58 Commits

Author	SHA1	Message	Date
Richard Palethorpe	bf6426aef2	feat: Realtime API support reboot (#5392) ... * feat(realtime): Initial Realtime API implementation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore: go mod tidy Signed-off-by: Richard Palethorpe <io@richiejp.com> * feat: Implement transcription only mode for realtime API Reduce the scope of the real time API for the initial realease and make transcription only mode functional. Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(build): Build backends on a separate layer to speed up core only changes Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>	2025-05-25 22:25:05 +02:00
Ettore Di Giacinto	3b0cf52f6a	feat(llama.cpp): add reranking (#5396) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-05-22 21:49:30 +02:00
Ettore Di Giacinto	b2f9fc870b	chore(defaults): enlarge defaults, drop gpu layers which is infered (#5308) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-05-03 18:44:51 +02:00
Ettore Di Giacinto	2c9279a542	feat(video-gen): add endpoint for video generation (#5247) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-04-26 18:05:01 +02:00
Ettore Di Giacinto	61cc76c455	chore(autogptq): drop archived backend (#5214) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-04-19 15:52:29 +02:00
Gianluca Boiano	f67e5dec68	fix: bark-cpp: assign FLAG_TTS to bark-cpp backend (#5186) ... Signed-off-by: Gianluca Boiano <morf3089@gmail.com>	2025-04-16 08:21:30 +02:00
Ettore Di Giacinto	9c74d74f7b	feat(gguf): guess default context size from file (#5089) ... feat(gguf): guess default config file from files Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-03-29 14:42:14 +01:00
Ettore Di Giacinto	a7b4001b75	feat: allow to specify a reply prefix (#4931) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-03-02 16:07:32 +01:00
Ettore Di Giacinto	bbbb28e3ca	fix(models): unify usecases identifications (#4914) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-02-27 15:51:12 +01:00
Brandon Beiler	6a6e1a0ea9	feat(vllm): Additional vLLM config options (Disable logging, dtype, and Per-Prompt media limits) (#4855) ... * Adding the following vLLM config options: disable_log_status, dtype, limit_mm_per_prompt Signed-off-by: TheDropZone <brandonbeiler@gmail.com> * using " marks in the config.yaml file Signed-off-by: TheDropZone <brandonbeiler@gmail.com> * adding in missing colon Signed-off-by: TheDropZone <brandonbeiler@gmail.com> --------- Signed-off-by: TheDropZone <brandonbeiler@gmail.com>	2025-02-18 19:27:58 +01:00
Ettore Di Giacinto	5b19af99ff	feat(ui): detect model usage and display link (#4864) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-02-18 19:27:07 +01:00
Dave	3cddf24747	feat: Centralized Request Processing middleware (#3847) ... * squash past, centralize request middleware PR Signed-off-by: Dave Lee <dave@gray101.com> * migrate bruno request files to examples repo Signed-off-by: Dave Lee <dave@gray101.com> * fix Signed-off-by: Dave Lee <dave@gray101.com> * Update tests/e2e-aio/e2e_test.go Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> --------- Signed-off-by: Dave Lee <dave@gray101.com> Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2025-02-10 12:06:16 +01:00
Ettore Di Giacinto	cc1f6f913f	fix(llama.cpp): disable mirostat as default (#2911) ... Even if increasing the quality of the output, it has shown to have performance drawbacks to be so noticeable that the confuses users about speed of LocalAI ( see also https://github.com/mudler/LocalAI/issues/2780 ). This changeset disables Mirostat by default (which can be still enabled manually). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Dave <dave@gray101.com>	2025-02-06 19:39:59 +01:00
Ettore Di Giacinto	e15d29aba2	chore(stablediffusion-ncn): drop in favor of ggml implementation (#4652) ... * chore(stablediffusion-ncn): drop in favor of ggml implementation Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ci): drop stablediffusion build Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): add Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): try to fixup current tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Try to fix tests Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tests improvements Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): use quality to specify step Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(tests): switch to sd-1.5 also increase prep time for downloading models Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-22 19:34:16 +01:00
Gianluca Boiano	032a33de49	chore: remove deprecated tinydream backend (#4631) ... Signed-off-by: Gianluca Boiano <morf3089@gmail.com>	2025-01-18 18:35:30 +01:00
Ettore Di Giacinto	7d0ac1ea3f	chore(vall-e-x): Drop backend (#4619) ... There are many new architectures that are SOTA and replaces vall-e-x nowadays. Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2025-01-17 09:35:10 +01:00
Ettore Di Giacinto	cea5a0ea42	feat(template): read jinja templates from gguf files (#4332) ... * Read jinja templates as fallback Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move templating out of model loader Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Test TemplateMessages Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Set role and content from transformers Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Tests: be more flexible Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * More jinja Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small refactoring and adaptations Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-12-08 13:50:33 +01:00
Ettore Di Giacinto	d4c1746c7d	feat(llama.cpp): expose cache_type_k and cache_type_v for quant of kv cache (#4329) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-12-06 10:23:59 +01:00
Ettore Di Giacinto	44a5dac312	feat(backend): add stablediffusion-ggml (#4289) ... * feat(backend): add stablediffusion-ggml Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * chore(ci): track stablediffusion-ggml Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Use default scheduler and sampler if not specified Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Move cfg scale out of diffusers block Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Make it working Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: set free_params_immediately to false to call the model in sequence https://github.com/leejet/stable-diffusion.cpp/issues/366 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-12-03 22:41:22 +01:00
Ettore Di Giacinto	947224b952	feat(diffusers): allow multiple lora adapters (#4081) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-11-05 15:14:33 +01:00
Ettore Di Giacinto	ae1ec4e096	feat(vllm): expose 'load_format' (#3943) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-10-23 15:34:57 +02:00
Ettore Di Giacinto	ccc7cb0287	feat(templates): use a single template for multimodals messages (#3892) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-10-22 09:34:05 +02:00
Ettore Di Giacinto	648ffdf449	feat(multimodal): allow to template placeholders (#3728) ... feat(multimodal): allow to template image placeholders Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-10-04 18:32:29 +02:00
Dave	307a835199	groundwork: ListModels Filtering Upgrade (#2773) ... * seperate the filtering from the middleware changes --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-10-01 18:55:46 +00:00
Ettore Di Giacinto	cf747bcdec	feat: extract output with regexes from LLMs (#3491) ... * feat: extract output with regexes from LLMs This changset adds `extract_regex` to the LLM config. It is a list of regexes that can match output and will be used to re extract text from the LLM output. This is particularly useful for LLMs which outputs final results into tags. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Add tests, enhance output in case of configuration error Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-09-13 13:27:36 +02:00
Ettore Di Giacinto	a36b721ca6	fix: be consistent in downloading files, check for scanner errors (#3108) ... * fix(downloader): be consistent in downloading files This PR puts some order in the downloader such as functions are re-used across several places. This fixes an issue with having uri's inside the model YAML file, it would resolve to MD5 rather then using the filename Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(scanner): do raise error only if unsafeFiles are found Fixes: https://github.com/mudler/LocalAI/issues/3114 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-08-02 20:06:25 +02:00
Ettore Di Giacinto	35561edb6e	feat(llama.cpp): support embeddings endpoints (#2871) ... * feat(llama.cpp): add embeddings Also enable embeddings by default for llama.cpp models Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(Makefile): prepare llama.cpp sources only once Otherwise we keep cloning llama.cpp for each of the variants Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * do not set embeddings to false Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs: add embeddings to the YAML config reference Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-07-15 22:54:16 +02:00
Ettore Di Giacinto	a181dd0ebc	refactor: gallery inconsistencies (#2647) ... * refactor(gallery): move under core/ Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(unarchive): do not allow symlinks Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-06-24 17:32:12 +02:00
Sertaç Özercan	5866fc8ded	chore: fix go.mod module (#2635) ... Signed-off-by: Sertac Ozercan <sozercan@gmail.com>	2024-06-23 08:24:36 +00:00
Ettore Di Giacinto	aae7ad9d73	feat(llama.cpp): guess model defaults from file (#2522) ... * wip: guess informations from gguf file Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * update go mod Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Identify llama3 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Do not try to guess the name, as reading gguf files can be expensive Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Allow to disable guessing Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-06-08 22:13:02 +02:00
Chakib Benziane	b99182c8d4	TTS API improvements (#2308) ... * update doc on COQUI_LANGUAGE env variable Signed-off-by: blob42 <contact@blob42.xyz> * return errors from tts gRPC backend Signed-off-by: blob42 <contact@blob42.xyz> * handle speaker_id and language in coqui TTS backend Signed-off-by: blob42 <contact@blob42.xyz> * TTS endpoint: add optional language paramter Signed-off-by: blob42 <contact@blob42.xyz> * tts fix: empty language string breaks non-multilingual models Signed-off-by: blob42 <contact@blob42.xyz> * allow tts param definition in config file - consolidate TTS options under `tts` config entry Signed-off-by: blob42 <contact@blob42.xyz> * tts: update doc Signed-off-by: blob42 <contact@blob42.xyz> --------- Signed-off-by: blob42 <contact@blob42.xyz> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>	2024-06-01 18:26:27 +00:00
Prajwal S Nayak	4d98dd9ce7	feat(image): support response_type in the OpenAI API request (#2347) ... * Change response_format type to string to match OpenAI Spec Signed-off-by: prajwal <prajwalnayak7@gmail.com> * updated response_type type to interface Signed-off-by: prajwal <prajwalnayak7@gmail.com> * feat: correctly parse generic struct Signed-off-by: mudler <mudler@localai.io> * add tests Signed-off-by: mudler <mudler@localai.io> --------- Signed-off-by: prajwal <prajwalnayak7@gmail.com> Signed-off-by: mudler <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com> Co-authored-by: mudler <mudler@localai.io>	2024-05-29 14:40:54 +02:00
Dave	0b637465d9	refactor: Minor improvements to BackendConfigLoader (#2353) ... some minor renames and refactorings within BackendConfigLoader - make things more consistent, remove underused code, rename things for clarity Signed-off-by: Dave Lee <dave@gray101.com>	2024-05-23 22:48:12 +02:00
Ettore Di Giacinto	6cbe6a4f99	models(gallery): add phi-3-medium-4k-instruct (#2367) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-22 08:32:30 +02:00
Ettore Di Giacinto	1a3dedece0	dependencies(grpcio): bump to fix CI issues (#2362) ... feat(grpcio): bump to fix CI issues Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-21 14:33:47 +02:00
Ettore Di Giacinto	c89271b2e4	feat(llama.cpp): add distributed llama.cpp inferencing (#2324) ... * feat(llama.cpp): support distributed llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: let tweak how chat messages are merged together Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Makefile: register to ALL_GRPC_BACKENDS Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactoring, allow disable auto-detection of backends Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * minor fixups Signed-off-by: mudler <mudler@localai.io> * feat: add cmd to start rpc-server from llama.cpp Signed-off-by: mudler <mudler@localai.io> * ci: add ccache Signed-off-by: mudler <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: mudler <mudler@localai.io>	2024-05-15 01:17:02 +02:00
Ettore Di Giacinto	e49ea0123b	feat(llama.cpp): add flash_attention and no_kv_offloading (#2310) ... feat(llama.cpp): add flash_attn and no_kv_offload Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-05-13 19:07:51 +02:00
Dave	c4f958e11b	refactor(application): introduce application global state (#2072) ... * start breaking up the giant channel refactor now that it's better understood - easier to merge bites Signed-off-by: Dave Lee <dave@gray101.com> * add concurrency and base64 back in, along with new base64 tests. Signed-off-by: Dave Lee <dave@gray101.com> * Automatic rename of whisper.go's Result to TranscriptResult Signed-off-by: Dave Lee <dave@gray101.com> * remove pkg/concurrency - significant changes coming in split 2 Signed-off-by: Dave Lee <dave@gray101.com> * fix comments Signed-off-by: Dave Lee <dave@gray101.com> * add list_model service as another low-risk service to get it out of the way Signed-off-by: Dave Lee <dave@gray101.com> * split backend config loader into seperate file from the actual config struct. No changes yet, just reduce cognative load with smaller files of logical blocks Signed-off-by: Dave Lee <dave@gray101.com> * rename state.go ==> application.go Signed-off-by: Dave Lee <dave@gray101.com> * fix lost import? Signed-off-by: Dave Lee <dave@gray101.com> --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-04-29 17:42:37 +00:00
Ettore Di Giacinto	e8d44447ad	feat(gallery): support model deletion (#2173) ... * feat(gallery): op now supports deletion of models Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Wire things with WebUI(WIP) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * minor improvements Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-28 23:42:46 +02:00
Ettore Di Giacinto	fb2a05ff43	feat(gallery): display job status also during navigation (#2151) ... * feat(gallery): keep showing progress also when refreshing Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(intel-gpu): better defaults Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat: make it thread-safe Signed-off-by: mudler <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Signed-off-by: mudler <mudler@localai.io>	2024-04-27 09:08:33 +02:00
Ettore Di Giacinto	0d8bf91699	feat: Galleries UI (#2104) ... * WIP: add models to webui Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * Register routes Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: don't cache models Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * small fixups Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix: fixup multiple installs (strings.Clone) Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-23 09:22:58 +02:00
Ettore Di Giacinto	180cd4ccda	fix(llama.cpp-ggml): fixup max_tokens for old backend (#2094) ... fix(llama.cpp-ggml): set 0 as default for `max_tokens` Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-21 16:34:00 +02:00
Ettore Di Giacinto	afa1bca1e3	fix(llama.cpp): set -1 as default for max tokens (#2087) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-20 20:20:10 +02:00
Taikono-Himazin	03adc1f60d	Add tensor_parallel_size setting to vllm setting items (#2085) ... Signed-off-by: Taikono-Himazin <kazu@po.harenet.ne.jp>	2024-04-20 14:37:02 +00:00
Ettore Di Giacinto	bbea62b907	feat(functions): support models with no grammar, add tests (#2068) ... Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-18 22:43:12 +02:00
Ettore Di Giacinto	af9e5a2d05	Revert #1963 (#2056) ... * Revert "fix(fncall): fix regression introduced in #1963 (#2048)" This reverts commit 6b06d4e0af. * Revert "fix: action-tmate back to upstream, dead code removal (#2038)" This reverts commit fdec8a9d00. * Revert "feat(grpc): return consumed token count and update response accordingly (#2035)" This reverts commit e843d7df0e. * Revert "refactor: backend/service split, channel-based llm flow (#1963)" This reverts commit eed5706994. * feat(grpc): return consumed token count and update response accordingly Fixes: #1920 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-17 23:33:49 +02:00
Dave	eed5706994	refactor: backend/service split, channel-based llm flow (#1963) ... Refactor: channel based llm flow and services split --------- Signed-off-by: Dave Lee <dave@gray101.com>	2024-04-13 09:45:34 +02:00
Ludovic Leroux	12c0d9443e	feat: use tokenizer.apply_chat_template() in vLLM (#1990) ... Use tokenizer.apply_chat_template() in vLLM Signed-off-by: Ludovic LEROUX <ludovic@inpher.io>	2024-04-11 19:20:22 +02:00
Ettore Di Giacinto	8342553214	fix(llama.cpp): set better defaults for llama.cpp (#1961) ... fix(defaults): set better defaults for llama.cpp Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-06 22:56:45 +02:00
Ettore Di Giacinto	ff77d3bc22	fix(seed): generate random seed per-request if -1 is set (#1952) ... * fix(seed): generate random seed per-request if -1 is set Also update ci with new workflows and allow the aio tests to run with an api key Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(openvino): Add OpenVINO example Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>	2024-04-03 22:25:47 +02:00