unclecode
685706e0aa
Update version, and change log
2024-06-30 00:17:43 +08:00
unclecode
7b0979e134
Update Redme and Docker file
2024-06-30 00:15:43 +08:00
unclecode
61ae2de841
1/Update setup.py to support following modes:
...
- default (most frequent mode)
- torch
- transformers
- all
2/ Update Docker file
3/ Update documentation as well.
2024-06-30 00:15:29 +08:00
unclecode
5b28eed2c0
Add a temporary solution for when we can't crawl websites in headless mode.
2024-06-29 23:25:50 +08:00
unclecode
f8a11779fe
Update change log
2024-06-26 16:48:36 +08:00
unclecode
d11a83c232
## [0.2.71] 2024-06-26
...
• Refactored `crawler_strategy.py` to handle exceptions and improve error messages
• Improved `get_content_of_website_optimized` function in `utils.py` for better performance
• Updated `utils.py` with latest changes
• Migrated to `ChromeDriverManager` for resolving Chrome driver download issues
2024-06-26 15:34:15 +08:00
unclecode
3255c7a3fa
Update CHANGELOG.md with recent commits
2024-06-26 15:20:34 +08:00
unclecode
4756d0a532
Refactor crawler_strategy.py to handle exceptions and improve error messages
2024-06-26 15:04:33 +08:00
unclecode
7ba2142363
chore: Refactor get_content_of_website_optimized function in utils.py
2024-06-26 14:43:09 +08:00
unclecode
96d1eb0d0d
Some updated ins utils.py
2024-06-26 13:03:03 +08:00
unclecode
144cfa0eda
Switch to ChromeDriverManager due some issues with download the chrome driver
2024-06-26 13:00:17 +08:00
unclecode
a0dff192ae
Update README for speed example
2024-06-24 23:06:12 +08:00
unclecode
1fffeeedd2
Update Readme: Showcase the speed
2024-06-24 23:02:08 +08:00
unclecode
f51b078042
Update reame example.
2024-06-24 22:54:29 +08:00
unclecode
b6023a51fb
Add star chart
2024-06-24 22:47:46 +08:00
unclecode
78cfad8b2f
chore: Update version to 0.2.7 and improve extraction function speed
2024-06-24 22:39:56 +08:00
unclecode
68b3dff74a
Update CSS
2024-06-23 00:36:03 +08:00
unclecode
bfc4abd6e8
Update documents
2024-06-22 20:57:03 +08:00
unclecode
8c77a760fc
Fixed:
...
- Redirect "/" to mkdocs
2024-06-22 20:54:32 +08:00
unclecode
b9bf8ac9d7
Fix mounting the "/" to mkdocs site folder
2024-06-22 20:41:39 +08:00
unclecode
d6182bedd7
chore:
...
- Add demo page to the new mkdocs
- Set website home page to mkdocs
2024-06-22 20:36:01 +08:00
unclecode
2217904876
Update .gitignore
2024-06-22 18:12:12 +08:00
unclecode
2c2362b4d3
issue 19 is resolved
...
- Update Dockerfile to install mkdocs and build documentation
2024-06-22 17:18:00 +08:00
unclecode
612ed3fef2
chore: Update print statement to use markdown format
2024-06-21 19:10:13 +08:00
unclecode
fb2a6d0d04
chore: Update documentation link in README.md
2024-06-21 18:05:18 +08:00
unclecode
19d3d39115
Update Marge the DOCS branch
2024-06-21 18:04:13 +08:00
unclecode
c1413e6916
chore: Update documentation link in README.md
2024-06-21 17:57:47 +08:00
unclecode
e7705e661a
ADD MKDocs
2024-06-21 17:56:54 +08:00
unclecode
21b110bfd7
Update LLMExtractionStrategy to disable chunking if specified, Add example of summarization for a web page.
2024-06-19 19:03:35 +08:00
unclecode
1fcb573909
chore: Update table of contents in README.md
2024-06-19 18:53:22 +08:00
unclecode
0f6c5f5453
chore: Update configuration values, create new example, and update Dockerfile and README
2024-06-19 18:50:58 +08:00
unclecode
350ca1511b
chore: Update configuration values, create new example, and update Dockerfile and README
2024-06-19 18:48:20 +08:00
unclecode
539263a8ba
chore: Update configuration values for chunk token threshold, overlap rate, and minimum word threshold. Create a new example for LLMExtraction Strategy, update Dockerfile, and README
2024-06-19 18:32:20 +08:00
unclecode
3f0e265baf
Merge branch 'format-inline-tags'
2024-06-19 00:48:38 +08:00
unclecode
21e2538e57
Update quickstart.py
2024-06-19 00:37:53 +08:00
unclecode
480902bd66
Update README
2024-06-18 20:02:21 +08:00
unclecode
853b9d59d8
feat: Add hooks for enhanced control over Selenium drivers
...
- Added six hooks: on_driver_created, before_get_url, after_get_url, before_return_html, on_user_agent_updated.
- Included example usage in quickstart.py.
- Updated README and changelog.
2024-06-18 20:00:51 +08:00
unclecode
6d04284c44
Merge branch 'hooks'
2024-06-18 19:53:50 +08:00
unclecode
4a50781453
chore: Remove local and .files folders from .gitignore
2024-06-17 15:57:34 +08:00
unclecode
18561c55ce
Remove .files folder from repository
2024-06-17 15:56:56 +08:00
unclecode
77da48050d
chore: Add custom headers to LocalSeleniumCrawlerStrategy
2024-06-17 15:50:03 +08:00
unclecode
9a97aacd85
chore: Add hooks for customizing the LocalSeleniumCrawlerStrategy
2024-06-17 15:37:18 +08:00
unclecode
52daf3936a
Fix typo in README
2024-06-17 15:15:37 +08:00
unclecode
2f246d19f4
Enhancement: Replaced inline HTML tags with textual format for better LLM context handling #45
2024-06-17 15:14:56 +08:00
unclecode
413595542a
Enhancement: Replaced inline HTML tags with textual format for better LLM context handling #24
2024-06-17 15:14:34 +08:00
unclecode
42a5da854d
Update version and change log.
2024-06-17 14:47:58 +08:00
unclecode
d1d83a6ef7
Fix issue #22 : Use MD5 hash for caching HTML files to handle long URLs
2024-06-17 14:44:01 +08:00
unclecode
194050705d
chore: Add pillow library to requirements.txt
2024-06-10 23:03:32 +08:00
unclecode
989f8c91c8
Update README
2024-06-08 18:50:35 +08:00
unclecode
edba5fb5e9
Update README
2024-06-08 18:48:21 +08:00
