Simple RAG library
Project description
Vishakha Rag lib
A simple RAG (Retrival-Agumented-Generation) Library Using PDFs and LLMs.
Features
-Load Pdf files -Chuks texts -generate embeddings -store in vector database -search nearast vectors -Retirive revelant Data -Connect With any LLM Api
Usage
''' Python from vish_rag_lib import RAGSystem
rag=RAGSystem() rag.ingest("Sample.pdf")
def my_llm(prompt): return "LLM respones" answer=rag.ask("What is AI?",my_llm) print(answer)
Installation
pip install vish-rag-lib
Work-Flow-RAG
Chunks-Text divided into small Parts Embedding-Sentence convert into meaining base vectors vectors-Loading embeddings search the similar queary answers Retriever- User queary storted in vectorDB (Most relevan chunks search)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vish_rag_lib-0.1.8.tar.gz.
File metadata
- Download URL: vish_rag_lib-0.1.8.tar.gz
- Upload date:
- Size: 4.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
be5344cd3de1be212cb757ad4bba21fd10f010077228589df6edf547895608b9
|
|
| MD5 |
536a14eee9f58ab980e576f0ff19a83b
|
|
| BLAKE2b-256 |
5de7660aabd79a5c99259fb19e4fccdafb30bb3f576cd8cb7e11597a8ddd7998
|
File details
Details for the file vish_rag_lib-0.1.8-py3-none-any.whl.
File metadata
- Download URL: vish_rag_lib-0.1.8-py3-none-any.whl
- Upload date:
- Size: 5.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bb24d4be4e74a202d5cf3a184a57c86880c9fa5eab59e189229940932edeb280
|
|
| MD5 |
23fd6aabffe1acecbbebe2107322ceb9
|
|
| BLAKE2b-256 |
092ac6d38deda045081a78fdb6f25b53ace21b552e3e37ecf360c602585458ea
|