She/her
Open Sourceress at @llamaindex.bsky.social
Girly dev who likes AI and python๐ ๐ป
Find out more here ๐ clelia.dev
Clelia Astra Bertelli
Loading...
Our OSS engineer @cle-does-things.bsky.social recently built ๐น๐ถ๐๐ฒ๐๐ฒ๐ฎ๐ฟ๐ฐ๐ต, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse โก
litesearch demonstrates how developers can assemble a high-performance, local-first pipeline using tools from across the ecosystem:
Find all the code on GitHub: github.com/AstraBert/l...
- Parse your unstructured documents with LiteParse, the lightning fast parser that we just open sourced at @llamaindex.bsky.social
- Chunk with @chonkie.bsky.social
- Embed with a local model through @hf.co transformers.js
โ Success โ ๐๐๐๐๐๐ ๐พ๐(๐)
โ Error โ ๐๐๐๐๐๐ ๐ด๐๐(๐๐๐๐๐๐๐)
This helps with control flow if you're trying to achieve a more monadic-style error handling.
๐ฆ Install: uv add better-result-py
๐ฉโ๐ป Repo: github.com/AstraBert/b...
๐ New release: ๐ฏ๐ฒ๐๐๐ฒ๐ฟ-๐ฟ๐ฒ๐๐๐น๐-๐ฝ๐ ๐๐ญ.๐ญ.๐ฌ
Inspired by the better-result library in the JS ecosystem, I built better-result-py to bring a Rust-style Result type to Python.
With v1.1.0, I introduced the ๐พ๐ and ๐ด๐๐ classes to make control flow clearer and more explicit:
The voice agent we built:
- Takes voice command from terminal
- Calls tools to explore available files and parse them, powered by LiteParse, our fully-local parser
- Live-updates you on its task๐
Take a look at the demoโ๏ธ
Repo: github.com/run-llama/v...
- Store embeddings in a local @qdrant.bsky.social edge shard (custom-built in Rust and compiled as a native add-on๐ฆ)
- Retrieve from stored files with (optional) path-based filtering and a relevance threshold
The app runs on @bun.sh, so make sure you have it installed๐ฅ
Hey there ๐ , I built ๐น๐ถ๐๐ฒ๐๐ฒ๐ฎ๐ฟ๐ฐ๐ต, a fully local document ingestion and retrieval CLI and TUI app, powered by LiteParseโก
The Google DeepMind team really cooked with Gemini 3.1 in the Live API: it's fast and the output quality is great๐ฅ
That's why at @llamaindex.bsky.social we decided to test it out with our bread and butter: document processing๐
