Commit Graph

1007 Commits

Author SHA1 Message Date
aziz-ullah-khan
e828c7010a perf: Proxy integration in googlesearch 2024-10-11 12:30:58 +05:00
Marco Vinciguerra
3b7b701a89 feat: refactoring of mdscraper 2024-10-11 08:32:41 +02:00
Marco Vinciguerra
cf0cfbd28b
Merge pull request #737 from ScrapeGraphAI/prompt-refactoring 2024-10-11 07:39:41 +02:00
aziz-ullah-khan
36875b67f1 Merge remote-tracking branch 'refs/remotes/origin/pre/beta' into pre/beta 2024-10-11 10:08:07 +05:00
aziz-ullah-khan
46195d65ca Update: proxy integration in googlesearch 2024-10-11 10:04:28 +05:00
Marco Vinciguerra
91ede933f8 refactoring of the code
Some checks failed
/ build (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-10-10 14:08:13 +02:00
Marco Vinciguerra
e9c8402091 Update fetch_node.py 2024-10-10 11:41:32 +02:00
Marco Vinciguerra
39a029ed9a feat: refactoring fetch_node 2024-10-10 11:36:48 +02:00
Marco Vinciguerra
5a2f6d9a77 feat: prompt refactoring 2024-10-10 10:35:37 +02:00
Marco Vinciguerra
72f16ab3b8
Merge pull request #736 from ScrapeGraphAI/refractoring-chromiumloader 2024-10-10 07:57:12 +02:00
Marco Vinciguerra
8753537ecd fix: nodes prompt 2024-10-09 14:38:31 +02:00
Marco Vinciguerra
c655642577 fix: refactoring prompts 2024-10-09 14:22:34 +02:00
Marco Vinciguerra
88ba2310ac feat:add dynamic rendering 2024-10-09 10:45:47 +02:00
Marco Vinciguerra
4f816f3b04 feat: update chromium loader 2024-10-09 10:39:29 +02:00
Marco Vinciguerra
7797631eac Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta 2024-10-09 08:46:51 +02:00
Marco Vinciguerra
d0e5671caf removed unused example 2024-10-09 08:46:48 +02:00
Marco Vinciguerra
a57da96175 fix: removed pdf_scraper graph and created document scraper 2024-10-08 09:35:47 +02:00
Marco Vinciguerra
a447aeae2a Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta 2024-10-08 08:54:22 +02:00
Marco Vinciguerra
a200f595de refactoring of examples 2024-10-08 08:54:18 +02:00
Marco Vinciguerra
e2d1816087
Merge pull request #729 from ekinsenler/selenium
feat: support for undetected_chromedriver with selenium backend
2024-10-07 10:36:01 +02:00
Marco Vinciguerra
37b6ba08ae fix: import error 2024-10-07 10:22:17 +02:00
ekinsenler
d94959c3a2 pass headless state to the browser 2024-10-06 23:10:56 +03:00
ekinsenler
80ece2179a feat: undected_chromedriver support 2024-10-06 22:50:52 +03:00
Marco Vinciguerra
420c71ba2c feat: refactoring of the conditional node 2024-10-06 09:16:33 +02:00
Marco Vinciguerra
c06cafc976
Merge branch 'pre/beta' into cond_node 2024-10-05 19:23:22 +02:00
Marco Vinciguerra
99aac5b055
Merge branch 'pre/beta' into tem 2024-10-05 09:35:31 +02:00
ekinsenler
f837dc16ce feat: conditional_node 2024-10-05 01:14:54 +03:00
Marco Vinciguerra
6664da07f8
Merge pull request #720 from ScrapeGraphAI/deep_scraper_integration
Deep scraper integration
2024-10-04 09:56:49 +02:00
Marco Vinciguerra
db54d69433 refactoring of code for pylint integration 2024-10-04 09:54:54 +02:00
Marco Vinciguerra
85cb957297 feat: finished basic version of deep scraper
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-10-03 13:13:04 +02:00
Marco Vinciguerra
4b371f4d94 feat: add deep scraper implementation
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-10-03 11:38:14 +02:00
Marco Vinciguerra
17c51457df
Merge pull request #717 from vedovati-matteo/deep_scraper_integration
Fetch_node_level_k and parse_node_depth_k added
2024-10-02 13:48:54 +02:00
Marco Vinciguerra
6124fbdfca add embeddings with openai 2024-10-02 13:41:15 +02:00
Matteo Vedovati
015c6fd905 remove link from markdown 2024-10-02 13:06:00 +02:00
Matteo Vedovati
f755d56bb1 updated parse node 2024-10-02 12:28:48 +02:00
Matteo Vedovati
2bdb01b07a Create parse_node_depth_k.py 2024-10-02 11:04:17 +02:00
Matteo Vedovati
ea3ae1fd6d fetch multiple links fix 2024-10-02 11:01:23 +02:00
Matteo Vedovati
4cb621feab fetch node level k implementation 2024-10-02 10:22:21 +02:00
Marco Vinciguerra
e017ee21f3 update readme and readibility of the code 2024-10-02 10:07:03 +02:00
Marco Vinciguerra
45f02cd4e2 refactoring of the format 2024-10-01 11:13:06 +02:00
Marco Vinciguerra
99ad654c43
Merge branch 'pre/beta' into 713-pdf-scrapping 2024-10-01 10:26:28 +02:00
Marco Vinciguerra
26f89d895d feat: refactoring of research web 2024-10-01 10:25:09 +02:00
Marco Vinciguerra
e88fee9a2b Update generate_answer_node_k_level.py 2024-09-30 15:10:55 +02:00
Marco Vinciguerra
55199e8307 add first iterations of the nodes 2024-09-30 14:23:46 +02:00
Matteo Vedovati
d80b792e15 fetching first level 2024-09-30 12:42:26 +02:00
Matteo Vedovati
57bf572ab4 initial code for fetch nodel level K 2024-09-30 12:23:11 +02:00
Matteo Vedovati
6915f3edfd start form scratch 2024-09-30 12:22:09 +02:00
Matteo Vedovati
462b27bc1d Revert "Stating anew"
This reverts commit 89de5b6cba.
2024-09-30 12:21:33 +02:00
Matteo Vedovati
7411ff061c Revert "initial creation of FetchNodeLevelK and DescriptionNode"
This reverts commit 336bf705ec.
2024-09-30 12:21:26 +02:00
Matteo Vedovati
336bf705ec initial creation of FetchNodeLevelK and DescriptionNode 2024-09-30 12:18:30 +02:00
Matteo Vedovati
89de5b6cba Stating anew 2024-09-30 12:10:40 +02:00
Marco Vinciguerra
ea27b2499e add empyt nodes 2024-09-30 11:52:14 +02:00
Marco Vinciguerra
d9a8208b08
Merge branch 'pre/beta' into branch_temp 2024-09-29 15:43:59 +02:00
Marco Vinciguerra
9aa8c889fb fix: removed deep scraper 2024-09-29 15:40:04 +02:00
Marco Vinciguerra
27ae896cb7 Update output_parser.py 2024-09-28 11:05:09 +02:00
Marco Vinciguerra
560f079d4c refactoring of the code 2024-09-28 09:02:20 +02:00
Marco Vinciguerra
f87ffa1d8d fix: integration with html_mode 2024-09-27 18:31:42 +02:00
Marco Vinciguerra
faf25eeba9
Merge branch 'reasoning-branch' into pre/beta 2024-09-27 17:50:29 +02:00
Marco Vinciguerra
b2822f620a feat: add reasoning integration 2024-09-27 17:45:44 +02:00
Marco Vinciguerra
bdcffd6360 feat: add html_mode to smart_scraper 2024-09-27 16:41:45 +02:00
Marco Vinciguerra
9fa109453f
Update reasoning_node_prompts.py 2024-09-27 14:09:35 +02:00
Marco Vinciguerra
90e6d077dc feat: add llama 3.2 2024-09-27 11:07:51 +02:00
Marco Vinciguerra
e9d6f547e8 Merge branch 'main' of https://github.com/ScrapeGraphAI/Scrapegraph-ai 2024-09-27 09:34:57 +02:00
Marco Vinciguerra
7c39b06640 update for pylint 2024-09-27 09:34:56 +02:00
Matteo Vedovati
afa9aa3fe7 import refactoring 2024-09-26 18:37:40 +02:00
Matteo Vedovati
b7b3e9660f reasoning node refactoring 2024-09-26 18:33:22 +02:00
Matteo Vedovati
0b12589664 reasoning node prompt refinement 2024-09-26 18:28:26 +02:00
Matteo Vedovati
3228f7dafb Update reasoning_node.py 2024-09-26 18:10:37 +02:00
Matteo Vedovati
e2fe39c093 Reasoning node created 2024-09-26 17:59:50 +02:00
Marco Vinciguerra
9905be8a37 fix: script creator multi 2024-09-26 10:09:36 +02:00
Marco Vinciguerra
d0976ddda9
Merge branch 'main' into temp-1 2024-09-25 17:45:45 +02:00
Marco Vinciguerra
76ce257efb fix: update to pydantic documentation 2024-09-25 15:12:29 +02:00
Marco Vinciguerra
d55f6bee47 fix: node refiner + examples 2024-09-25 14:53:51 +02:00
Marco Vinciguerra
bcf02e5f19 add possiibility to save the code 2024-09-24 21:42:45 +02:00
Matteo Vedovati
ce841e21fb Code generation refactoring 2024-09-24 19:04:43 +02:00
Matteo Vedovati
2d2c7194be Template refactoring 2024-09-24 18:33:12 +02:00
Matteo Vedovati
d6a77029bb Validator fixed 2024-09-24 18:12:50 +02:00
Matteo Vedovati
8578bf17d5
Merge pull request #8 from VinciGit00/patch-5
Update generate_code_node.py
2024-09-24 17:33:13 +02:00
Matteo Vedovati
b0d9b37bac
Merge pull request #7 from VinciGit00/patch-4
Update html_analyzer_node.py
2024-09-24 17:32:56 +02:00
Marco Vinciguerra
54ebb39732
Update generate_code_node.py 2024-09-24 17:00:18 +02:00
Marco Vinciguerra
d38a50115f
Update html_analyzer_node.py 2024-09-24 16:59:33 +02:00
Marco Vinciguerra
04ac7362d4
i don't like comments 2024-09-24 16:57:52 +02:00
Marco Vinciguerra
ceede46673 fix: parse_node 2024-09-24 15:27:20 +02:00
Matteo Vedovati
cd55c92b4e
Merge branch 'pre/beta' into pre/beta 2024-09-24 12:47:38 +02:00
Matteo Vedovati
84abaa6dfe
Merge pull request #5 from ScrapeGraphAI/temp
Pre/beta
2024-09-24 12:46:28 +02:00
Matteo Vedovati
df90770779 Update generate_code_node.py 2024-09-24 12:44:55 +02:00
Marco Vinciguerra
5a3ece9a1a
Merge branch 'pre/beta' into temp 2024-09-24 12:41:55 +02:00
Marco Vinciguerra
36a8a1c872 refining and refactoring of the code 2024-09-24 12:36:10 +02:00
Marco Vinciguerra
657ef711f7 raise keyerror exception for the schema 2024-09-24 12:06:45 +02:00
Marco Vinciguerra
3876cb7be8 feat: update exception
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-09-24 09:35:33 +02:00
Marco Vinciguerra
3b5ee767cb feat: add info to the dictionary for toghtherai 2024-09-24 09:18:15 +02:00
Marco Vinciguerra
1ffdd3f4e9 Update models_tokens.py
Some checks failed
/ build (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-09-23 20:56:53 +02:00
Marco Vinciguerra
d0969feb7c removed unused imports and comments + removed dead code 2024-09-23 09:25:13 +02:00
Marco Vinciguerra
bc881b4aaa refctoring of the code
Some checks failed
CodeQL / Analyze (python) (push) Has been cancelled
/ build (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-09-23 08:37:52 +02:00
Marco Vinciguerra
de10b281ba feat: update search_link_graph 2024-09-23 08:26:36 +02:00
Marco Vinciguerra
8ce08baf01 fix: graph Iterator node 2024-09-22 22:25:01 +02:00
Marco Vinciguerra
69880b680a Update generate_answer_node.py 2024-09-22 21:16:16 +02:00
Marco Vinciguerra
65b8675586 Update smart_scraper_multi_concat_graph.py 2024-09-22 21:10:57 +02:00
Marco Vinciguerra
7eda6bc06b fix: issue about parser 2024-09-22 18:55:05 +02:00
Marco Vinciguerra
f9b121f765 fix: chat for bedrock 2024-09-22 16:47:19 +02:00