guest400123064 Goto Github PK

bbm25-haystack

Simple Haystack in-memory document store alternative that performs incremental indexing and supports SentencePiece tokenizer.

distill-retriever

Distilling bi-encoders for fast ad-hoc query embedding generation

empathic-bot

empathic-decoding-parameter

eqt-inference-example

Showing how to predict the question type and intention using models from the EQT paper

fed-iris

A prototype federated-learning iris-classifier CLI application

fedkgqa

gen-item-desc

guest400123064

Guest400123064's README

haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.

keyspacy

A simple spaCy integration of KeyBERT

mephisto-timeout

Forked from the FAIR Mephisto repository to implement experimental maximum wait time feature.

mining-risk-contagion

parse-sec-filings

Fetch and parse SEC 10-K, 20-F, and 40-F filings.

pennguin

sentence-negator

Simple set of utilities to generate negated version of input sentences

sif-bert

Experimental BERT sentence embedding method with SIF pooling strategy