2212 Commits

Author SHA1 Message Date
Gergő Móricz
df305c2a97 fix(): null-proof/nan-proof 2025-04-19 12:35:55 -07:00
Gergő Móricz
0e027fe430 fix(scrape): bill llm on fail 2025-04-19 02:56:18 -07:00
Gergő Móricz
b35462456e billing for smart scrape 2025-04-19 02:06:30 -07:00
Gergő Móricz
0a86d2738f reenable 2025-04-19 01:57:58 -07:00
Gergő Móricz
324b4e2e1e fix rounding 2025-04-19 01:45:36 -07:00
Gergő Móricz
6d2347b5f8 feat(llmExtract): add token tracking to all calls 2025-04-19 01:38:55 -07:00
Gergő Móricz
438ea19f16 feat(extract): add thinking tokens 2025-04-19 01:35:17 -07:00
Gergő Móricz
653a0207c3 fix(calculateCost): accuracy 2.5 2025-04-19 01:10:32 -07:00
Gergő Móricz
2b2e648d41 feat(smart-scrape): log failed costs 2025-04-19 01:07:00 -07:00
Gergő Móricz
3909b6641d temp: 2025-04-19 00:19:25 -07:00
Gergő Móricz
5453bed58e temp: put everything back 2025-04-19 00:13:20 -07:00
Gergő Móricz
f451b71308 fix acuc extract preview 2025-04-18 12:37:41 -07:00
Gergő Móricz
3caeaae074 fix(scrapeURL/llmExtract): fix schema-less JSON mode 2025-04-18 10:25:32 -07:00
Nicolas
c69acdffd8 Update v1.ts 2025-04-18 01:57:03 -07:00
Rafael Miller
29b36c5f9a
[python-SDK] improvs/async (#1337)
* improv/types-and-comments-descs

* async

* removed v0 in example

* tomkosms review

* refator: dry request and error handling

* fixed websocket params

* added origin to requests

* Update firecrawl.py

* Update firecrawl.py

* added agent options types

* Update firecrawl.py

* generic

* Update firecrawl.py

* scrape params commentary

* Update firecrawl.py

* Update firecrawl.py

* Update firecrawl.py

* Update firecrawl.py

* async scrape

* Update firecrawl.py

* Nick: new examples

* Nick: python sdk 2.0

* async functions

* Nick:

* Nick:

---------

Co-authored-by: Ademílson F. Tonato <ademilsonft@outlook.com>
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
2025-04-18 01:32:55 -07:00
Gergő Móricz
33aece8e96 more cost calc 2025-04-17 14:00:48 -07:00
Gergő Móricz
9bea877eb1
feat(extract): cost limit (#1473) 2025-04-17 21:44:28 +02:00
Gergő Móricz
7df557e59c feat(cost-tracking): add model tracking and more costs 2025-04-17 11:33:10 -07:00
Gergő Móricz
f844b329f1 remove agent preview rate limiter 2025-04-17 11:04:45 -07:00
Gergő Móricz
06770bc63f fix(scrape/json): move back to 4o mini 2025-04-17 10:48:13 -07:00
Gergő Móricz
8546bcacc0 new cost tracking 2025-04-17 09:23:53 -07:00
Gergő Móricz
ba4df67de7 force 2.5 2025-04-16 16:53:04 -07:00
Gergő Móricz
6a93293fd0 feat(smart-scrape): use correct models for multi-entity assembly 2025-04-16 16:39:48 -07:00
Gergő Móricz
751c30f139 feat(extractSmartScrape): better pagination handling 2025-04-16 16:23:12 -07:00
Gergő Móricz
509e6e658c feat(llmExtract): more logging 2025-04-16 15:40:07 -07:00
Gergő Móricz
4c5120e081 feat(llm-extract): do more logging, even more 2025-04-16 15:10:17 -07:00
Gergő Móricz
b45e3bda13 better logs 2025-04-16 15:08:05 -07:00
Gergő Móricz
ad7e3f62d1 feat(extractSmartScrape): resolve refs in provided schema 2025-04-16 14:32:00 -07:00
Gergő Móricz
5ee2434c9d more logs 2025-04-16 14:24:09 -07:00
Gergő Móricz
4740254b89 feat(rquests.http): add extract 2025-04-16 12:32:02 -07:00
Gergő Móricz
c713251261 feat(extraction-service): send thisSessionId for single entity 2025-04-16 12:28:35 -07:00
Gergő Móricz
7787a58beb default timeout 2025-04-16 10:48:03 -07:00
Gergő Móricz
39d10dc734 feat: disable cost tracking 2025-04-16 09:55:32 -07:00
Gergő Móricz
8766bc6f6b temp: don't... do that 2025-04-16 03:28:33 -07:00
Gergő Móricz
defc80af32 stream session IDs for single URLs 2025-04-16 03:23:18 -07:00
Gergő Móricz
d82f44c93e feat(extract): log failed extracts 2025-04-16 03:13:02 -07:00
Gergő Móricz
aa20246571 minor cost tracking fix 2025-04-16 02:06:39 -07:00
Nicolas
51967c7c3d Merge branch 'main' into rafa/sessionIdsExtract 2025-04-16 01:48:13 -07:00
Gergő Móricz
dcef6fbc13 feat(extractSmartScrape): mog it to 100 pages max 2025-04-16 01:13:49 -07:00
Gergő Móricz
129b10e478 fix(llmExtract): cost calculation 2025-04-16 01:04:48 -07:00
rafaelmmiller
f92217e3b6 wip 2025-04-16 00:38:35 -07:00
Gergő Móricz
0d813b628b feat: correlate smart scrape 2025-04-16 00:25:42 -07:00
Gergő Móricz
edd4c30908 FIX IT 2025-04-16 00:11:27 -07:00
Gergő Móricz
a06910115b asd 2025-04-16 00:03:07 -07:00
Gergő Móricz
2245650bc3 fix 2025-04-15 23:54:56 -07:00
Gergő Móricz
2193bee133 Improve logging 2025-04-15 23:52:20 -07:00
Gergő Móricz
0935ec210e feat(smartScrape): better loggin 2025-04-15 23:34:00 -07:00
Gergő Móricz
b6abe4f26b fix(smartScrape): pass extract id 2025-04-15 23:23:18 -07:00
Gergő Móricz
80b507e64e correlate with eid 2025-04-15 23:06:13 -07:00
Gergő Móricz
512a2b1cd4 feat(extract): run on original links if reranker is weird 2025-04-15 22:57:20 -07:00