30 Commits

Author SHA1 Message Date
Nicolas
5e5b5ee0e2
(feat/extract) New re-ranker + multi entity extraction (#1061)
* agent that decides if splits schema or not

* split and merge properties done

* wip

* wip

* changes

* ch

* array merge working!

* comment

* wip

* dereferentiate schema

* dereference schemas

* Nick: new re-ranker

* Create llm-links.txt

* Nick: format

* Update extraction-service.ts

* wip: cooking schema mix and spread functions

* wip

* wip getting there!!!

* nick:

* moved functions to helpers

* nick:

* cant reproduce the error anymore

* error handling all scrapes failed

* fix

* Nick: added the sitemap index

* Update sitemap-index.ts

* Update map.ts

* deduplicate and merge arrays

* added error handler for object transformations

* Update url-processor.ts

* Nick:

* Nick: fixes

* Nick: big improvements to rerank of multi-entity

* Nick: working

* Update reranker.ts

* fixed transformations for nested objs

* fix merge nulls

* Nick: fixed error piping

* Update queue-worker.ts

* Update extraction-service.ts

* Nick: format

* Update queue-worker.ts

* Update pnpm-lock.yaml

* Update queue-worker.ts

---------

Co-authored-by: rafaelmmiller <150964962+rafaelsideguide@users.noreply.github.com>
Co-authored-by: Thomas Kosmas <thomas510111@gmail.com>
2025-01-13 22:30:15 -03:00
Nicolas
f4d10c5031 Nick: formatting fixes 2025-01-10 18:35:10 -03:00
Nicolas
aef040b41e Nick: from cache fixes 2025-01-03 23:07:15 -03:00
Nicolas
05e845a971 Update cache.ts 2025-01-03 22:55:38 -03:00
Nicolas
eba5fda9a1
Merge pull request #955 from mendableai/rafa/fix-default-on-schema-llm-extract
fixed optional+default bug on llm schema
2024-12-27 16:33:04 -03:00
Nicolas
066071cd54 Update llmExtract.ts 2024-12-18 23:45:43 -03:00
Nicolas
e899ecbe44 Update llmExtract.ts 2024-12-18 16:52:05 -03:00
rafaelmmiller
b6802bc443 merged with main 2024-12-16 11:41:59 -03:00
Rafael Miller
8192d756e9
Merge branch 'main' into rafa/fix-default-on-schema-llm-extract 2024-12-16 09:33:36 -03:00
rafaelmmiller
eab30c474b added unit tests 2024-12-16 09:30:40 -03:00
Nicolas
8a1c404918 Nick: revert trailing comma 2024-12-11 19:51:08 -03:00
Nicolas
00335e2ba9 Nick: fixed prettier 2024-12-11 19:46:11 -03:00
rafaelmmiller
5c81ea1803 fixed optional+default bug on llm schema 2024-12-09 15:34:50 -03:00
Nicolas
eb2e51e50b Nick: fixed /extract without a schema 2024-12-03 12:08:15 -03:00
rafaelmmiller
943bbae88d fixed nested data inside extract 2024-11-27 18:29:37 -03:00
Nicolas
3de4997f4d Loggin num tokens 2024-11-20 13:09:46 -08:00
Nicolas
67a2989874 Nick: fixes 2024-11-20 12:48:10 -08:00
Nicolas
28696da6b2 Nick: gpt-4o 2024-11-20 12:25:50 -08:00
Nicolas
d49f62fb56 Nick: extract fixes 2024-11-20 11:50:14 -08:00
Nicolas
c9b0a80522 Nick: 2024-11-20 10:23:44 -08:00
rafaelmmiller
2fb8a3c8dc fix schema 2024-11-19 10:04:42 -03:00
Gergő Móricz
359c30fbda fix(cache): don't cache on failure error code 2024-11-14 19:49:34 +01:00
Gergő Móricz
49ff37afb4 feat: cache 2024-11-14 19:47:12 +01:00
rafaelmmiller
904c904971 wip 2024-11-13 18:06:20 -03:00
Gergő Móricz
2ca22659d3 fix(scrapeURL/llmExtract): fix schema-less LLM extract 2024-11-11 21:07:37 +01:00
Gergő Móricz
d13a2e7d26 fix(scrapeURL): reduce logs 2024-11-11 20:51:45 +01:00
Móricz Gergő
e97864b806 fix(scrapeURL/llmExtract): better schema normalization 2024-11-11 10:55:45 +01:00
Gergő Móricz
79cadcb769 fix(scrapeURL/llmExtract): fill in required field as well 2024-11-07 22:48:57 +01:00
Gergő Móricz
0588f340c3 fix(scrapeURL/llmExtract): array schema fix 2024-11-07 22:46:59 +01:00
Gergő Móricz
8d467c8ca7
WebScraper refactor into scrapeURL (#714)
* feat: use strictNullChecking

* feat: switch logger to Winston

* feat(scrapeURL): first batch

* fix(scrapeURL): error swallow

* fix(scrapeURL): add timeout to EngineResultsTracker

* fix(scrapeURL): report unexpected error to sentry

* chore: remove unused modules

* feat(transfomers/coerce): warn when a format's response is missing

* feat(scrapeURL): feature flag priorities, engine quality sorting, PDF and DOCX support

* (add note)

* feat(scrapeURL): wip readme

* feat(scrapeURL): LLM extract

* feat(scrapeURL): better warnings

* fix(scrapeURL/engines/fire-engine;playwright): fix screenshot

* feat(scrapeURL): add forceEngine internal option

* feat(scrapeURL/engines): scrapingbee

* feat(scrapeURL/transformars): uploadScreenshot

* feat(scrapeURL): more intense tests

* bunch of stuff

* get rid of WebScraper (mostly)

* adapt batch scrape

* add staging deploy workflow

* fix yaml

* fix logger issues

* fix v1 test schema

* feat(scrapeURL/fire-engine/chrome-cdp): remove wait inserts on actions

* scrapeURL: v0 backwards compat

* logger fixes

* feat(scrapeurl): v0 returnOnlyUrls support

* fix(scrapeURL/v0): URL leniency

* fix(batch-scrape): ts non-nullable

* fix(scrapeURL/fire-engine/chromecdp): fix wait action

* fix(logger): remove error debug key

* feat(requests.http): use dotenv expression

* fix(scrapeURL/extractMetadata): extract custom metadata

* fix crawl option conversion

* feat(scrapeURL): Add retry logic to robustFetch

* fix(scrapeURL): crawl stuff

* fix(scrapeURL): LLM extract

* fix(scrapeURL/v0): search fix

* fix(tests/v0): grant larger response size to v0 crawl status

* feat(scrapeURL): basic fetch engine

* feat(scrapeURL): playwright engine

* feat(scrapeURL): add url-specific parameters

* Update readme and examples

* added e2e tests for most parameters. Still a few actions, location and iframes to be done.

* fixed type

* Nick:

* Update scrape.ts

* Update index.ts

* added actions and base64 check

* Nick: skipTls feature flag?

* 403

* todo

* todo

* fixes

* yeet headers from url specific params

* add warning when final engine has feature deficit

* expose engine results tracker for ScrapeEvents implementation

* ingest scrape events

* fixed some tests

* comment

* Update index.test.ts

* fixed rawHtml

* Update index.test.ts

* update comments

* move geolocation to global f-e option, fix removeBase64Images

* Nick:

* trim url-specific params

* Update index.ts

---------

Co-authored-by: Eric Ciarla <ericciarla@yahoo.com>
Co-authored-by: rafaelmmiller <8574157+rafaelmmiller@users.noreply.github.com>
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
2024-11-07 20:57:33 +01:00