Update readme
This commit is contained in:
parent
4a43cd0501
commit
eac87d8603
1 changed files with 6 additions and 1 deletions
|
|
@ -8,7 +8,9 @@ Agentic RAG built on [LanceDB](https://lancedb.com/), [Pydantic AI](https://ai.p
|
||||||
- **Reranking** — MxBAI, Cohere, Zero Entropy, or vLLM
|
- **Reranking** — MxBAI, Cohere, Zero Entropy, or vLLM
|
||||||
- **Question answering** — QA agents with citations (page numbers, section headings)
|
- **Question answering** — QA agents with citations (page numbers, section headings)
|
||||||
- **Research agents** — Multi-agent workflows via pydantic-graph: plan, search, evaluate, synthesize
|
- **Research agents** — Multi-agent workflows via pydantic-graph: plan, search, evaluate, synthesize
|
||||||
- **Document structure** — Stores full [DoclingDocument](https://docling-project.github.io/docling/concepts/docling_document/), enabling structure-aware context expansion and visual grounding
|
- **Document structure** — Stores full [DoclingDocument](https://docling-project.github.io/docling/concepts/docling_document/), enabling structure-aware context expansion
|
||||||
|
- **Visual grounding** — View chunks highlighted on original page images
|
||||||
|
- **Time travel** — Query the database at any historical point with `--before`
|
||||||
- **Multiple providers** — Embeddings: Ollama, OpenAI, VoyageAI, LM Studio, vLLM. QA/Research: any model supported by Pydantic AI
|
- **Multiple providers** — Embeddings: Ollama, OpenAI, VoyageAI, LM Studio, vLLM. QA/Research: any model supported by Pydantic AI
|
||||||
- **Local-first** — Embedded LanceDB, no servers required. Also supports S3, GCS, Azure, and LanceDB Cloud
|
- **Local-first** — Embedded LanceDB, no servers required. Also supports S3, GCS, Azure, and LanceDB Cloud
|
||||||
- **MCP server** — Expose as tools for AI assistants (Claude Desktop, etc.)
|
- **MCP server** — Expose as tools for AI assistants (Claude Desktop, etc.)
|
||||||
|
|
@ -54,6 +56,9 @@ haiku-rag ask "How does the proposed method compare to the baseline on MMLU?" --
|
||||||
# Research mode — iterative planning and search
|
# Research mode — iterative planning and search
|
||||||
haiku-rag research "What are the limitations of the approach?" --verbose
|
haiku-rag research "What are the limitations of the approach?" --verbose
|
||||||
|
|
||||||
|
# Interactive research — human-in-the-loop with decision points
|
||||||
|
haiku-rag research "Compare the approaches discussed" --interactive
|
||||||
|
|
||||||
# Watch a directory for changes
|
# Watch a directory for changes
|
||||||
haiku-rag serve --monitor
|
haiku-rag serve --monitor
|
||||||
```
|
```
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue