Marco Perini
0c1594737f
fix(fetch-node): removed isSoup from default
2024-05-13 12:09:55 +02:00
Marco Perini
7e8acd8e6a
Merge branch 'pre/beta' into fix/fetch-node-proxybroker
2024-05-13 11:17:37 +02:00
Marco Perini
1e9a564616
fix(proxy-rotation): removed duplicated arg and passed the loader_kwarhs correctly to the node
2024-05-12 18:39:03 +02:00
VinciGit00
e2350eda62
feat: add new prompt info
2024-05-12 11:14:30 +02:00
mayurdb
9a67a26cd3
Update documentation
2024-05-11 16:57:22 +05:30
mayurdb
df271b6451
Add search link node that can find out relevant links in the webpage
2024-05-11 16:39:55 +05:30
Marco Vinciguerra
b752499fab
Merge pull request #217 from mayurdb/fetchLinkFix
...
Fetch links in the page while parsing html
2024-05-11 09:42:40 +02:00
mayurdb
300fd5d253
Fetch links in the page while parsing html
2024-05-11 09:46:51 +05:30
Eric Page
0683e78e78
Merge branch 'pre/beta' into fix-GenerateScraperGraph
2024-05-11 01:59:28 +02:00
Eric Page
aac51ba290
Removed dead code, allows GenerateScraperNode to generate scraper with
...
one chunk of context
2024-05-11 01:34:51 +02:00
Eric Page
40884747c7
Added parse_html option in parse_node
2024-05-11 00:32:01 +02:00
Federico Minutoli
fc2aa3ac1c
Merge branch 'pre/beta' of https://github.com/DiTo97/Scrapegraph-ai into fix/fetch-node-proxybroker
2024-05-10 21:20:40 +02:00
Federico Minutoli
768719cce8
feat(safe-web-driver): enchanced the original AsyncChromiumLoader web driver with proxy protection and flexible kwargs and backend
...
the original class prevents passing kwargs down to the playwright backend, making some config unfeasible, including passing a proxy server to the web driver.
the new class has backward compatibility with the original, but 1) allows any kwarg to be passed down to the web driver, 2) allows specifying the web driver backend (only playwright is supported for now) in case more (e.g., selenium) will be supported in the future and 3) automatically fetches a suitable proxy if one is not passed already
2024-05-10 21:13:38 +02:00
Marco Perini
864aa91326
feat: revert fetch_node
2024-05-10 15:11:54 +02:00
Marco Vinciguerra
99adc9799f
Merge branch 'pre/beta' into fetchNodeFix
2024-05-10 11:13:54 +02:00
mayurdb
f8ce3d5916
fix: Augment the information getting fetched from a webpage
2024-05-10 13:28:53 +05:30
VinciGit00
0ab31c3fdb
fix: add json integration
2024-05-09 21:07:07 +02:00
VinciGit00
324e977b85
fix: fixed bugs for csv and xml
2024-05-09 20:46:46 +02:00
Shubham Kamboj
f10f3b1438
feat: Add support for passing pdf path as source
2024-05-09 21:55:05 +05:30
Marco Perini
6b71ec1d2b
fix(examples): local, mixed models and fixed SearchGraph embeddings problem
2024-05-08 15:36:26 +02:00
Marco Perini
186c0d035d
fix(examples): openai std examples
2024-05-08 14:56:44 +02:00
VinciGit00
5a67bca0db
Merge branch 'pre/beta' into pr/161
2024-05-06 14:50:04 +02:00
VinciGit00
5e1d5db6da
Update search_internet_node.py
2024-05-06 10:09:17 +02:00
VinciGit00
80053a2358
Merge branch 'pre/beta' of https://github.com/VinciGit00/Scrapegraph-ai into pre/beta
2024-05-06 10:07:56 +02:00
VinciGit00
389b52aabb
removed examples
2024-05-06 10:07:31 +02:00
VinciGit00
88d999e15b
add website content
2024-05-06 09:36:32 +02:00
Marco Perini
930adb38f2
feat(node): multiple url search in SearchGraph + fixes
...
Implemented GraphIteratorNode and MergeAnswersNode to create multiple istances of a graph and merge the scraped content from multiple pages
2024-05-06 00:30:09 +02:00
Marco Perini
dbb614a8dd
feat: multiple graph instances
2024-05-05 23:51:04 +02:00
Marco Perini
84fcb44aaa
feat: fixed custom_graphs example and robots_node
2024-05-05 22:02:24 +02:00
Eric Page
cc27b21c3f
Merge branch 'pre/beta' into pass-common-params-graph
2024-05-05 16:18:32 +02:00
Eric Page
3ae2ea1dbd
Miscellaneous "llm" -> "llm_model" refactors
2024-05-05 15:58:50 +02:00
VinciGit00
cb1bd00a19
removed unused node
2024-05-05 09:40:35 +02:00
Eric Page
729d5d7597
Changed node_config["llm"] to node_config["llm_model"]
2024-05-05 09:36:11 +02:00
Eric Page
c2c61625b3
Corrected logic of update_config function in base_node.py
2024-05-05 06:37:31 +02:00
Eric Page
b7539d4725
Added update_config function to base_node.py
2024-05-05 06:25:43 +02:00
Shubham Kamboj
fd59f282a8
Bug fixes
2024-05-04 22:18:54 +05:30
Shubham Kamboj
d830d1371b
Resolve merge conflicts
2024-05-04 22:01:40 +05:30
Shubham Kamboj
7599234ab9
feat: Enable end users to pass model instances of HuggingFaceHub
2024-05-04 21:42:57 +05:30
Marco Perini
df293fdfd2
Merge pull request #139 from VinciGit00/pdf_scraper_graph_introduction
...
feat: add pdf scraper
2024-05-03 21:45:09 +02:00
VinciGit00
10a94530e3
feat: add pdf scraper
2024-05-03 21:42:02 +02:00
Marco Perini
aa9271e7bc
feat: Azure implementation + embeddings refactoring
2024-05-03 21:40:01 +02:00
Marco Vinciguerra
2abe05a0cf
Merge pull request #135 from S4mpl3r/feature
2024-05-03 16:49:07 +02:00
S4mpl3r
819cbcd3be
refactor: Changed the way embedding model is created in AbstractGraph class and removed handling of embedding model creation from RAGNode. Now AbstractGraph will call a dedicated method for embedding models instead of _create_llm. This makes it easy to use any LLM with any supported embedding model.
2024-05-03 16:14:27 +03:30
Marco Perini
cb1cb616b7
feat: add base_node to __init__.py
...
Useful for people to create custom nodes
2024-05-03 14:18:12 +02:00
Marco Vinciguerra
579a27faf9
Merge pull request #126 from VinciGit00/bedrock_support
...
feat: bedrock support
2024-05-02 17:57:20 +02:00
Marco Vinciguerra
a2d5c75f10
Merge branch 'pre/beta' into main
2024-05-02 17:55:21 +02:00
Shubham Kamboj
b86aac2188
feat: Allow end users to pass model instances for llm and embedding model
2024-05-02 20:09:23 +05:30
VinciGit00
16de49fa08
add integration for bedrock
...
Co-Authored-By: redrusty2 <15157208+redrusty2@users.noreply.github.com>
2024-05-02 13:47:17 +02:00
Marco Perini
0631985e61
docs: graphs and helpers docstrings
2024-05-02 00:23:38 +02:00
Marco Perini
1409797475
docs: refactor nodes docstrings
2024-05-01 23:17:57 +02:00
