AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-05 22:26:43 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update extract.ts

Browse Source
This commit is contained in:
Nicolas 2024-11-24 20:37:58 -08:00
parent 2513efc971
commit 8a26f08b14
1 changed files with 4 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
apps/api/src/controllers/v1/extract.ts
View File

@ -32,7 +32,7 @@ const MAX_EXTRACT_LIMIT = 100;
const MAX_RANKING_LIMIT = 10;
const INITIAL_SCORE_THRESHOLD = 0.75;
const FALLBACK_SCORE_THRESHOLD = 0.5;
const MIN_REQUIRED_LINKS = 3;
const MIN_REQUIRED_LINKS = 1;
/**
* Extracts data from the provided URLs based on the request parameters.
@ -103,6 +103,7 @@ export async function extractController(
// If we don't have enough high-quality links, try with lower threshold
if (filteredLinks.length < MIN_REQUIRED_LINKS) {
console.log(`Only found ${filteredLinks.length} links with score > ${INITIAL_SCORE_THRESHOLD}. Trying lower threshold...`);
logger.info(`Only found ${filteredLinks.length} links with score > ${INITIAL_SCORE_THRESHOLD}. Trying lower threshold...`);
filteredLinks = filterAndProcessLinks(mappedLinks, linksAndScores, FALLBACK_SCORE_THRESHOLD);
@ -227,15 +228,8 @@ export async function extractController(
// Optionally, you could notify an admin or add to a retry queue here
});
let data: any;
let warning = completions.warning ?? "";
try {
data = JSON.parse(completions.extract);
} catch (e) {
logger.warn(`ExtractController: Error parsing JSON: ${e}`);
data = completions.extract;
warning = "JSON could not be parsed correctly. Returning raw LLM output...";
}
let data = completions.extract ?? {};
let warning = completions.warning;
logJob({
job_id: id,