Helper modules for AI Engineering RAG Bootcamp reference implementations
Project description
aieng-rag-utils
aieng-rag-utils is a Python library providing utility functions and tools to streamline Retrieval-Augmented Generation (RAG) workflows. It is designed to help AI engineers build, evaluate, and deploy RAG-based applications efficiently.
Features
- Document loaders, chunkers and pretty-print
- Web Search
- Vector store integrations
- Query and retrieval helpers
- Evaluation and benchmarking tools
Installation
pip3 install aieng-rag-utils
Sample Usage
from aieng.rag.utils import get_device_name
from aieng.rag.utils.search import DocumentReader
from aieng.rag.utils.pubmed import RAGLLM
device = get_device_name()
doc_reader = DocumentReader(directory_path="./source_documents")
docs, chunks = doc_reader.load()
llm = RAGLLM(
llm_type="openai",
llm_name="gpt-4o",
api_base=OPENAI_BASE_URL,
api_key=OPENAI_API_KEY,
).load_model(**rag_cfg) # RAG Configuration
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 aieng_rag_utils-0.1.0a1.tar.gz.
File metadata
- Download URL: aieng_rag_utils-0.1.0a1.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
df8622b5ee31563cf02898460db401896b80a375046c54247fc03fd3332a2f8c
|
|
| MD5 |
eaa4e91441e583f4da8473a0e660a3a1
|
|
| BLAKE2b-256 |
db4c469083dddb58e8c9f7a36f8776e58368e9a29a4d0f0022f16fa547e80f4e
|
File details
Details for the file aieng_rag_utils-0.1.0a1-py3-none-any.whl.
File metadata
- Download URL: aieng_rag_utils-0.1.0a1-py3-none-any.whl
- Upload date:
- Size: 9.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b3ac3db9c56d152e6f1fb3477bd4851735fd31424d81b83a358750e2c742ba10
|
|
| MD5 |
d4c19042361b54b7cc18a18009a62664
|
|
| BLAKE2b-256 |
14ac10554499dc959a6f1d3103c23a6293d0150a8cc76af458c8affbd5a12a47
|