Commit Graph

  • b7ee43788d
    Update README.md main github/main Iván Martínez 2024-11-13 20:29:56 +0100
  • 940bdd49af
    fix: 503 when private gpt gets ollama service (#2104) meng-hui 2024-10-17 18:44:28 +0800
  • 5851b02378
    feat: update llama-index + dependencies (#2092) Javier Martinez 2024-09-26 16:29:52 +0200
  • 5fbb402477
    fix: Sanitize null bytes before ingestion (#2090) Dmitri Qiu 2024-09-25 13:00:03 +0300
  • fa3c30661d
    fix: Add default mode option to settings (#2078) J 2024-09-24 02:33:02 -0400
  • f9182b3a86
    feat: Adding MistralAI mode (#2065) Liam Dowd 2024-09-24 07:31:30 +0100
  • 8c12c6830b
    fix: docker permissions (#2059) Javier Martinez 2024-09-24 08:30:58 +0200
  • 77461b96cf
    feat: add retry connection to ollama (#2084) Javier Martinez 2024-09-16 16:43:05 +0200
  • 42628596b2
    ci: bump actions/checkout to v4 (#2077) Trivikram Kamat 2024-09-08 23:53:13 -0700
  • 7603b3627d
    fix: Rectify ffmpy poetry config; update version from 0.3.2 to 0.4.0 (#2062) Artur Martins 2024-08-21 09:39:58 +0100
  • 89477ea9d3
    fix: naming image and ollama-cpu (#2056) Javier Martinez 2024-08-12 08:23:16 +0200
  • 22904ca8ad
    chore(main): release 0.6.2 (#2049) github-actions[bot] 2024-08-08 18:16:41 +0200
  • 7fefe408b4
    fix: auto-update version (#2052) Javier Martinez 2024-08-08 16:50:42 +0200
  • b1acf9dc2c
    fix: publish image name (#2043) Javier Martinez 2024-08-07 17:39:32 +0200
  • 4ca6d0cb55
    fix: add numpy issue to troubleshooting (#2048) Javier Martinez 2024-08-07 12:16:03 +0200
  • b16abbefe4
    fix: update matplotlib to 3.9.1-post1 to fix win install Javier Martinez 2024-08-07 11:26:42 +0200
  • ca2b8da69c
    chore(main): release 0.6.1 (#2041) github-actions[bot] 2024-08-05 17:17:34 +0200
  • f09f6dd255
    fix: add built image from DockerHub (#2042) Javier Martinez 2024-08-05 17:15:38 +0200
  • 1c665f7900
    fix: Adding azopenai to model list (#2035) Liam Dowd 2024-08-05 16:30:10 +0200
  • 1d4c14d7a3
    fix(deploy): generate docker release when new version is released (#2038) Javier Martinez 2024-08-05 16:18:34 +0200
  • dae0727a1b
    fix(deploy): improve Docker-Compose and quickstart on Docker (#2037) Javier Martinez 2024-08-05 16:17:36 +0200
  • 6674b46fea
    chore(main): release 0.6.0 (#1834) github-actions[bot] 2024-08-02 11:28:22 +0200
  • e44a7f5773
    chore: bump version (#2033) Javier Martinez 2024-08-02 11:26:03 +0200
  • cf61bf780f
    feat(llm): add progress bar when ollama is pulling models (#2031) Javier Martinez 2024-08-01 19:14:26 +0200
  • 50b3027a24
    docs: update docs and capture (#2029) Javier Martinez 2024-08-01 10:01:22 +0200
  • 54659588b5
    fix: nomic embeddings (#2030) Javier Martinez 2024-08-01 09:43:30 +0200
  • 8119842ae6
    feat(recipe): add our first recipe `Summarize` (#2028) Javier Martinez 2024-07-31 16:53:27 +0200
  • 40638a18a5
    fix: unify embedding models (#2027) Javier Martinez 2024-07-31 14:35:46 +0200
  • 9027d695c1
    feat: make llama3.1 as default (#2022) Javier Martinez 2024-07-31 14:35:36 +0200
  • e54a8fe043
    fix: prevent to ingest local files (by default) (#2010) Javier Martinez 2024-07-31 14:33:46 +0200
  • 1020cd5328
    fix: light mode (#2025) Javier Martinez 2024-07-31 12:59:31 +0200
  • 65c5a1708b
    chore(docker): dockerfiles improvements and fixes (#1792) Quentin McGaw 2024-07-30 17:59:38 +0200
  • d080969407
    added llama3 prompt (#1962) Robert Hirsch 2024-07-29 17:28:00 +0200
  • d4375d078f
    fix(ui): gradio bug fixes (#2021) Javier Martinez 2024-07-29 16:48:16 +0200
  • 20bad17c98
    feat(llm): autopull ollama models (#2019) Javier Martinez 2024-07-29 13:25:42 +0200
  • dabf556dae
    fix: ffmpy dependency (#2020) Javier Martinez 2024-07-29 11:56:57 +0200
  • 05a986231c
    Add proper param to demo urls (#2007) Iván Martínez 2024-07-22 14:44:03 +0200
  • b62669784b
    docs: update welcome page (#2004) Javier Martinez 2024-07-18 14:42:39 +0200
  • 2c78bb2958
    docs: add PR and issue templates (#2002) Javier Martinez 2024-07-18 12:56:10 +0200
  • 90d211c5cd
    Update README.md (#2003) Iván Martínez 2024-07-18 12:11:24 +0200
  • 43cc31f740
    feat(vectordb): Milvus vector db Integration (#1996) Jackson 2024-07-18 16:55:45 +0800
  • 4523a30c8f
    feat(docs): update documentation and fix preview-docs (#2000) Javier Martinez 2024-07-18 10:06:51 +0200
  • 01b7ccd064
    fix(config): make tokenizer optional and include a troubleshooting doc (#1998) Javier Martinez 2024-07-17 10:06:27 +0200
  • 15f73dbc48
    docs: update repo links, citations (#1990) Javier Martinez 2024-07-09 10:03:57 +0200
  • 187bc9320e
    (feat): add github button (#1989) fern 2024-07-09 01:48:47 -0500
  • dde02245bc
    fix(docs): Fix concepts.mdx referencing to installation page (#1779) Marco Braga 2024-07-08 11:19:50 -0300
  • 067a5f144c
    feat(docs): Fix setup docu (#1926) Mart 2024-07-08 16:19:16 +0200
  • 2612928839
    feat(vectorstore): Add clickhouse support as vectore store (#1883) Proger666 2024-07-08 16:18:22 +0200
  • fc13368bc7
    feat(llm): Support for Google Gemini LLMs and Embeddings (#1965) uw4 2024-07-08 11:47:36 +0200
  • 19a7c065ef
    feat(docs): update doc for ipex-llm (#1968) Shengsheng Huang 2024-07-08 15:42:44 +0800
  • b687dc8524
    feat: bump dependencies (#1987) Javier Martinez 2024-07-05 16:31:13 +0200
  • c7212ac7cc
    fix(LLM): mistral ignoring assistant messages (#1954) Pablo Orgaz 2024-05-30 15:41:16 +0200
  • 3b3e96ad6c
    Allow parameterizing OpenAI embeddings component (api_base, key, model) (#1920) Yevhenii Semendiak 2024-05-17 10:52:50 +0300
  • 45df99feb7
    Add timeout parameter for better support of openailike LLM tools on local computer (like LM Studio). (#1858) jcbonnet-fwd 2024-05-10 16:44:08 +0200
  • 966af4771d
    fix(settings): enable cors by default so it will work when using ts sdk (spa) (#1925) Fran García 2024-05-10 14:13:46 +0200
  • d13029a046
    feat(docs): add privategpt-ts sdk (#1924) Fran García 2024-05-10 14:13:15 +0200
  • 9d0d614706
    fix: Replacing unsafe `eval()` with `json.loads()` (#1890) Patrick Peng 2024-04-30 15:58:19 +0800
  • e21bf20c10
    feat: prompt_style applied to all LLMs + extra LLM params. (#1835) icsy7867 2024-04-30 03:53:10 -0400
  • c1802e7cf0
    fix(docs): Update installation.mdx (#1866) Daniel Gallego Vico 2024-04-19 17:10:58 +0200
  • 2a432bf9c5
    fix: make embedding_api_base match api_base when on docker (#1859) Marco Repetto 2024-04-19 06:42:19 -0700
  • 947e737f30
    fix: "no such group" error in Dockerfile, added docx2txt and cryptography deps (#1841) dividebysandwich 2024-04-19 15:40:00 +0200
  • 49ef729abc Allow passing HF access token to download tokenizer. Fallback to default tokenizer. imartinez 2024-04-19 15:38:25 +0200
  • 347be643f7
    fix(llm): special tokens and leading space (#1831) Pablo Orgaz 2024-04-04 14:37:29 +0200
  • 08c4ab175e Fix version in poetry imartinez 2024-04-03 10:59:35 +0200
  • f469b4619d Add required Ollama setting imartinez 2024-04-02 18:27:57 +0200
  • 94ef38cbba
    chore(main): release 0.5.0 (#1708) github-actions[bot] 2024-04-02 17:45:15 +0200
  • 8a836e4651
    feat(docs): Add guide Llama-CPP Linux AMD GPU support (#1782) Иван 2024-04-02 17:55:05 +0300
  • f0b174c097
    feat(ui): Add Model Information to ChatInterface label Ingrid Stevens 2024-04-02 16:52:27 +0200
  • bac818add5
    feat(code): improve concat of strings in ui (#1785) igeni 2024-04-02 17:42:40 +0300
  • ea153fb92f
    feat(scripts): Wipe qdrant and obtain db Stats command (#1783) Brett England 2024-04-02 10:41:42 -0400
  • b3b0140e24
    feat(llm): Ollama LLM-Embeddings decouple + longer keep_alive settings (#1800) Robin Boone 2024-04-02 16:23:10 +0200
  • 83adc12a8e
    feat(RAG): Introduce SentenceTransformer Reranker (#1810) machatschek 2024-04-02 10:29:51 +0200
  • f83abff8bc
    feat(docker): set default Docker to use Ollama (#1812) Marco Repetto 2024-04-01 13:08:48 +0200
  • 087cb0b7b7
    feat(rag): expose similarity_top_k and similarity_score to settings (#1771) icsy7867 2024-03-20 17:25:26 -0400
  • 774e256052
    fix: Fixed docker-compose (#1758) Marco Repetto 2024-03-20 21:36:45 +0100
  • 6f6c785dac
    feat(llm): Ollama timeout setting (#1773) Iván Martínez 2024-03-20 21:33:46 +0100
  • c2d694852b
    feat: wipe per storage type (#1772) Brett England 2024-03-20 16:31:44 -0400
  • 7d2de5c96f
    fix(ingest): update script label (#1770) Ikko Eltociear Ashimine 2024-03-21 04:23:08 +0900
  • 348df781b5
    feat(UI): Faster startup and document listing (#1763) Iván Martínez 2024-03-20 19:11:44 +0100
  • 572518143a
    feat(docs): Feature/upgrade docs (#1741) Iván Martínez 2024-03-19 21:26:53 +0100
  • 134fc54d7d
    feat(ingest): Created a faster ingestion mode - pipeline (#1750) Brett England 2024-03-19 16:24:46 -0400
  • 1efac6a3fe
    feat(llm - embed): Add support for Azure OpenAI (#1698) Otto L 2024-03-15 16:49:50 +0100
  • 258d02d87c
    fix(docs): Minor documentation amendment (#1739) Brett England 2024-03-15 11:36:32 -0400
  • 63de7e4930
    feat: unify settings for vector and nodestore connections to PostgreSQL (#1730) Brett England 2024-03-15 04:55:17 -0400
  • 68b3a34b03
    feat(nodestore): add Postgres for the doc and index store (#1706) Brett England 2024-03-14 12:12:33 -0400
  • d17c34e81a
    fix(settings): set default tokenizer to avoid running make setup fail (#1709) Iván Martínez 2024-03-13 09:53:40 +0100
  • 84ad16af80
    feat(docs): upgrade fern (#1596) Andrew Jiang 2024-03-12 09:02:56 +1100
  • 821bca32e9
    feat(local): tiktoken cache within repo for offline (#1467) Arun Yadav 2024-03-12 03:25:13 +0530
  • 02dc83e8e9
    feat(llm): adds serveral settings for llamacpp and ollama (#1703) icsy7867 2024-03-11 17:51:05 -0400
  • 410bf7a71f
    feat(ui): maintain score order when curating sources (#1643) Hoffelhas 2024-03-11 22:27:30 +0100
  • 290b9fb084
    feat(ui): add sources check to not repeat identical sources (#1705) icsy7867 2024-03-11 17:24:18 -0400
  • 1b03b369c0
    chore(main): release 0.4.0 (#1628) github-actions[bot] 2024-03-06 17:53:35 +0100
  • 45f05711eb
    feat: Upgrade to LlamaIndex to 0.10 (#1663) Iván Martínez 2024-03-06 17:51:30 +0100
  • 12f3a39e8a
    Update x handle to zylon private gpt (#1644) Daniel Gallego Vico 2024-02-23 15:51:35 +0100
  • cd40e3982b
    feat(Vector): support pgvector (#1624) TQ 2024-02-20 22:29:26 +0800
  • 066ea5bf28
    chore(main): release 0.3.0 (#1413) github-actions[bot] 2024-02-16 17:42:39 +0100
  • aa13afde07
    feat(UI): Select file to Query or Delete + Delete ALL (#1612) Iván Martínez 2024-02-16 17:36:09 +0100
  • 24fb80ca38
    fix(UI): Updated ui.py. Frees up the CPU to not be bottlenecked. icsy7867 2024-02-16 06:52:14 -0500
  • 6bbec79583
    feat(llm): Add support for Ollama LLM (#1526) Ygal Blum 2024-02-09 16:50:50 +0200
  • b178b51451
    feat(bulk-ingest): Add --ignored Flag to Exclude Specific Files and Directories During Ingestion (#1432) Nick Smirnov 2024-02-07 21:59:32 +0300