Commit Graph

1007 Commits

Author SHA1 Message Date
smith peng
553527a269 fix: fix pydantic object copy 2024-09-01 16:42:48 +08:00
Marco Vinciguerra
a73573d87a update version 2024-08-31 12:32:25 +02:00
smith peng
71b22d4880 feat: add deepcopy error 2024-08-31 17:55:14 +08:00
smith peng
36818b1fb3 feat:adjust uncopiable obj raise error and remove memo 2024-08-31 17:39:33 +08:00
smith peng
cd07418474 fix: deepcopy fail for coping model_instance config 2024-08-31 16:26:11 +08:00
smith peng
4f4d091b82 feat:add deepcopy tool 2024-08-31 11:30:20 +08:00
Marco Vinciguerra
388630c0ff fix: screenshot scraper 2024-08-30 13:02:13 +02:00
Marco Vinciguerra
a0d21137b7 refactoring of folders 2024-08-30 12:17:21 +02:00
Marco Vinciguerra
735120d0a3
Merge branch 'screenshot-scraper-fix' into pre/beta 2024-08-30 11:41:45 +02:00
Marco Vinciguerra
c348f674ad fix: update generate answernode 2024-08-30 11:37:44 +02:00
elijahbenizzy
25d8fd2e72 Fixes node expression validator error message to make it easier to debug missing keys 2024-08-29 13:24:47 -07:00
Federico Aguzzi
34942deca5 chore(examples): create Together AI examples
Co-Authored-By: Marco Vinciguerra <88108002+VinciGit00@users.noreply.github.com>
2024-08-28 22:39:05 +02:00
Marco Vinciguerra
8f615adef3 feat: add togheterai 2024-08-28 17:02:48 +02:00
Marco Vinciguerra
08fa257407
Merge pull request #602 from ScrapeGraphAI/593-abstract-graph-fix-round-4
Abstract graph fix
2024-08-28 16:10:36 +02:00
Federico Aguzzi
f7a85c266a fix(models): better DeepSeek and OneApi integration 2024-08-28 12:51:50 +02:00
Federico Aguzzi
4f120e29c5 fix(AbstractGraph): model selection bug 2024-08-28 12:36:03 +02:00
Santabot123
90d75498fc updated requirements.txt 2024-08-28 11:46:49 +03:00
Santabot123
aa9e85fdac remove some comments and image 2024-08-28 11:38:56 +03:00
ajenkins
bda30a9ecb swapped failing imports (local Gemini and non-imported Ernie) for langchain chat models in graph_builder.py 2024-08-28 16:48:00 +10:00
Marco Vinciguerra
df70b4f75d Update abstract_graph.py 2024-08-27 18:08:53 +02:00
Marco Vinciguerra
cf73883451 fix: bug for abstract graph 2024-08-27 18:05:34 +02:00
Marco Vinciguerra
d45064b09a
Merge pull request #597 from ScrapeGraphAI/593-abstract-graph-fix-round-4
Abbstract graph fix, round 4
2024-08-27 17:54:04 +02:00
Federico Aguzzi
7789663338 fix(BurrBrige): dynamic imports 2024-08-27 17:17:51 +02:00
Federico Aguzzi
83e71df2e2 fix: set up dynamic imports correctly 2024-08-27 16:54:57 +02:00
Federico Aguzzi
5c16ee985b fix(docloaders): BrowserBase dynamic import 2024-08-27 16:44:05 +02:00
Federico Aguzzi
f6df9b7512 chore(examples): update model names 2024-08-27 12:41:18 +02:00
Federico Aguzzi
f73343f193 fix(AbstractGraph): correct and simplify instancing logic 2024-08-27 12:22:53 +02:00
Marco Vinciguerra
04128e7e9f fix: abstract graph local model 2024-08-26 18:00:17 +02:00
Marco Vinciguerra
2a602a157e
Merge branch 'pre/beta' into jamie-beck-patch-1 2024-08-26 17:54:31 +02:00
Jamie Beck
35b994a8cd
fix model_tokens not being used for ollama
I am passing in the explicit model_tokens from user config as the default_token so it will correctly fallback to the users setting if the model is not found
2024-08-26 11:30:09 -04:00
Santabot123
0cf7c44409 correct the typo and updated select_area_with_ipywidget() 2024-08-26 14:51:28 +03:00
Santabot123
b4f8ea420b add __init__.py and docstrings 2024-08-26 13:53:19 +03:00
Marco Vinciguerra
e3fbf01c5b
Revert "Anthropic refactoring" 2024-08-25 10:54:19 +02:00
Marco Vinciguerra
9df4b14bc0 refacttoring of the anthropic example 2024-08-25 10:53:01 +02:00
Marco Vinciguerra
86fe5fcaf1 fix: update abstract graph 2024-08-24 21:57:04 +02:00
Marco Vinciguerra
ee8f8b31ec fix: add claude3.5 sonnet 2024-08-24 21:25:55 +02:00
Santabot123
e11f0cd28d Added text_detection.py and updated screenshot_preparation.py 2024-08-24 18:40:54 +03:00
Marco Vinciguerra
cf1fada36a fix: abstract graph
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-08-23 18:43:49 +02:00
Santabot123
49ae56ceee Added screenshot preparation script for screenshot scraping 2024-08-23 19:00:14 +03:00
Marco Vinciguerra
26de5dd623
Merge branch 'pre/beta' into ligthweigthing_library 2024-08-23 12:22:31 +02:00
Marco Vinciguerra
f7ba1f30de refactoring of the code 2024-08-23 11:33:22 +02:00
Marco Vinciguerra
0d2b7b37e0 update dependenceis 2024-08-21 20:48:47 +02:00
aziz-ullah-khan
a92b9c6970 Fix: Azure OpenAI issue 2024-08-21 16:18:51 +05:00
Federico Aguzzi
b05ec16b25 fix(models_tokens): add llama2 and llama3 sizes explicitly 2024-08-21 09:32:59 +02:00
Federico Aguzzi
dd406dff0c style(models_tokens): enforce formatting 2024-08-21 09:29:38 +02:00
Marco Vinciguerra
860fde8a2c
Merge pull request #558 from ScrapeGraphAI/screenshot_scraper
Screenshot scraper integration
2024-08-20 11:33:51 +02:00
Federico Aguzzi
d2486469af Merge branch 'pre/beta' into screenshot_scraper 2024-08-20 09:58:34 +02:00
Federico Aguzzi
052f7d5e66 fix(SearchNode): prompt
Co-Authored-By: Andrew Masek <8219702+portoaj@users.noreply.github.com>
2024-08-20 09:53:35 +02:00
Marco Vinciguerra
fee77d1fe6 Update screenshot_scraper_graph.py
Some checks failed
/ build (push) Has been cancelled
2024-08-19 14:35:13 +02:00
Marco Vinciguerra
f774fe40e5 add try catch and robust integration 2024-08-19 14:24:27 +02:00
Federico Aguzzi
d29338b7c2 feat(GenerateAnswerNode): built-in structured output through LangChain
Some checks failed
/ build (push) Has been cancelled
Co-Authored-By: Marco Vinciguerra <88108002+VinciGit00@users.noreply.github.com>
2024-08-19 13:45:37 +02:00
Federico Aguzzi
b48ee825ee Merge branch 'pre/beta' into support_structured_output_shema_openai 2024-08-19 13:31:01 +02:00
Federico Aguzzi
683bf57d89 fix(ParseNode): leave room for LLM reply in context window 2024-08-19 11:33:09 +02:00
Marco Vinciguerra
f60aa3acde feat: add async call
Some checks are pending
/ build (push) Waiting to run
2024-08-19 11:22:40 +02:00
ekinsenler
08e9d9d6a0 feat: Implemented a filter logic in search_link_node.py
feat: Added dict entry for Llama3.1:8b
2024-08-19 11:05:31 +03:00
Marco Vinciguerra
0bf79b5926 Update generate_answer_from_image_node.py
Some checks are pending
/ build (push) Waiting to run
2024-08-19 02:21:45 +02:00
Marco Vinciguerra
79fa3f6bd6 add if and cool stuff 2024-08-19 02:01:41 +02:00
Marco Vinciguerra
c72c077eb6 refactoring of the nodes 2024-08-19 01:15:45 +02:00
Marco Vinciguerra
8d6c0b7288 Update generate_answer_node.py
Some checks failed
/ build (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-08-18 22:01:39 +02:00
Marco Vinciguerra
103c21c86e Update generate_answer_from_image_node.py 2024-08-18 20:54:35 +02:00
Marco Vinciguerra
5eb3cff64f feat: refactoring of the code 2024-08-18 20:53:35 +02:00
Marco Vinciguerra
8e3d5deaaa add screenshot scraper 2024-08-18 19:39:49 +02:00
Marco Vinciguerra
8b8d8f09b7 refactoring of the code according to pylint style
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-08-18 11:51:34 +02:00
Marco Vinciguerra
ebdb74967d add new model for gpt 2024-08-17 15:00:44 +02:00
Marco Vinciguerra
609316c8e7 Update abstract_graph.py
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-08-17 14:39:39 +02:00
Marco Vinciguerra
391d051a5e updated 2024-08-17 14:39:19 +02:00
Marco Vinciguerra
0aca28732b feat: update model tokens dict 2024-08-17 14:34:06 +02:00
Marco Vinciguerra
c2c2e6582f Update generate_answer_node.py 2024-08-17 13:30:44 +02:00
Marco Vinciguerra
f0587908e2 Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta 2024-08-17 12:21:03 +02:00
Marco Vinciguerra
1d7f30b65b fix: browser-base integration 2024-08-17 12:21:00 +02:00
Federico Aguzzi
5eed0a7654 fix(FetchNode) add OpenAI optimization to GPT models on Azure
closes #547
2024-08-17 10:33:54 +02:00
Marco Vinciguerra
faef3186f7 fix: model count 2024-08-16 17:38:55 +02:00
Marco Vinciguerra
5100368b5a Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta 2024-08-16 09:01:30 +02:00
Marco Vinciguerra
b115f9612f refactoring of code and documentation 2024-08-16 09:01:27 +02:00
Marco Vinciguerra
333f09a289
Merge pull request #552 from sandeepchittilla/550-add-support-gpt4o-variants
Add new feature to support gpt-4o variant models with different pricing
2024-08-16 09:00:31 +02:00
Federico Aguzzi
ea72d7609c
Merge pull request #536 from ScrapeGraphAI/refactoring-of-abstract-graph
Refactoring of abstract graph
2024-08-15 16:46:03 +02:00
sandeepchittilla
855144876d
feat: Add new feature to support gpt-4o variant models with different pricing 2024-08-15 14:59:48 +01:00
Marco Vinciguerra
203ee2c186 removed unused imports
Some checks failed
/ build (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-08-14 11:07:11 +02:00
Marco Vinciguerra
597f2acd07 fixed doc bugs and removed unused rag node 2024-08-14 10:59:53 +02:00
Marco Vinciguerra
c5aebd73d3
Merge pull request #541 from ScrapeGraphAI/496-not-match-gemini-embeddings-model 2024-08-13 20:54:57 +02:00
Marco Vinciguerra
9be44742d6 Update abstract_graph.py
Some checks failed
/ build (push) Has been cancelled
2024-08-13 19:29:03 +02:00
Marco Vinciguerra
795c9325cc
Merge branch 'pre/beta' into refactoring-of-abstract-graph
Some checks are pending
/ build (push) Waiting to run
2024-08-12 18:35:55 +02:00
Marco Vinciguerra
c105c26b2f Update abstract_graph.py 2024-08-12 18:32:41 +02:00
Federico Aguzzi
cb6b35397e fix(models_tokens): incorrect provider names 2024-08-12 10:52:13 +02:00
Federico Aguzzi
bae89e832e Merge branch 'pre/beta' into 530-probable-bug 2024-08-12 10:37:50 +02:00
Federico Aguzzi
e6bedb6701 fix(AbstractGraph): pass kwargs to Ernie and Nvidia models
Some checks failed
/ build (push) Has been cancelled
Co-Authored-By: Marco Vinciguerra <88108002+VinciGit00@users.noreply.github.com>
2024-08-12 10:11:45 +02:00
Marco Vinciguerra
8cece1d31b
Merge branch 'pre/beta' into refactoring-of-abstract-graph 2024-08-11 19:20:26 +02:00
Marco Vinciguerra
cef2fdb420 Update abstract_graph.py
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-11 19:19:17 +02:00
Marco Vinciguerra
c77231c983 feat: update abstract graph
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-11 19:18:24 +02:00
Marco Vinciguerra
de1ec250ef refactoring pyproject.toml
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-11 18:04:31 +02:00
Marco Vinciguerra
cec5537f2a add new tests
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-11 17:10:55 +02:00
Matteo Vedovati
a3b7181f95 quick fix typo 2024-08-11 11:52:50 +02:00
Matteo Vedovati
734b740bf9 Template name refactoring 2024-08-11 11:46:01 +02:00
Matteo Vedovati
98779d193b search_link_node prompts moved 2024-08-11 11:43:22 +02:00
Matteo Vedovati
ef966525c3 search_link_node prompt moved 2024-08-11 11:34:49 +02:00
Matteo Vedovati
86a4903e99 search_internet_node prompt moved 2024-08-11 11:31:51 +02:00
Matteo Vedovati
f455fcbc5f robot_node prompt moved 2024-08-11 11:27:27 +02:00
Matteo Vedovati
9814b6dd85 fixed versioning errors 2024-08-11 10:04:15 +02:00
Matteo Vedovati
7c6210019e Merge branch 'pre/beta' of https://github.com/vedovati-matteo/Scrapegraph-ai into pre/beta 2024-08-11 09:42:38 +02:00
Matteo Vedovati
f17cef94bb fix: merge_anwser prompt import 2024-08-11 09:41:31 +02:00
Matteo Vedovati
9fa3df2390 Changed prompts import from helpers to prompts 2024-08-11 09:33:21 +02:00
Matteo Vedovati
3b5b24d6f8 Added new folder for prompts 2024-08-11 09:32:00 +02:00
Matteo Vedovati
4ca606cf7a remove promps form helpers folders 2024-08-11 09:31:26 +02:00
Marco Vinciguerra
0cda020d48
Merge branch 'pre/beta' into temp 2024-08-10 17:45:52 +02:00
Marco Vinciguerra
8b2c266aff refactoring of the code
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-10 17:44:35 +02:00
Marco Vinciguerra
778efd4c87 fix: conditional node 2024-08-10 12:21:09 +02:00
Marco Vinciguerra
c3f1520240 Update abstract_graph.py 2024-08-10 12:13:09 +02:00
Marco Vinciguerra
6c3b37ab00 feat: add refactoring of default temperature 2024-08-10 11:51:37 +02:00
Marco Vinciguerra
f01b55e89b fix: fetch node 2024-08-10 11:41:51 +02:00
Marco Vinciguerra
ce00345495 fix: conditional node 2024-08-09 23:38:26 +02:00
Marco Vinciguerra
1272273499 fix: broken node 2024-08-09 17:35:43 +02:00
Marco Vinciguerra
157d59d5c0
Merge branch 'pre/beta' into temp 2024-08-09 10:28:59 +02:00
Federico Aguzzi
50edbcc7f8 fix(FetchNode): missing bracket syntax error 2024-08-09 09:37:51 +02:00
Marco Vinciguerra
0048ba1542 Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-08-08 12:09:39 +02:00
Marco Vinciguerra
71ae3845b4 Update generate_answer_node_prompts.py 2024-08-08 12:09:38 +02:00
Federico Aguzzi
5ec2de9e1a fix(chunking): count tokens from words instead of characters
closes #513
2024-08-08 10:50:52 +02:00
Marco Vinciguerra
7f03926432
Merge pull request #515 from vedovati-matteo/pre/beta
fix: refactoring of merge_answer_node
2024-08-07 21:50:14 +02:00
Matteo Vedovati
898e5a7af5 fix: refactoring of merge_answer_node 2024-08-07 21:42:54 +02:00
Marco Vinciguerra
b6bff0be33
Merge branch 'pre/beta' into mistral-ai-integration 2024-08-07 21:24:18 +02:00
Marco Vinciguerra
a7db47ecad refatoring
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
2024-08-07 21:23:42 +02:00
Federico Aguzzi
786af992f8 fix(AbstractGraph): LangChain warnings handling, Mistral tokens 2024-08-07 15:16:10 +02:00
Federico Aguzzi
07720b6e0c fix(FetchNode): handling of missing browser_base key 2024-08-07 15:15:13 +02:00
Marco Vinciguerra
b52e4a390b fix: generate answer node omni 2024-08-07 14:09:02 +02:00
Marco Vinciguerra
625ca9f22a fix: generate answer node pdf has a bug 2024-08-07 14:06:53 +02:00
Matteo Vedovati
bfc6852b77 fix: refactoring of fetch_node adding comment 2024-08-07 13:02:02 +02:00
Matteo Vedovati
1ea2ad8e79 fix: refactoring of fetch_node qixed error 2024-08-07 12:04:54 +02:00
Matteo Vedovati
29ad140fa3 fix: refactoring of fetch_node 2024-08-07 11:56:10 +02:00
Federico Aguzzi
f8ad616e10 chore(mistral): create examples 2024-08-06 18:16:15 +02:00
Federico Aguzzi
17f2707313 feat: add mistral support 2024-08-06 17:51:50 +02:00
Federico Aguzzi
5e824327c3 chore(models_tokens): add mistral models 2024-08-06 17:22:39 +02:00
Marco Vinciguerra
82e63213ae Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta
Some checks failed
/ build (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-08-06 17:07:35 +02:00
Marco Vinciguerra
37dd6e9ba9 update reqs
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-06 17:07:33 +02:00
Federico Aguzzi
bc9e70031f Merge branch 'main' into pre/beta 2024-08-06 16:50:46 +02:00
Marco Vinciguerra
6e4d04450f Update base_graph.py 2024-08-06 16:29:59 +02:00
Marco Vinciguerra
fa651d4cd9 feat: add grok integration 2024-08-06 15:17:49 +02:00
Marco Vinciguerra
0571b6da55 feat: update base_graph 2024-08-06 14:01:11 +02:00
Marco Vinciguerra
886bab78e7
Merge branch 'main' into temp-1 2024-08-06 10:04:57 +02:00
Marco Vinciguerra
66a29bc5cc refactoring of the openai examples
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-08-05 20:54:53 +02:00
Marco Vinciguerra
1fb711ae51 Merge branch 'pre/beta' of https://github.com/ScrapeGraphAI/Scrapegraph-ai into pre/beta
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-08-05 14:54:16 +02:00
Marco Vinciguerra
a3d7f1b71c Update csv_scraper_graph.py 2024-08-05 14:54:14 +02:00
Marco Vinciguerra
ddb3135109
Merge pull request #503 from ScrapeGraphAI/497-abstract-graph-refactor
fix(AbstractGraph): instantiation of Azure GPT models
2024-08-02 14:32:29 +02:00
Federico Aguzzi
ade28fca2c fix(AbstractGraph): instantiation of Azure GPT models
Some checks failed
/ build (push) Has been cancelled
Closes #498
2024-08-02 12:15:43 +02:00
Marco Vinciguerra
9355507a2d feat: refactoring of the code 2024-08-02 12:00:00 +02:00
Marco Vinciguerra
fe099f9cbc
Merge branch 'pre/beta' into browserbase_integration
Some checks failed
/ build (push) Has been cancelled
2024-08-01 15:14:49 +02:00
Lorenzo Padoan
abd0ea13f9
Merge pull request #500 from ScrapeGraphAI/497-abstract-graph-refactor
497 abstract graph refactor
2024-08-01 14:51:36 +02:00
Marco Vinciguerra
53dc06a2cb Update speech_graph.py
Some checks are pending
/ build (push) Waiting to run
2024-08-01 14:48:19 +02:00
Marco Vinciguerra
9ac74de622 Update speech_graph.py 2024-08-01 14:47:49 +02:00
Marco Vinciguerra
0b4cfd6522 fix: abstract_graph and removed unused embeddings
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-08-01 14:38:50 +02:00
Marco Vinciguerra
be870a4316 Update fetch_node.py
Co-Authored-By: Federico Minutoli <40361744+DiTo97@users.noreply.github.com>
2024-08-01 13:24:48 +02:00
Marco Vinciguerra
6d8e02cd62 Update browser_base.py
Co-Authored-By: Federico Minutoli <40361744+DiTo97@users.noreply.github.com>
2024-08-01 13:24:32 +02:00
Marco Vinciguerra
968c69e217 fix: fixed bug on fetch_node
Co-Authored-By: Federico Minutoli <40361744+DiTo97@users.noreply.github.com>
2024-08-01 13:23:54 +02:00
Marco Vinciguerra
e21d461710 push 2024-08-01 13:16:49 +02:00
Marco Vinciguerra
d03eedccd7 Update chromium.py 2024-08-01 13:05:13 +02:00
Marco Vinciguerra
65f9e3a24c Delete browser_base.py 2024-08-01 12:58:35 +02:00
Marco Vinciguerra
4cd5986516
Merge branch 'pre/beta' into browserbase_integration
Some checks are pending
/ build (push) Waiting to run
2024-08-01 12:52:36 +02:00
Marco Vinciguerra
5ecdbe715f feat: add integration in the abstract grapgh 2024-08-01 12:51:18 +02:00
Federico Aguzzi
a94ebcde00 refactor: move embeddings code from AbstractGraph to RAGNode
Some checks are pending
/ build (push) Waiting to run
2024-08-01 11:53:17 +02:00
Marco Vinciguerra
7076ab12d3 allignment 2024-08-01 11:31:27 +02:00
Marco Vinciguerra
4caed545e5 feat: intregration of firebase 2024-07-31 19:49:59 +02:00
Federico Aguzzi
bb73d916a1 refactor: reuse code for common interface models 2024-07-31 13:41:09 +02:00
Federico Aguzzi
b17756d934 style: enforce pylint styling 2024-07-31 13:07:19 +02:00
Federico Aguzzi
88710f1a7c chore: remove unused import 2024-07-30 15:57:08 +02:00
Federico Aguzzi
bc2c9967d2 refactor: remove redundant wrappers for Ernie and Nvidia 2024-07-30 10:59:12 +02:00
Federico Aguzzi
9275486240 refactor: remove redundant LangChain wrappers
Some checks are pending
/ build (push) Waiting to run
2024-07-29 21:59:39 +02:00
Marco Vinciguerra
5007167af1 removed unused models
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-07-29 17:59:16 +02:00
Marco Vinciguerra
f6b7c6a430 refactoring
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-07-29 17:56:32 +02:00
Federico Aguzzi
25066b2bc5 refactor: remove LangChain wrappers for Ollama 2024-07-29 17:49:21 +02:00
Federico Aguzzi
2c5f934f10 refactor: remove LangChain wrappers 2024-07-29 17:46:17 +02:00
Marco Vinciguerra
9e795f4e35 removed unused init files
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-07-29 17:35:10 +02:00
Federico Aguzzi
5e3eb6e43d refactor(OpenAI): integrate new LangChain chat init
Some checks are pending
/ build (push) Waiting to run
2024-07-29 11:26:20 +02:00
Federico Aguzzi
d177afb68b refactor(Ollama): integrate new LangChain chat init 2024-07-29 11:24:34 +02:00
amosdinh
05cf9adaa7 Ollama: Use no json format when creating the search query 2024-07-26 12:10:14 +02:00
Marco Vinciguerra
5137b8aa5b Update models_tokens.py
Some checks are pending
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-07-26 10:18:08 +02:00
Federico Aguzzi
d745564ad1
Merge pull request #485 from ScrapeGraphAI/generate_answer_parallel
merge: generate answer parallel
2024-07-25 11:49:43 +02:00
Marco Perini
5c08eea189 docs: prev version
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
2024-07-24 23:37:57 +02:00
Marco Vinciguerra
377d679eec
feat: pdate models_tokens.py 2024-07-24 15:17:48 +02:00
Marco Vinciguerra
e08b30495d boh
Some checks are pending
CodeQL / Analyze (python) (push) Waiting to run
/ build (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-07-24 14:33:55 +02:00
Marco Vinciguerra
41ea3e0e27 add llama3.1 model 2024-07-24 13:38:27 +02:00
Federico Aguzzi
ddbfbe1205 Merge branch 'pre/beta' into generate_answer_parallel 2024-07-23 20:51:35 +02:00
Marco Perini
1d41f6eafe
fix: md conversion 2024-07-23 19:27:18 +02:00
Marco Perini
5a45e9f2d8
fix: md conversion 2024-07-23 18:09:15 +02:00
Marco Perini
49b6468fb1
Merge branch 'main' into pre/beta 2024-07-23 16:14:15 +02:00
Marco Perini
0ebc387446
Merge pull request #487 from ScrapeGraphAI/update-generate-answer-node
Update generate answer node
2024-07-23 15:45:20 +02:00
Marco Perini
12b5eada6e
fix(md_conversion): add absolute links md, added missing dependency 2024-07-23 15:34:12 +02:00
Marco Vinciguerra
df1ecc0019 Update generate_answer_node.py
Some checks are pending
/ build (push) Waiting to run
2024-07-23 13:06:59 +02:00
Marco Vinciguerra
cf2734392c removed unused function 2024-07-23 13:05:50 +02:00
Marco Vinciguerra
8dd941e39e update generate answer nodes
Co-Authored-By: Federico Aguzzi <62149513+f-aguzzi@users.noreply.github.com>
2024-07-23 12:40:11 +02:00
Marco Vinciguerra
879a554a78 Update telemetry.py 2024-07-23 11:15:44 +02:00
Marco Vinciguerra
70911f83be Update generate_answer_pdf_node.py 2024-07-23 11:07:35 +02:00
Marco Vinciguerra
0c4b2908d9 feat: add generate_answer node paralellization
Some checks are pending
/ build (push) Waiting to run
Co-Authored-By: Federico Minutoli <40361744+DiTo97@users.noreply.github.com>
2024-07-22 19:58:33 +02:00
Marco Vinciguerra
2ae19aee56 update function 2024-07-22 16:50:58 +02:00
Marco Vinciguerra
09256f7b11 fix: parse node 2024-07-22 16:15:38 +02:00
Marco Vinciguerra
71f894eee3
fix: parse_html node have a bug 2024-07-22 16:01:27 +02:00
Marco Vinciguerra
fc0dadb8f8 feat: add nvidia connection 2024-07-22 11:56:33 +02:00
Marco Vinciguerra
b49f9866fd fixed telemetry version 2024-07-21 19:20:19 +02:00
Marco Vinciguerra
ce6be37fbc fix: abstract_graph moel token bug 2024-07-21 18:37:15 +02:00
Marco Vinciguerra
7a3c21b58d Update generate_answer_node.py 2024-07-20 20:19:16 +02:00
Marco Vinciguerra
6a9205920f
Merge branch 'pre/beta' into temp 2024-07-20 20:03:20 +02:00
Marco Perini
99dc8497d8
docs(gpt-4o-mini): added new gpt, fixed chromium lazy loading,
add documentation and metrics
2024-07-20 20:02:26 +02:00
Marco Perini
61a51d4bce
Merge pull request #466 from ScrapeGraphAI/refactoring_convert_to_md
refactoring of generate answer node
2024-07-20 19:40:57 +02:00
Marco Vinciguerra
19af78c7d8
Merge branch 'pre/beta' into main 2024-07-20 18:14:36 +02:00
DragonelRoland
4b8360658e
Update models_tokens.py
added gpt4o mini to the models
2024-07-20 16:51:24 +02:00
DragonelRoland
e9ecf5f0dc
Update typo in conditional_node.py
"thar" -> "that"
2024-07-20 15:06:52 +02:00
Marco Vinciguerra
3cf7089e3f
Merge branch 'pre/beta' into temp 2024-07-20 13:27:37 +02:00
Marco Vinciguerra
77777c898d fix: add gpt o mini for azure 2024-07-20 13:20:16 +02:00
Marco Vinciguerra
03f4a3aa29 fix: azure models 2024-07-20 13:19:21 +02:00
Marco Vinciguerra
3a9d556e1b
Merge branch 'pre/beta' into add-openai-supported-model-gpt-4o-mini 2024-07-19 10:08:41 +02:00
Kernick
4f079cfc74
Fixed a typo in the model name 2024-07-18 21:06:16 +03:00
Kernick
b91020ce56
Update models_tokens.py with gpt-4o-mini
OpenAI added a new available model - gpt-4o-mini. Adding this model to the supported models, so it would be possible to use it with the Scrapegraph-ai.
2024-07-18 21:03:55 +03:00
Federico Aguzzi
dfa759e834 style(models): fix module docstrings 2024-07-18 11:02:51 +02:00
Marco Vinciguerra
032a491605 Update parse_node.py
Some checks failed
/ build (push) Has been cancelled
2024-07-17 23:06:05 +02:00
Marco Vinciguerra
07f1e23d23 fix: parse_node 2024-07-17 22:58:21 +02:00
Marco Vinciguerra
68f58cc4dd refactoring of generate answer node 2024-07-17 22:41:49 +02:00
Marco Vinciguerra
602dd00209 feat: refactoring_to_md function 2024-07-16 12:39:48 +02:00
Federico Aguzzi
dccb893fdf
Merge pull request #456 from ScrapeGraphAI/refactoring-of-search_link_node
fix: search link node
2024-07-15 23:06:03 +02:00
Marco Vinciguerra
830daee1f3 Update search_link_node.py
Some checks failed
/ build (push) Has been cancelled
2024-07-15 20:47:09 +02:00
Marco Vinciguerra
57fdaf9e3a create search_link_graph
Some checks are pending
/ build (push) Waiting to run
2024-07-15 12:36:11 +02:00
Federico Aguzzi
789c16fb76
Merge pull request #458 from ScrapeGraphAI/searchngx_integration
merge: update research_web.py
2024-07-14 22:55:52 +02:00
Federico Aguzzi
7ba2f6ae0b chore: correct search engine name
Some checks failed
/ build (push) Has been cancelled
2024-07-14 22:39:34 +02:00
Federico Aguzzi
fd1b7cb24a chore: remove unused import
Some checks failed
/ build (push) Has been cancelled
2024-07-14 22:36:43 +02:00
Marco Vinciguerra
7e5789baa3 Update research_web.py 2024-07-14 19:31:22 +02:00
Marco Vinciguerra
cf3ab5564a fix: search link node 2024-07-14 16:49:29 +02:00
Marco Vinciguerra
a7249685cb removed rag node 2024-07-14 10:24:38 +02:00
salamanderxing
4b65392cca Resolves #447 2024-07-12 10:56:25 +02:00
Marco Vinciguerra
765b548c0e
Merge pull request #417 from ScrapeGraphAI/md_scraper_integration
feat: add integrations for markdown files
2024-07-04 19:42:53 +02:00
Marco Vinciguerra
8a52914871
Merge pull request #429 from ScrapeGraphAI/421-default-prompt-template-customization
421 default prompt template customization
2024-07-04 19:42:35 +02:00
Federico Aguzzi
104d8692d6
Merge branch 'pre/beta' into support
Some checks failed
/ build (push) Has been cancelled
2024-07-04 18:36:34 +02:00
Federico Aguzzi
1bbd25a63f
Merge pull request #407 from ScrapeGraphAI/404-split-unit-testing-from-src
Merge #404 (split unit testing from src)
2024-07-04 18:33:45 +02:00
Federico Aguzzi
d77a622b05 Merge branch '423-add-vertex-ai-integration' into support 2024-07-04 18:23:22 +02:00
Federico Aguzzi
720f18729b Merge branch 'fireworks_integration' into support 2024-07-04 18:17:38 +02:00
Federico Aguzzi
2ab7ddc95a
Merge pull request #405 from ScrapeGraphAI/integration_markdown
Integration markdown
2024-07-04 18:13:12 +02:00
Marco Vinciguerra
3ee1743687 update prompts
Some checks failed
/ build (3.10) (push) Has been cancelled
2024-07-04 14:22:45 +02:00
Marco Vinciguerra
ed2af51501 update the chunk size
Some checks are pending
/ build (3.10) (push) Waiting to run
2024-07-02 12:03:08 +02:00
Marco Vinciguerra
3bf5f570a8 feat: add integration for infos 2024-07-01 21:19:16 +02:00
AmosDinh
3f9bf5b4d4 fixed typo 2024-07-01 13:42:10 +00:00
Marco Vinciguerra
119514bdfc feat: add vertexai integration 2024-07-01 12:21:47 +02:00
Marco Vinciguerra
5fe694b6b4 feat: improve md prompt recognition
Some checks are pending
/ build (3.10) (push) Waiting to run
2024-06-30 18:10:00 +02:00
Marco Vinciguerra
30ca15ca28
Merge branch 'md_scraper_integration' into integration_markdown
Some checks failed
/ build (3.10) (push) Has been cancelled
2024-06-30 16:58:37 +02:00
Marco Vinciguerra
b6a78e926f
Merge branch 'main' into temp 2024-06-30 16:54:15 +02:00
Marco Vinciguerra
2804434a9e feat: add integrations for markdown files
Some checks are pending
/ build (3.10) (push) Waiting to run
2024-06-29 13:35:39 +02:00
Marco Vinciguerra
9b45ebcdcf modify fetch node with no cut mode 2024-06-28 14:38:36 +02:00
Marco Vinciguerra
f3cbbcee92
Merge pull request #412 from oviniciusfeitosa/patch-1
Some checks failed
/ build (3.10) (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
🐛 Rename user_prompt parameter to prompt
2024-06-28 11:09:25 +02:00
Marco Vinciguerra
5d2e592a67 add new claude models
Some checks failed
CodeQL / Analyze (python) (push) Has been cancelled
/ build (3.10) (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-06-28 10:53:40 +02:00
Marco Vinciguerra
4d936410cc fix: add new claude model 2024-06-28 10:50:01 +02:00
Vinícius Feitosa da Silva
a3c43c9a99
🐛 Rename user_prompt parameter to prompt
This adjustment makes the class consistent with the definition of the arguments.
2024-06-27 17:53:20 -03:00
Marco Vinciguerra
228a1de2be add new force 2024-06-27 18:57:27 +02:00
Marco Vinciguerra
ff4ccb94a1 add claude 3.5 integration
Some checks failed
CodeQL / Analyze (python) (push) Has been cancelled
/ build (3.10) (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-06-25 11:21:06 +02:00
Marco Vinciguerra
0dfa5bf07e
Merge branch 'pre/beta' into main 2024-06-25 10:47:15 +02:00
Maorsg
f75e0835fc added a function to the search_graph class to allow user to return URLs considered in the search 2024-06-24 21:31:28 -04:00
Marco Vinciguerra
df0e310829 feat: add fireworks integration 2024-06-24 23:11:28 +02:00
Marco Vinciguerra
3a537eec6f fix: add test 2024-06-23 17:54:09 +02:00
Djamel Feddad
2b4f4f12be
doc: Fixed a small typo in the warning message
This PR fixes a small type in the warning message
2024-06-23 15:34:48 +08:00
Marco Vinciguerra
9917972c11 fixed request
Some checks are pending
/ build (3.10) (push) Waiting to run
2024-06-22 21:39:37 +02:00
Marco Vinciguerra
afd46ac77b fixed generate_answer_node
Some checks are pending
/ build (3.10) (push) Waiting to run
2024-06-22 11:31:54 +02:00
Marco Vinciguerra
d1c3de777f fixed a bug 2024-06-21 14:14:43 +02:00
Marco Vinciguerra
599512d2e5 fix: add new model for claude 2024-06-21 14:08:10 +02:00
Marco Vinciguerra
7af411aa99 add trigger
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-06-21 13:36:27 +02:00
Marco Vinciguerra
5d6123847e add new convert function
Some checks are pending
/ build (3.10) (push) Waiting to run
Co-Authored-By: Federico Minutoli <40361744+DiTo97@users.noreply.github.com>
2024-06-20 21:15:16 +02:00
Marco Vinciguerra
2f02830c81 refactoring of fetch node
Some checks are pending
/ build (3.10) (push) Waiting to run
2024-06-20 13:44:42 +02:00
Marco Vinciguerra
5664eb292b Update generate_answer_node_prompts.py 2024-06-20 11:57:11 +02:00
Marco Vinciguerra
23bc6332d0 fixed a bug 2024-06-19 21:46:31 +02:00
Marco Vinciguerra
8bb560a489 add convert function 2024-06-19 20:17:45 +02:00
Marco Vinciguerra
88f9def69d fix: reduced model tokens 2024-06-19 19:55:13 +02:00
Marco Vinciguerra
79a2f51c34 add new models tokens 2024-06-19 10:42:41 +02:00
Marco Vinciguerra
40b4b2d939 add new models tokens 2024-06-19 10:42:00 +02:00
Marco Perini
0cb46f5f30
Merge pull request #392 from VinciGit00/391-switch-between-search-engines
Some checks failed
/ build (3.10) (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
feat: add new search engine avaiability and new tests
2024-06-18 23:46:28 +02:00
Marco Perini
c7870905e1 fix: total tokens and docs 2024-06-18 23:22:23 +02:00
Marco Vinciguerra
aa2160c108 feat: add research with bing + test function
Some checks failed
/ build (3.10) (push) Has been cancelled
2024-06-18 21:28:29 +02:00
Jason Vertrees
aedda44868 fix: updated for schema changes
docs: updated for schema changes
2024-06-18 13:31:10 -05:00
Marco Vinciguerra
073d226723 feat: add new search engine avaiability and new tests 2024-06-18 14:35:13 +02:00
Marco Vinciguerra
1d0cbbc6d6 fix: add new embedding models 2024-06-18 09:13:15 +02:00
Marco Vinciguerra
48ff87f20a Merge branch 'pre/beta' of https://github.com/VinciGit00/Scrapegraph-ai into pre/beta 2024-06-17 14:17:46 +02:00
Marco Vinciguerra
03ffebc52d fix: add chinese embedding model 2024-06-17 14:17:44 +02:00
Marco Perini
080a318ff6 feat(telemetry): add telemetry module 2024-06-17 13:00:33 +02:00
Marco Vinciguerra
da93162b53
Merge branch 'pre/beta' into main 2024-06-17 11:02:56 +02:00
shubihu
d8d5cd267a
Update abstract_graph.py
fix: Incorrect API Key Error with OpenAI Proxy
2024-06-17 16:26:33 +08:00
Marco Perini
4c8becc721 overwrite common params to affect nodes config
Some checks failed
/ build (3.10) (push) Has been cancelled
Release / Build (push) Has been cancelled
Release / Release (push) Has been cancelled
2024-06-16 15:19:40 +02:00
Marco Vinciguerra
2419003999 fix: fix robot node
Some checks are pending
/ build (3.10) (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-06-16 14:04:36 +02:00
Marco Vinciguerra
3d34ea65df
Merge pull request #384 from liaoliaojun/fix/merge
fix: TypeError ‘Model provided by the configuration not supported’
2024-06-16 13:34:43 +02:00
Marco Vinciguerra
dcd216e345 fix: removed duplicate from ollama dictionary
Co-Authored-By: Matteo Vedovati <68272450+vedovati-matteo@users.noreply.github.com>
2024-06-15 19:51:20 +02:00
liaoliaojun
62b372b675 fix: shallow copy config of create_embedder 2024-06-15 17:53:13 +08:00
Marco Perini
09cb6e964e refactor: add missing schemas and renamed files
Some checks are pending
/ build (3.10) (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-06-14 15:38:46 +02:00
Marco Perini
12f4386552
Merge branch 'pre/beta' into 349-problem-with-scrapegraphaigraphspdf_scraper_graphpy 2024-06-14 15:22:43 +02:00
Marco Perini
203de83405 fix(pdf): correctly read .pdf files 2024-06-14 15:20:30 +02:00
Marco Perini
91c5b5af43 fix(multi): updated multi pdf scraper with schema 2024-06-14 14:59:12 +02:00
Marco Vinciguerra
7a34562d50 refactoring of merging answers nodes 2024-06-13 21:41:54 +02:00
Marco Perini
283b61fafc docs: better logging 2024-06-13 18:13:47 +02:00
Marco Vinciguerra
a6757aca57
Merge pull request #380 from Kshitij-Jande/main
Strip out the scheme from the proxy server address URI.
2024-06-13 13:23:26 +02:00
Kshitij Jande
2a9ab69f4b Strip out the scheme from the server address URI 2024-06-13 12:18:41 +05:30
Marco Vinciguerra
1705046cc7 Update pdf_scraper_graph.py 2024-06-12 18:00:12 +02:00
Marco Vinciguerra
dc1340e302 Update generate_answer_pdf_node.py 2024-06-12 15:47:04 +02:00
Marco Vinciguerra
e45f159a31 enhanced performance and readibility 2024-06-12 14:59:10 +02:00
Marco Vinciguerra
58a257f05b update model tokens
Some checks are pending
/ build (3.10) (push) Waiting to run
Release / Build (push) Waiting to run
Release / Release (push) Blocked by required conditions
2024-06-12 12:41:58 +02:00
Marco Vinciguerra
e6c7940a57 feat: add Parse_Node 2024-06-12 12:29:14 +02:00
Marco Vinciguerra
5065aa00e1
Merge branch 'pre/beta' into supercoder-327 2024-06-12 12:12:15 +02:00
supercoder-dev
d0e300af72
Update fetch_node.py 2024-06-12 14:32:01 +05:30
supercoder-dev
879c94a2b5
Update cleanup_html.py 2024-06-12 14:30:02 +05:30
supercoder-dev
828bdeedce
Update smart_scraper_graph.py 2024-06-12 14:28:33 +05:30
Marco Perini
6b4cdf92b8 fix: common params 2024-06-12 03:06:21 +02:00
Marco Perini
ab00f23d85 fix(node): fixed generate answer node pydantic schema 2024-06-12 01:40:49 +02:00