Easily implement RAG workflows with pre-built modules.
Project description
easy_rag
NOT YET ALLOWED.
PLAN TO APPLY OPENAI AND DEEPSEEK MODELS.
Usage
Install
pip install easy_rag
How to integrate to your service?
from easy_rag import RagService
# Step 1: 서비스 초기화
rs = RagService(
embedding_model="text-embedding-3-small", # Fix openai.
response_model="deepseek", # openai or deepseek
open_api_key="your_openai_api_key_here",
deepseek_api_key="your_deepseek_api_key_here",
deepseek_base_url="https://api.deepseek.com",
)
# Step 2: 자료 학습
# rsc()는 학습 리소스를 반환하며, 내부적으로 임베딩을 생성하고 저장
resource = rs.rsc("./rscFiles") # rscFiles 디렉토리 아래 모든 파일 학습
# Step 3: 에이전트 생성 및 쿼리
# agent()는 입력 쿼리에 대한 답변을 생성
query = "What is the summary of the first document?"
response = rs.agent(resource, query)
print(response)
MEMO.
pdf 제목을 강제하자. info.json 을 추가하는 방식 대신 pdf의 제목을 추출하는 방식으로. worker 개수 사용자 단에서 조정할 필요성. 아니면 그냥 CPU 개수로 조절하는 방식 생각.
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
easy_rag_llm-1.0.0.tar.gz
(7.0 kB
view details)
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 easy_rag_llm-1.0.0.tar.gz.
File metadata
- Download URL: easy_rag_llm-1.0.0.tar.gz
- Upload date:
- Size: 7.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b8131af1d147410f5da425521b1510c63350096ba359dde8210ab00a1fa66daf
|
|
| MD5 |
788fc0854348fcf177301427a11b876d
|
|
| BLAKE2b-256 |
cddf1246c437e74116137c3e516d681d0b5f9795cd4e618ac768abf6e5a89aa4
|
File details
Details for the file easy_rag_llm-1.0.0-py3-none-any.whl.
File metadata
- Download URL: easy_rag_llm-1.0.0-py3-none-any.whl
- Upload date:
- Size: 7.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0707f7ed40d1ced877d8c6ad36c77a706cc05570b576381737ad777722fab9a0
|
|
| MD5 |
1ddfd7487b426119889ddae97ceaa333
|
|
| BLAKE2b-256 |
2ed9694b78c08b1eef059899c56b8a5cc18734e51388d95c0971d9507a3aae71
|