50 Commits
Author SHA1 Message Date
davidmezzetti 7672f42743 httpx import at module level causes ModuleNotFoundError for Embeddings-only usage, closes #1012 2026-01-23 11:39:11 -05:00
davidmezzetti cf45a400ce Add GGML ANN, closes #975 2025-10-30 17:53:44 -04:00
davidmezzetti e6e1d57ac4 Add quantization support to Torch ANN, closes #971 2025-10-17 07:24:05 -04:00
davidmezzetti e765be3f6c Refactor of ann and vectors packages for sparse vectors. Closes #930. Closes #934. Closes #935. Closes #936. Closes #937. 2025-07-14 07:48:23 -04:00
davidmezzetti db60bd76e6 Add IVFFlat indexing for sparse vectors, closes #929 2025-07-08 21:44:35 -04:00
davidmezzetti d9c50c84b7 Add sparse vector scoring, closes #924. Update default Embeddings parameters, closes #925 2025-07-04 09:26:36 -04:00
davidmezzetti b18854f788 Migrate to smolagents, closes #890 2025-04-11 09:38:19 -04:00
davidmezzetti a92bb73c9c Add similar query clause to graph queries, closes #875 2025-02-17 13:07:42 -05:00
davidmezzetti 53f5af52ad Ensure staticvectors is installed before calling method, closes #876 2025-02-12 07:33:14 -05:00
davidmezzetti 7dc1e4bb5f Update test 2025-02-07 09:01:23 -05:00
davidmezzetti bf32498a79 Add semantic chunking, closes #812 2025-02-04 07:45:25 -05:00
davidmezzetti 13bafb01c6 Add support for GLiNER models, closes #862 2025-01-31 10:37:02 -05:00
davidmezzetti f79d8062ae Replace fasttext and pymagnitude with staticvectors. Closes #857. Closes #858. Closes #859 2025-01-27 11:17:51 -05:00
davidmezzetti 9efc9ba070 Add text extraction with Docling, closes #814. Refactor Textractor pipeline into multiple pipelines, closes #828 2024-12-03 14:27:49 -05:00
davidmezzetti a246052f4a Add model2vec vectorization, closes #801 2024-10-21 13:53:11 -04:00
davidmezzetti 8ffaccfe7a Add Text to Audio pipeline, closes #792. Add support for SpeechT5, closes #793. Updated cache methods, closes #794. Add audio signal processing, closes #795. 2024-10-11 08:30:20 -04:00
davidmezzetti ea730ff5ec Refactor microphone pipeline to remove unnecessary dependencies and improve overall logic #785 2024-09-26 20:28:10 -04:00
davidmezzetti 748998d21d Add an audio playback pipeline, closes #786 2024-09-20 13:31:08 -04:00
davidmezzetti d535fc5101 Add SQLite ANN, closes #780 2024-09-04 10:55:14 -04:00
davidmezzetti 3422e0fbb1 Add additional vector backends. Closes #725. Closes #726. Closes #727 2024-05-28 08:26:29 -04:00
davidmezzetti f3b7cb9569 Update #704 to not require a path parameter in Embeddings as not all vector models need a path. Update test. 2024-05-25 06:25:30 -04:00
davidmezzetti 498eb7c977 Add Postgres Full Text Scoring, closes #713 2024-05-09 16:42:54 -04:00
davidmezzetti 9aa2edd4fb Add RDBMS Graph, closes #699 2024-04-24 11:20:19 -04:00
davidmezzetti f2adc383eb Update HFTrainer to add PEFT support, closes #654 2024-01-31 13:52:47 -05:00
davidmezzetti 6ce37d4cfc Refactor LLM pipeline to support multiple framework methods. Closes #614. Closes #611. Closes #554 2023-12-09 11:39:39 -05:00
davidmezzetti a1b92e0a33 Add metadata support for client-server databases, closes #532 2023-08-25 20:47:34 -04:00
davidmezzetti 80d4f340f7 Raise error message when DuckDB backend not found, closes #464 2023-04-21 11:17:36 -04:00
davidmezzetti 5aeefc3ab8 Update tests 2023-02-19 13:49:13 -05:00
davidmezzetti 65a110e9fb Add TextToSpeech pipeline, closes #389 2022-11-29 11:51:10 -05:00
davidmezzetti b6cddd1378 Update onnx quantization call to remove MatMul warnings #369 2022-10-19 20:09:00 -04:00
davidmezzetti 8bd6bc7b38 Add a semantic graph component, closes #339 2022-09-14 11:18:18 -04:00
davidmezzetti 7e9ee71cdf Update pylint statement 2022-09-12 10:05:57 -04:00
davidmezzetti f28a1c0154 Update console to conditionally import library, closes #333 2022-09-12 10:04:23 -04:00
davidmezzetti c39bfad8e3 Add Image Hash pipeline, closes #240 2022-03-07 10:01:21 -05:00
davidmezzetti 41e93f097c Add support for loading/storing embedding indexes on cloud storage, closes #229 2022-02-23 15:31:47 -05:00
davidmezzetti 466f88aa79 Add console task, closes #215. Add export task, closes #216 2022-02-01 21:24:29 -05:00
davidmezzetti 0162b5974c Add workflow scheduling, closes #206 2022-01-27 12:27:14 -05:00
davidmezzetti b14d8769dd Update test method docs for consistency 2021-12-22 06:44:49 -05:00
davidmezzetti cbd6849697 Increase test coverage 2021-11-27 22:15:12 -05:00
davidmezzetti dbdb68144b Add objects and caption pipelines to API, closes #161 2021-11-27 15:30:46 -05:00
davidmezzetti 1b80f7674f Update optional package tests to better simulate missing packages, closes #154 2021-11-22 13:55:02 -05:00
davidmezzetti 538c052de2 Update test 2021-11-18 16:07:13 -05:00
davidmezzetti d9b4afaa7e Fix bug with xmltodict not being wrapped in a conditional import, closes #146 2021-11-15 13:31:48 -05:00
davidmezzetti 809151c3cc Add tabular pipeline, closes #134 2021-11-02 11:26:09 -04:00
davidmezzetti 8cbbf8d76d Add ONNX export pipeline backed by onnxmltools library, closes #124 2021-10-12 19:15:33 -04:00
davidmezzetti 2ed7c7fec4 Add ONNX support for Embeddings and Pipelines, closes #109 2021-08-31 19:18:21 -04:00
davidmezzetti de6da9daba Add ONNX export pipeline, closes #107 2021-08-27 11:58:52 -04:00
davidmezzetti 68d2477f4f Add new vector method and fix performance regression, closes #101, closes #102 2021-08-17 11:57:38 -04:00
davidmezzetti b90b2f4460 Make faiss a required library for all platforms (#98) 2021-08-14 17:27:01 -04:00
davidmezzetti 1f82d54009 Make txtai install modular, base install is now a minimal set of libraries to support most commonly used functionality, closes #97 2021-08-13 20:02:40 -04:00