PyPI page
Author:
Diego Peláez Paquico
Summary:
Training language models to perform agentic multi-hop search through reinforcement learning
Latest version:
0.4.2
Required dependencies:
chonkie
|
colorlog
|
httpx
|
httpx-retries
|
lingua-language-detector
|
openai
|
pydantic
|
python-dotenv
|
rapidfuzz
|
renderers
|
sentence-transformers
|
skypilot
|
tiktoken
|
transformers
|
turbopuffer
|
verifiers
Optional dependencies:
flash-attn
|
torch
|
vllm
Downloads last day:
1
Downloads last week:
31
Downloads last month:
85
7-day smoothing