed = time.monotonic() - started

assert [result["url"] for result in results] == urls
assert [result["content"] for result in results] == [
"markdown:https://example.com/one",
"markdown:https://example.com/two",
]
assert elapsed < 0.32

def test_exa_extract_is_sync(self) -> None:
_ensure_plugins_loaded()
from agent.web_search_registry import get_provider
Expand Down
Loading