-
Hello.
I'm planning to add a change to txtai to autodetect model2vec models. The best idea I have right now is the read the config.json file and see if it has the keys `apply_pca` and `apply_zipf`.…
-
Hello, I'm the primary author of txtai. I have searches that run to find projects that are using txtai on GitHub 😀
I saw what you were trying to do and wanted to share that txtai has an integration…
-
Using the tutorial [here](https://github.com/neuml/txtai/blob/master/examples/53_Integrate_LLM_Frameworks.ipynb), it seems creating a general class to wrap `ExLlama2` allows it to be used as an LLM fo…
-
Title.
See `Docs/Evaluation_Plans.md`
-
Rather than full text search , it might be useful to support some form of semantic search.
See for example [`doc2vec` semantic search](https://psychemedia.github.io/storynotes/Lang_Doc2Vec.html), o…
-
Based on the requirements and the existing TxtAI ecosystem, here's a proposed approach to develop LLM Integration for Knowledge Graph Enhancement:
1. Automatic Knowledge Graph Generation and Enrich…
-
[Docling](https://github.com/DS4SD/docling) looks like a promising text extraction library that could possibly augment or replace Apache Tika.
**Update**: Docling added 3.9 support, this is a go!
…
-
Request to integrate advanced reasoning and inference capabilities into TxtAI, here's a proposed roadmap that aims to be simple, well-integrated with TxtAI's native ecosystem, and using up-to-date lib…
-
Here's a plan to enhance TxtAI with geospatial and temporal search capabilities:
**1. Extend indexing for geospatial data:**
- Use GeoPandas for geospatial data handling, as it integrates well …
-
I tried to highlight the entire document with its list of sentences that parsed by txtai pipeline extractor, but not all of them were highlighted. Everything should be highlighted if this is done. Can…