Commit Graph

1957 Commits

Author SHA1 Message Date
Ettore Di Giacinto
beb598e4f9
feat(functions): mixed JSON BNF grammars (#2328)
feat(functions): support mixed JSON BNF grammar

This PR provides new options to control how functions are extracted from
the LLM, and also provides more control on how JSON grammars can be used
(also in conjunction).

New YAML settings introduced:

- `grammar_message`: when enabled, the generated grammar can also decide
  to push strings and not only JSON objects. This allows the LLM to pick
to either respond freely or using JSON.
- `grammar_prefix`: Allows to prefix a string to the JSON grammar
  definition.
- `replace_results`: Is a map that allows to replace strings in the LLM
  result.

As an example, consider the following settings for Hermes-2-Pro-Mistral,
which allow extracting both JSON results coming from the model, and the
ones coming from the grammar:

```yaml
function:
  # disable injecting the "answer" tool
  disable_no_action: true
  # This allows the grammar to also return messages
  grammar_message: true
  # Suffix to add to the grammar
  grammar_prefix: '<tool_call>\n'
  return_name_in_function_response: true
  # Without grammar uncomment the lines below
  # Warning: this is relying only on the capability of the
  # LLM model to generate the correct function call.
  # no_grammar: true
  # json_regex_match: "(?s)<tool_call>(.*?)</tool_call>"
  replace_results:
    "<tool_call>": ""
    "\'": "\""
```

Note: To disable entirely grammars usage in the example above, uncomment the
`no_grammar` and `json_regex_match`.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-15 20:03:18 +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
29909666c3
Update README.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-15 00:33:16 +02:00
LocalAI [bot]
566b5cf2ee
⬆️ Update ggerganov/whisper.cpp (#2326)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-14 21:17:46 +00:00
Sertaç Özercan
a670318a9f
feat: auto select llama-cpp cuda runtime (#2306)
* auto select cpu variant

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* remove cuda target for now

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* fix metal

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* fix path

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* cuda

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* auto select cuda

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* update test

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* select CUDA backend only if present

Signed-off-by: mudler <mudler@localai.io>

* ci: keep cuda bin in path

Signed-off-by: mudler <mudler@localai.io>

* Makefile: make dist now builds also cuda

Signed-off-by: mudler <mudler@localai.io>

* Keep pushing fallback in case auto-flagset/nvidia fails

There could be other reasons for which the default binary may fail. For example we might have detected an Nvidia GPU,
however the user might not have the drivers/cuda libraries installed in the system, and so it would fail to start.

We keep the fallback of llama.cpp at the end of the llama.cpp backends to try to fallback loading in case things go wrong

Signed-off-by: mudler <mudler@localai.io>

* Do not build cuda on MacOS

Signed-off-by: mudler <mudler@localai.io>

* cleanup

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* Apply suggestions from code review

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

---------

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.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>
2024-05-14 19:40:18 +02:00
Ettore Di Giacinto
84e2407afa
feat(functions): allow to set JSON matcher (#2319)
Signed-off-by: mudler <mudler@localai.io>
2024-05-14 09:39:20 +02:00
Ettore Di Giacinto
c4186f13c3
feat(functions): support models with no grammar and no regex (#2315)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-14 00:32:32 +02:00
LocalAI [bot]
4ac7956f68
⬆️ Update ggerganov/whisper.cpp (#2317)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-13 22:25:14 +00:00
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
Ettore Di Giacinto
7123d07456
models(gallery): add orthocopter (#2313)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-13 18:45:58 +02:00
Ettore Di Giacinto
2db22087ae
models(gallery): add lumimaidv2 (#2312)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-13 18:44:44 +02:00
Ettore Di Giacinto
fa7b2aee9c
models(gallery): add Bunny-llama (#2311)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-13 18:44:25 +02:00
Ettore Di Giacinto
4d70b6fb2d
models(gallery): add aura-llama-Abliterated (#2309)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-13 18:44:10 +02:00
Sertaç Özercan
e2c3ffb09b
feat: auto select llama-cpp cpu variant (#2305)
* auto select cpu variant

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* remove cuda target for now

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* fix metal

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

* fix path

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>

---------

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
2024-05-13 11:37:52 +02:00
LocalAI [bot]
b4cb22f444
⬆️ Update ggerganov/llama.cpp (#2303)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-12 21:18:59 +00:00
LocalAI [bot]
5534b13903
feat(swagger): update swagger (#2302)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-12 21:00:18 +00:00
fakezeta
5b79bd04a7
add setuptools for openvino (#2301) 2024-05-12 19:31:43 +00:00
Ettore Di Giacinto
9d8c705fd9
feat(ui): display number of available models for installation (#2298)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-12 14:24:36 +02:00
Ettore Di Giacinto
310b2171be
models(gallery): add llama-3-refueled (#2297)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-12 09:39:58 +02:00
Ettore Di Giacinto
98af0b5d85
models(gallery): add jsl-medllama-3-8b-v2.0 (#2296)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-12 09:38:05 +02:00
Ettore Di Giacinto
ca14f95d2c
models(gallery): add l3-chaoticsoliloquy-v1.5-4x8b (#2295)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-12 09:37:55 +02:00
Ikko Eltociear Ashimine
1b69b338c0
docs: Update semantic-todo/README.md (#2294)
seperate -> separate

Signed-off-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
2024-05-12 09:02:11 +02:00
cryptk
88942e4761
fix: add missing openvino/optimum/etc libraries for Intel, fixes #2289 (#2292)
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-05-12 09:01:45 +02:00
Ettore Di Giacinto
efa32a2677
feat(grammar): support models with specific construct (#2291)
When enabling grammar with functions, it might be useful to
allow more flexibility to support models that are fine-tuned against returning
function calls of the form of { "name": "function_name", "arguments" {...} }
rather then { "function": "function_name", "arguments": {..} }.

This might call out to a more generic approach later on, but for the moment being we can easily support both
as we have just to specific different types.

If needed we can expand on this later on

Signed-off-by: mudler <mudler@localai.io>
2024-05-12 01:13:22 +02:00
LocalAI [bot]
dfc420706c
⬆️ Update ggerganov/llama.cpp (#2290)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-11 21:16:34 +00:00
cryptk
e2de8a88f7
feat: create bash library to handle install/run/test of python backends (#2286)
* feat: create bash library to handle install/run/test of python backends

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* chore: minor cleanup

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: remove incorrect LIMIT_TARGETS from parler-tts

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: update runUnitests to handle running tests from a custom test file

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* chore: document runUnittests

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

---------

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-05-11 18:32:46 +02:00
Ettore Di Giacinto
7f4febd6c2
models(gallery): add Llama-3-8B-Instruct-abliterated (#2288)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-11 10:10:57 +02:00
LocalAI [bot]
93e581dfd0
⬆️ Update ggerganov/llama.cpp (#2285)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-10 21:09:22 +00:00
Ettore Di Giacinto
cf513efa78
Update openai-functions.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-10 17:09:51 +02:00
Ettore Di Giacinto
9e8b34427a
Update openai-functions.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-10 17:05:16 +02:00
Ettore Di Giacinto
88d0aa1e40
docs: update function docs
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-10 17:03:56 +02:00
Ettore Di Giacinto
9b09eb005f
build: do not specify a BUILD_ID by default (#2284)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-10 16:01:55 +02:00
Ettore Di Giacinto
4db41b71f3
models(gallery): add aloe (#2283)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-05-10 16:01:47 +02:00
cryptk
28a421cb1d
feat: migrate python backends from conda to uv (#2215)
* feat: migrate diffusers backend from conda to uv

  - replace conda with UV for diffusers install (prototype for all
    extras backends)
  - add ability to build docker with one/some/all extras backends
    instead of all or nothing

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate autogtpq bark coqui from conda to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: convert exllama over to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate exllama2 to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate mamba to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate parler to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate petals to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: fix tests

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate rerankers to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate sentencetransformers to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: install uv for tests-linux

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: make sure file exists before installing on intel images

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate transformers backend to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate transformers-musicgen to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate vall-e-x to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: migrate vllm to uv

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: add uv install to the rest of test-extra.yml

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: adjust file perms on all install/run/test scripts

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: add missing acclerate dependencies

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: add some more missing dependencies to python backends

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: parler tests venv py dir fix

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: correct filename for transformers-musicgen tests

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: adjust the pwd for valle tests

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: cleanup and optimization work for uv migration

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: add setuptools to requirements-install for mamba

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: more size optimization work

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* feat: make installs and tests more consistent, cleanup some deps

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: cleanup

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: mamba backend is cublas only

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

* fix: uncomment lines in makefile

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>

---------

Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-05-10 15:08:08 +02:00
LocalAI [bot]
e6768097f4
⬆️ Update docs version mudler/LocalAI (#2280)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-10 09:10:00 +02:00
LocalAI [bot]
18a04246fa
⬆️ Update ggerganov/llama.cpp (#2281)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-09 22:18:49 +00:00
LocalAI [bot]
f69de3be0d
models(gallery): ⬆️ update checksum (#2278)
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-09 12:21:24 +00:00
Ettore Di Giacinto
650ae620c5
ci: get latest git version
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 11:33:16 +02:00
Ettore Di Giacinto
6a209cbef6
ci: get file name correctly in checksum_checker.sh
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 10:57:23 +02:00
Ettore Di Giacinto
9786bb826d
ci: try to fix checksum_checker.sh
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 09:34:07 +02:00
Ettore Di Giacinto
9b4c6f348a
Update checksum_checker.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:57:22 +02:00
Ettore Di Giacinto
cb6ddb21ec
Update checksum_checker.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:55:48 +02:00
Ettore Di Giacinto
0baacca605
Update checksum_checker.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:54:35 +02:00
Ettore Di Giacinto
222d714ec7
Update checksum_checker.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:51:57 +02:00
Ettore Di Giacinto
fd2d89d37b
Update checksum_checker.sh
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:43:16 +02:00
Ettore Di Giacinto
6440b608dc
Update checksum_checker.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:42:48 +02:00
Ettore Di Giacinto
1937118eab
Update checksum_checker.yaml
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-09 00:34:56 +02:00
Ettore Di Giacinto
bc272d1e4b
ci: add checksum checker pipeline (#2274)
Signed-off-by: mudler <mudler@localai.io>
2024-05-09 00:31:27 +02:00
LocalAI [bot]
d651f390cd
⬆️ Update ggerganov/whisper.cpp (#2273)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-05-08 22:11:10 +00:00
Ettore Di Giacinto
ea777f8716
models(gallery): update SHA for einstein
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-05-08 23:40:58 +02:00