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
parent 3f0e265baf
commit 539263a8ba
11 changed files with 212 additions and 130 deletions
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,21 +1,22 @@
-aiohttp
-aiosqlite
-bs4
-fastapi
-html2text
-httpx
-litellm
-nltk
-pydantic
-python-dotenv
-requests
-rich
-scikit-learn
-selenium
-uvicorn
-transformers
-chromedriver-autoinstaller
-torch
-onnxruntime
-tokenizers
-pillow
+numpy==1.25.0
+aiohttp==3.9.5
+aiosqlite==0.20.0
+beautifulsoup4==4.12.3
+fastapi==0.111.0
+html2text==2024.2.26
+httpx==0.27.0
+litellm==1.40.17
+nltk==3.8.1
+pydantic==2.7.4
+python-dotenv==1.0.1
+requests==2.32.3
+rich==13.7.1
+scikit-learn==1.5.0
+selenium==4.21.0
+uvicorn==0.30.1
+transformers==4.41.2
+chromedriver-autoinstaller==0.6.4
+torch==2.3.1
+onnxruntime==1.18.0
+tokenizers==0.19.1
+pillow==10.3.0