What's Changed

Breaking Changes 🛠

• :fire: add LLaVA support and GPT vision API, Multiple requests for llama.cpp, return JSON types by @mudler in https://github.com/mudler/LocalAI/pull/1254
• refactor: rename llama-stable to llama-ggml by @mudler in https://github.com/mudler/LocalAI/pull/1287

Bug fixes :bug:

• fix: respect OpenAI spec for response format by @mudler in https://github.com/mudler/LocalAI/pull/1289
• fix: handle grpc and llama-cpp with REBUILD=true by @mudler in https://github.com/mudler/LocalAI/pull/1328
• fix: propagate CMAKE_ARGS when building grpc by @mudler in https://github.com/mudler/LocalAI/pull/1334
• fix(vall-e-x): correctly install reqs in environment by @mudler in https://github.com/mudler/LocalAI/pull/1377

Exciting New Features 🎉

• feat(certificates): add support for custom CA certificates by @vitorstone in https://github.com/mudler/LocalAI/pull/880
• feat(conda): conda environments by @mudler in https://github.com/mudler/LocalAI/pull/1144
• refactor: move backends into the backends directory by @mudler in https://github.com/mudler/LocalAI/pull/1279
• feat: allow to run parallel requests by @mudler in https://github.com/mudler/LocalAI/pull/1290
• feat(transformers): add embeddings with Automodel by @mudler in https://github.com/mudler/LocalAI/pull/1308
• ci(core): add -core images without python deps by @mudler in https://github.com/mudler/LocalAI/pull/1309
• feat: initial watchdog implementation by @mudler in https://github.com/mudler/LocalAI/pull/1341
• feat: update whisper_cpp with CUBLAS, HIPBLAS, METAL, OPENBLAS, CLBLAST support by @wuxxin in https://github.com/mudler/LocalAI/pull/1302

👒 Dependencies

• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1231
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1236
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1285
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1288
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1291

Other Changes

• Update .gitignore for backend/llama.cpp by @dave-gray101 in https://github.com/mudler/LocalAI/pull/1235
• llama index example by @sfxworks in https://github.com/mudler/LocalAI/pull/1237
• chianlit example by @sfxworks in https://github.com/mudler/LocalAI/pull/1238
• Fixes the bug 1196 by @diego-minguzzi in https://github.com/mudler/LocalAI/pull/1232
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1242
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1256
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1265
• deps(go-piper): update to 2023.11.6-3 by @M0Rf30 in https://github.com/mudler/LocalAI/pull/1257
• feat(llama.cpp): support lora with scale and yarn by @mudler in https://github.com/mudler/LocalAI/pull/1277
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1272
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1280
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1282
• feat: queue up requests if not running parallel requests by @mudler in https://github.com/mudler/LocalAI/pull/1296
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1297
• fix(api/config): allow YAML config with .yml by @Papawy in https://github.com/mudler/LocalAI/pull/1299
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1300
• llava.yaml (yaml format standardization) by @lunamidori5 in https://github.com/mudler/LocalAI/pull/1303
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1304
• :arrow_up: Update mudler/go-piper by @localai-bot in https://github.com/mudler/LocalAI/pull/1305
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1306
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1310
• fix: ExLlama Backend Context Size & Rope Scaling by @ok2sh in https://github.com/mudler/LocalAI/pull/1311
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1313
• docs: Initial import from localai-website by @mudler in https://github.com/mudler/LocalAI/pull/1312
• fix: move python header comments below shebang in some backends by @B4ckslash in https://github.com/mudler/LocalAI/pull/1321
• Feat: OSX Local Codesigning by @dave-gray101 in https://github.com/mudler/LocalAI/pull/1319
• docs: Add llava, update hot topics by @mudler in https://github.com/mudler/LocalAI/pull/1322
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1323
• docs: Update Features->Embeddings page to reflect backend restructuring by @B4ckslash in https://github.com/mudler/LocalAI/pull/1325
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1330
• fix: rename transformers.py to avoid circular import by @mudler in https://github.com/mudler/LocalAI/pull/1337
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1340
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1345
• feat(petals): add backend by @mudler in https://github.com/mudler/LocalAI/pull/1350
• fix: go-piper add libucd at linking time by @M0Rf30 in https://github.com/mudler/LocalAI/pull/1357
• docs: Add docker instructions, add community projects section in README by @mudler in https://github.com/mudler/LocalAI/pull/1359
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1351
• docs: Update getting started and GPU section by @mudler in https://github.com/mudler/LocalAI/pull/1362
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1363
• ci: limit concurrent jobs by @mudler in https://github.com/mudler/LocalAI/pull/1364
• fix/docs: Python backend dependencies by @B4ckslash in https://github.com/mudler/LocalAI/pull/1360
• ci: split into reusable workflows by @mudler in https://github.com/mudler/LocalAI/pull/1366
• fix: OSX Build Fix Part 1: Metal by @dave-gray101 in https://github.com/mudler/LocalAI/pull/1365
• docs: add fine-tuning example by @mudler in https://github.com/mudler/LocalAI/pull/1374
• docs: site/how-to clean up by @lunamidori5 in https://github.com/mudler/LocalAI/pull/1342
• :arrow_up: Update ggerganov/llama.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1375
• :arrow_up: Update ggerganov/whisper.cpp by @localai-bot in https://github.com/mudler/LocalAI/pull/1227

New Contributors

• @vitorstone made their first contribution in https://github.com/mudler/LocalAI/pull/880
• @sfxworks made their first contribution in https://github.com/mudler/LocalAI/pull/1237
• @diego-minguzzi made their first contribution in https://github.com/mudler/LocalAI/pull/1232
• @M0Rf30 made their first contribution in https://github.com/mudler/LocalAI/pull/1257
• @Papawy made their first contribution in https://github.com/mudler/LocalAI/pull/1299
• @ok2sh made their first contribution in https://github.com/mudler/LocalAI/pull/1311
• @B4ckslash made their first contribution in https://github.com/mudler/LocalAI/pull/1321
• @wuxxin made their first contribution in https://github.com/mudler/LocalAI/pull/1302

Full Changelog: https://github.com/mudler/LocalAI/compare/v1.40.0...v2.0.0