Commit Graph

440 Commits

Author SHA1 Message Date
Ettore Di Giacinto
1c4fbaae20
Add support for cerebras (#45)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-20 19:33:36 +02:00
Ettore Di Giacinto
d517a54e28
Major API enhancements (#44) 2023-04-20 18:33:02 +02:00
Tyler Gillson
c905512bb0
Update example K8s manifests (#40) 2023-04-20 18:31:11 +02:00
Ettore Di Giacinto
1254951fab
Add logo (#37)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-19 19:03:12 +02:00
Ettore Di Giacinto
80f50e6ccd
Rename project to LocalAI (#35)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-19 18:43:10 +02:00
Ettore Di Giacinto
7fec26f5d3
Enhancements (#34)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-19 17:10:29 +02:00
Ettore Di Giacinto
a9a875ee2b
⬆️ Bump llama.cpp (#33)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-17 21:34:02 +02:00
Ettore Di Giacinto
db5ac715f3
Use a reasonable default context size (#31) 2023-04-17 18:45:42 +02:00
Ettore Di Giacinto
0b330d90ad
feat: drop embedded webui (#27)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-16 10:46:20 +02:00
Ettore Di Giacinto
63601fabd1
feat: drop default model and llama-specific API (#26)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-16 10:40:50 +02:00
Ettore Di Giacinto
1370b4482f
📖 Add prompt-templates examples (#25)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-16 10:24:15 +02:00
Ettore Di Giacinto
b062f3142b
feat: enhance API, expose more parameters (#24)
Signed-off-by: mudler <mudler@c3os.io>
2023-04-16 10:16:48 +02:00
Marc R Kellerman
c37175271f
feature: makefile & updates (#23)
Co-authored-by: mudler <mudler@c3os.io>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2023-04-15 16:39:07 -07:00
Ettore Di Giacinto
e8eab66c30
Merge pull request #22 from go-skynet/update-llama.cpp
⬆️ Update go-llama.cpp to `llama.cpp-2f7c8e0`
2023-04-16 00:06:52 +02:00
mudler
a73a497143 Update llama.cpp 2023-04-15 23:57:00 +02:00
Ettore Di Giacinto
6aea515e1d
Merge pull request #20 from go-skynet/mudler-patch-1
📖 Update README.md
2023-04-15 00:38:30 +02:00
Ettore Di Giacinto
dfc2b7e02a
📖 Update README.md 2023-04-15 00:38:18 +02:00
Ettore Di Giacinto
040290971c
Merge pull request #19 from go-skynet/tags
Use tags for go-llama.cpp
2023-04-15 00:14:47 +02:00
mudler
553bad585e Use tags for go-llama.cpp 2023-04-15 00:07:39 +02:00
Ettore Di Giacinto
f76b612506
Merge pull request #17 from go-skynet/mudler-patch-1
Fix comment typo
2023-04-13 15:21:13 +02:00
Ettore Di Giacinto
c4e94c88d7
Fix comment typo
Thanks to @deadprogram for noticing it!
2023-04-13 15:20:51 +02:00
mudler
a9cd6b3ca3 ci: Fix tag detection for 'latest' 2023-04-13 01:37:09 +02:00
mudler
e786576b95 Update README 2023-04-13 01:28:15 +02:00
Ettore Di Giacinto
d426571789
Merge pull request #16 from go-skynet/fix_arm
Drop armv7 builds
2023-04-13 01:21:58 +02:00
mudler
a896a2b5ad Drop armv7 builds 2023-04-13 01:21:40 +02:00
Ettore Di Giacinto
8273cd5c04
Merge pull request #15 from go-skynet/docker-compose
Add docker-compose file
2023-04-13 01:17:44 +02:00
mudler
16f1281d38 Minor workflow fixes 2023-04-13 01:16:13 +02:00
mudler
8042e9a2d6 Add docker-compose
Fixes #14

Signed-off-by: mudler <mudler@c3os.io>
2023-04-13 01:13:14 +02:00
mudler
624092cb99 Update README 2023-04-12 00:07:30 +02:00
mudler
a422a883ac Minor rephrasing 2023-04-12 00:04:15 +02:00
mudler
7858a97254 Update README 2023-04-12 00:02:47 +02:00
mudler
5556aa46dd Small refinements and refactors 2023-04-12 00:02:39 +02:00
mudler
eb4257f946 Add .gitignore 2023-04-11 23:44:00 +02:00
mudler
ae30bd346d Reorganize repository layout 2023-04-11 23:43:43 +02:00
mudler
93d8977ba2 Return model list 2023-04-10 12:02:40 +02:00
mudler
f43aeeb4a1 Add both API endpoints (completion, chat) 2023-04-09 12:30:55 +02:00
mudler
c17dcc5e9d Allow to inject prompt as part of the call 2023-04-09 09:36:19 +02:00
mudler
4a932483e1 Small fixup to template loading 2023-04-08 11:59:40 +02:00
mudler
b710147b95 Add mutex on same models (parallel isn't supported yet) 2023-04-08 11:45:36 +02:00
mudler
ba70363330 Use template input 2023-04-08 11:24:25 +02:00
mudler
9fb581739b Allow to template model prompts inputs 2023-04-08 10:46:51 +02:00
mudler
48aca246e3 Drop unused interactive mode 2023-04-07 11:31:14 +02:00
mudler
12eee097b7 Make it compatible with openAI api, support multiple models
Signed-off-by: mudler <mudler@c3os.io>
2023-04-07 11:30:59 +02:00
mudler
b33d015b8c Use go-llama.cpp 2023-04-07 10:08:15 +02:00
Ettore Di Giacinto
b7c0a108f5
Update README.md 2023-04-05 22:28:03 +02:00
Ettore Di Giacinto
f694a89c28
Update README.md 2023-04-05 22:14:00 +02:00
Ettore Di Giacinto
be682e6c2f
Update README.md
Add short-term roadmap and mention webui
2023-04-05 22:04:35 +02:00
mudler
bf85a31f9e Don't set a default model path 2023-04-05 22:00:15 +02:00
Ettore Di Giacinto
d69048e0b0
Update README.md 2023-04-05 00:41:02 +02:00
mudler
827f189163 Update README 2023-03-30 18:46:11 +02:00