Commit Graph

2500 Commits

Author SHA1 Message Date
Ettore Di Giacinto
b38fd8780b
models(gallery): add magnum-v3-34b (#3384)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-26 17:53:47 +02:00
Ettore Di Giacinto
11eaf9c0a7
models(gallery): add calme-2.1-phi3.5-4b-i1 (#3383)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-26 17:39:54 +02:00
Ettore Di Giacinto
5d892f86ea
chore(cuda): reduce binary size (#3379)
fix(cuda): reduce binary size

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-26 14:47:36 +02:00
Ettore Di Giacinto
7f06954425
fix(model-loading): keep track of open GRPC Clients (#3377)
Due to a previous refactor we moved the client constructor tight to the
model address, however that was just a string which we would use to
build the client each time.

With this change we make the loader to return a *Model which carries a
constructor for the client and stores the client on the first
connection.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-25 14:36:09 +02:00
Ettore Di Giacinto
771a052480
models(gallery): add phi-3.5 (#3376)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-25 09:02:54 +02:00
Dave
99b57b321b
fix: devcontainer utils.sh ssh copy improvements (#3372)
fix utils.sh - use HOME variable, permissions and logging

Signed-off-by: Dave Lee <dave@gray101.com>
2024-08-24 22:42:05 +00:00
LocalAI [bot]
75ef6ccf1e
feat(swagger): update swagger (#3370)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-24 21:53:18 +00:00
grant-wilson
de1fbdca71
Update quickstart.md (#3373)
fix typo.

Signed-off-by: grant-wilson <grantm.wilsonii@gmail.com>
2024-08-24 23:01:34 +02:00
Ettore Di Giacinto
ce827139bb
fix(p2p): correctly allow to pass extra args to llama.cpp (#3368)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-24 10:30:24 +02:00
Ettore Di Giacinto
0762aa5327
Update GPU-acceleration.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-24 09:58:49 +02:00
Dave
81ae92f017
feat: elevenlabs sound-generation api (#3355)
* initial version of elevenlabs compatible soundgeneration api and cli command

Signed-off-by: Dave Lee <dave@gray101.com>

* minor cleanup

Signed-off-by: Dave Lee <dave@gray101.com>

* restore TTS, add test

Signed-off-by: Dave Lee <dave@gray101.com>

* remove stray s

Signed-off-by: Dave Lee <dave@gray101.com>

* fix

Signed-off-by: Dave Lee <dave@gray101.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>
2024-08-24 00:20:28 +00:00
Ettore Di Giacinto
84d6e5a987
chore(model-gallery): add more quants for popular models (#3365)
* models(gallery): add higher quants for some llama and hermes

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

* models(gallery): vllm: specify a reasonable max_tokens

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-24 00:29:24 +02:00
Dave
ac5f6f210b
feat: external backend launching log improvements and relative path support (#3348)
* specify workdir when launching external backend for safety / relative paths, bump version, logs

Signed-off-by: Dave Lee <dave@gray101.com>

* sneak in a devcontainer fix

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-08-24 00:27:14 +02:00
LocalAI [bot]
61fe2404a0
chore: ⬆️ Update ggerganov/llama.cpp to 3ba780e2a8f0ffe13f571b27f0bbf2ca5a199efc (#3361)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-23 21:49:18 +00:00
LocalAI [bot]
db2d8f4d04
docs: ⬆️ update docs version mudler/LocalAI (#3366)
⬆️ Update docs version mudler/LocalAI

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-23 21:44:06 +00:00
Ettore Di Giacinto
a9c521eb41
fix(deps): bump grpcio (#3362)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-23 10:29:04 +02:00
Ettore Di Giacinto
a913fd310d
models(gallery): add hermes-3-llama-3.1(8B,70B,405B) with vLLM (#3360)
models(gallery): add hermes-3-llama-3.1 with vLLM

it adds 8b, 70b and 405b to the gallery

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-23 09:24:34 +02:00
Ettore Di Giacinto
fbaae8528d
fix(chat): re-generated uuid, created, and text on each request (#3359)
This was noticed by models returning content besides function calls.
Sadly we can't test that easily in the CI so it got unnoticed.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-22 10:56:05 +02:00
LocalAI [bot]
7d030b56b2
chore: ⬆️ Update ggerganov/whisper.cpp to 9e3c5345cd46ea718209db53464e426c3fe7a25e (#3357)
⬆️ Update ggerganov/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-22 08:49:33 +00:00
LocalAI [bot]
0add16049e
chore: ⬆️ Update ggerganov/llama.cpp to fc54ef0d1c138133a01933296d50a36a1ab64735 (#3356)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-21 22:14:02 +00:00
Ettore Di Giacinto
2bb48b0816
fix(parler-tts): pin torchaudio and torch for hipblas
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-21 18:27:20 +02:00
Ettore Di Giacinto
023ce59d44
feat(p2p): allow to set intervals (#3353)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-21 18:23:51 +02:00
Ettore Di Giacinto
7822d944b5
chore(p2p): single-node when sharing federated instance (#3354)
* chore(p2p): single-node when sharing federated instance

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

* chore: refactor out and extract into functions

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-21 18:23:42 +02:00
Ettore Di Giacinto
b510352393
chore(anime.js): drop unused (#3351)
* fix(anime.js): correctly set the static path

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

* Drop anime.js (unused)

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-21 13:10:09 +02:00
Ettore Di Giacinto
d3a217c254
chore(docs): update p2p env var documentation (#3350)
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-21 13:09:57 +02:00
四少爷
2a3427e533
fix(docs): Refer to the OpenAI documentation to update the openai-functions docu… (#3317)
* Refer to the OpenAI documentation to update the openai-functions documentation

I saw the openai official website, apIn the description: The parameters `function_call` and `functions` have been replaced by `tool_choice` and `tools`.So I submitted this update;But I haven't read the code of localai, so I'm not sure if it also applies to localai.

Signed-off-by: 四少爷 <sex@jermey.cn>

* Update Usage Example

The original usage example was too outdated, and calling with the new version of the openai python package would result in errors. Therefore, the curl example was rewritten (as curl examples are also used elsewhere).

Signed-off-by: 四少爷 <sex@jermey.cn>

* add python example

Signed-off-by: 四少爷 <sex@jermey.cn>

---------

Signed-off-by: 四少爷 <sex@jermey.cn>
2024-08-21 13:09:26 +02:00
Ettore Di Giacinto
7ec02babd5
fix(parler-tts): pin numba
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-21 13:09:12 +02:00
Ettore Di Giacinto
5a4c4f4ab2
fix(parler-tts): pin llvmlite
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-21 10:46:31 +02:00
Ettore Di Giacinto
af095204fa
fix(p2p): avoid starting the node twice (#3349)
* fix(p2p): avoid starting the node twice

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

* fix(p2p): keep exposing service if we don't start the llama.cpp runner

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-21 10:30:56 +02:00
Ettore Di Giacinto
70e53bc191 chore(deps): update edgevpn
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-21 10:18:43 +02:00
LocalAI [bot]
7cf59d9f98
chore: ⬆️ Update ggerganov/llama.cpp to 2f3c1466ff46a2413b0e363a5005c46538186ee6 (#3345)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-21 00:37:13 +02:00
LocalAI [bot]
7147f1990f
chore: ⬆️ Update ggerganov/whisper.cpp to d65786ea540a5aef21f67cacfa6f134097727780 (#3344)
⬆️ Update ggerganov/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-20 22:20:34 +00:00
Ettore Di Giacinto
16f7140461
chore(deps): update edgevpn (#3346)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 22:54:16 +02:00
LocalAI [bot]
6f1b4f29a8
feat(swagger): update swagger (#3343)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-20 22:54:04 +02:00
dependabot[bot]
93658fc5fd
chore(deps): Bump langchain from 0.2.12 to 0.2.14 in /examples/langchain/langchainpy-localai-example (#3307)
chore(deps): Bump langchain

Bumps [langchain](https://github.com/langchain-ai/langchain) from 0.2.12 to 0.2.14.
- [Release notes](https://github.com/langchain-ai/langchain/releases)
- [Commits](https://github.com/langchain-ai/langchain/compare/langchain==0.2.12...langchain==0.2.14)

---
updated-dependencies:
- dependency-name: langchain
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-20 19:28:48 +00:00
Ettore Di Giacinto
736df11454
fix(ci): pin to llvmlite 0.43 (#3342)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 20:14:35 +02:00
Ettore Di Giacinto
2669f4738a
fix(p2p): re-use p2p host when running federated mode (#3341)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 20:14:17 +02:00
Ettore Di Giacinto
aca2c4196a
ci(Dockerfile): try to install lvm-10 from Ubuntu repositories
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-20 19:36:11 +02:00
Dave
9cfd89087b
feat: devcontainer part 4 (#3339)
add utils.sh, prelim docs

Signed-off-by: Dave Lee <dave@gray101.com>
2024-08-20 19:25:22 +02:00
Ettore Di Giacinto
6aba6223c7
ci(Dockerfile): adjust deps from typos
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-20 19:21:47 +02:00
Ettore Di Giacinto
a28b3771a7
chore(deps): update edgevpn (#3340)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 19:17:35 +02:00
Ettore Di Giacinto
d02a0f6f01
ci: add llvm dependencies
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-20 18:27:10 +02:00
dependabot[bot]
c12d121783
chore(deps): Bump llama-index from 0.10.65 to 0.10.67.post1 in /examples/langchain-chroma (#3335)
chore(deps): Bump llama-index in /examples/langchain-chroma

Bumps [llama-index](https://github.com/run-llama/llama_index) from 0.10.65 to 0.10.67.post1.
- [Release notes](https://github.com/run-llama/llama_index/releases)
- [Changelog](https://github.com/run-llama/llama_index/blob/main/CHANGELOG.md)
- [Commits](https://github.com/run-llama/llama_index/compare/v0.10.65...v0.10.67.post1)

---
updated-dependencies:
- dependency-name: llama-index
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-20 16:12:02 +00:00
Ettore Di Giacinto
b06046fe4c
chore: install llvm 10
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-08-20 18:06:55 +02:00
Ettore Di Giacinto
6d350ccce0
feat(federation): do not allocate local services for load balancing (#3337)
* refactor: extract proxy into functions

* feat(federation): do not allocate services, directly connect with libp2p

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 14:45:36 +02:00
dependabot[bot]
bcd3c1deb2
chore(deps): Bump openai from 1.40.6 to 1.41.1 in /examples/langchain/langchainpy-localai-example (#3320)
chore(deps): Bump openai

Bumps [openai](https://github.com/openai/openai-python) from 1.40.6 to 1.41.1.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Changelog](https://github.com/openai/openai-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/openai/openai-python/compare/v1.40.6...v1.41.1)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-20 12:32:36 +00:00
dependabot[bot]
5afea9babf
chore(deps): Bump openai from 1.40.4 to 1.41.1 in /examples/functions (#3319)
Bumps [openai](https://github.com/openai/openai-python) from 1.40.4 to 1.41.1.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Changelog](https://github.com/openai/openai-python/blob/main/CHANGELOG.md)
- [Commits](https://github.com/openai/openai-python/compare/v1.40.4...v1.41.1)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-08-20 11:49:54 +00:00
LocalAI [bot]
a495515e10
chore: ⬆️ Update ggerganov/llama.cpp to cfac111e2b3953cdb6b0126e67a2487687646971 (#3315)
⬆️ Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-08-20 12:16:39 +02:00
Dave
9a8a249932
feat: devcontainer part 3 (#3318)
* stash initial fixes, attempt to open branch inside container

Signed-off-by: Dave Lee <dave@gray101.com>

* add yq, from inside DC

Signed-off-by: Dave Lee <dave@gray101.com>

* stash progress, rebuild container

Signed-off-by: Dave Lee <dave@gray101.com>

* snap

Signed-off-by: Dave Lee <dave@gray101.com>

* split builder into builder-sd, will speed up devcontainer build times and potentially help caching in other situations.

Signed-off-by: Dave Lee <dave@gray101.com>

* fix yq

Signed-off-by: Dave Lee <dave@gray101.com>

* fix paths

Signed-off-by: Dave Lee <dave@gray101.com>

* fix paths - new folder to bypass the .dockerignore which _should_ exclude the other files

Signed-off-by: Dave Lee <dave@gray101.com>

* fix

Signed-off-by: Dave Lee <dave@gray101.com>

* fix ]

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
2024-08-20 12:16:21 +02:00
Ettore Di Giacinto
dfa183551e
fix: add llvm to extra images (#3321)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-08-20 12:14:47 +02:00