muthuk1
/

graphrag-inference-hackathon

Model card Files Files and versions

graphrag-inference-hackathon / web /src /lib /llm-providers.ts

Commit History

Improve latency: parallel LLM calls, embedding cache, client reuse

90b36cb

muthuk1 commited on 5 days ago

Add .gitignore, dataset metadata, retrieval layer, and latest web/graphrag updates

577adc4

muthuk1 commited on 5 days ago

Add universal LLM provider layer supporting 12 providers including Ollama

641deaa
verified

muthuk1 commited on 12 days ago