Commit Graph

3184 Commits

Author SHA1 Message Date
Ettore Di Giacinto
85f0f8227d
refactor: drop code dups (#234) 2023-05-11 16:34:16 +02:00
Ettore Di Giacinto
59e3c02002
make use of new bindings for gpt4all (#232) 2023-05-11 14:31:19 +02:00
Matthew Campbell
032dee256f
Keep whisper models in memory (#233) 2023-05-11 14:05:07 +02:00
Matthew Campbell
6b5e2b2bf5
Upload transcription API wasn't reading the data from the post (#229) 2023-05-11 10:43:05 +02:00
renovate[bot]
6fc303de87
fix(deps): update github.com/go-skynet/go-llama.cpp digest to 70593fc (#221)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-11 10:34:34 +02:00
renovate[bot]
6ad6e4873d
fix(deps): update github.com/ggerganov/whisper.cpp/bindings/go digest to 1d17cd5 (#216)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-11 01:14:34 +02:00
ci-robbot [bot]
d6d7391da8
⬆️ Update donomii/go-rwkv.cpp (#225)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-11 01:13:28 +02:00
Ettore Di Giacinto
11675932ac
feat: add dolly/redpajama/bloomz models support (#214) 2023-05-11 01:12:58 +02:00
Ettore Di Giacinto
f02202e1e1
update README 2023-05-10 15:51:16 +02:00
Ettore Di Giacinto
f8ee20991c
feat: add bert.cpp embeddings (#222) 2023-05-10 15:20:21 +02:00
Cedrik Boudreau
e6db14e2f1
Added spark in projects (#215) 2023-05-10 14:05:44 +02:00
Dave
d00886abea
Tiny .gitignore suggestion (#213) 2023-05-09 20:03:29 +02:00
renovate[bot]
4873d2bfa1
fix(deps): update github.com/go-skynet/go-llama.cpp digest to f4d26f4 (#212)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-09 12:17:15 +02:00
Ettore Di Giacinto
9f426578cf
feat: add transcript endpoint (#211) 2023-05-09 11:43:50 +02:00
ci-robbot [bot]
9d01b695a8
⬆️ Update go-skynet/go-llama.cpp (#209)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-08 22:37:16 +02:00
Ettore Di Giacinto
93829ab228
docs: update news 2023-05-08 22:34:12 +02:00
renovate[bot]
dd234f86d5
fix(deps): update github.com/go-skynet/go-llama.cpp digest to c03e8ad (#208)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-08 20:30:52 +02:00
mudler
3daff6f1aa doc: update README with embeddings docs 2023-05-08 20:02:59 +02:00
Ettore Di Giacinto
89dfa0f5fc
feat: add experimental support for embeddings as arrays (#207) 2023-05-08 19:31:18 +02:00
renovate[bot]
bc03c492a0
fix(deps): update module github.com/gofiber/fiber/v2 to v2.45.0 (#206)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-07 17:46:31 +02:00
Fabian Hachenberg
f50a4c1454
Added runpod.io template for LocalAI to examples (#203) 2023-05-07 10:58:15 +02:00
mudler
d13d4d95ce examples: fix default parameter 2023-05-07 10:13:57 +02:00
renovate[bot]
428790ec06
fix(deps): update github.com/go-skynet/go-llama.cpp digest to cf9b522 (#202)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-07 09:14:00 +02:00
mudler
4f551ce414 examples: add update index example, update README 2023-05-07 09:05:24 +02:00
mudler
6ed7b10273 examples: add langchain agent example 2023-05-07 08:14:01 +02:00
mudler
02979566ee examples: better defaults 2023-05-07 00:58:30 +02:00
ci-robbot [bot]
cbdcc839f3
⬆️ Update go-skynet/go-llama.cpp (#201)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-06 22:49:44 +02:00
mudler
e1c8f087f4 Update README 2023-05-06 19:18:03 +02:00
mudler
3a90ea44a5 Update readme and examples 2023-05-06 19:15:22 +02:00
renovate[bot]
e55492475d
fix(deps): update github.com/go-skynet/go-llama.cpp digest to 691d479 (#189)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-05-06 00:42:31 +02:00
Dave
07ec2e441d
mini fix - OpenAI documentation url (#200) 2023-05-06 00:42:08 +02:00
ci-robbot [bot]
38d7e0b43c
⬆️ Update go-skynet/go-llama.cpp (#198)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-06 00:21:48 +02:00
Dave
3411bfd00d
Langchain Example Updates (#199) 2023-05-06 00:21:06 +02:00
Ettore Di Giacinto
7e5fe35ae4
Mixed enhancements (#196) 2023-05-06 00:00:58 +02:00
mudler
8c8cf38d4d tests: use 1 core 2023-05-05 23:29:34 +02:00
mudler
75b25297fd tests: run with ginkgo 2023-05-05 22:51:30 +02:00
mudler
009ee47fe2 Don't allow 0 as thread count 2023-05-05 22:51:20 +02:00
mudler
ec2adc2c03 tests: use 3 cores 2023-05-05 22:07:01 +02:00
mudler
ad301e6ed7 example(add): document query example 2023-05-05 21:56:31 +02:00
mudler
d094381e5d ci: lower fixtures spec 2023-05-05 21:28:38 +02:00
mudler
3ff9bbd217 examples: add rwkv script folder 2023-05-05 19:04:52 +02:00
mudler
e62ee2bc06 fix: remove trailing 0s from embeddings
This happens when no max_tokens are set, so by default go-llama
allocates more space for the slice and padding happens.
2023-05-05 18:35:03 +02:00
mudler
b49721cdd1 fix: respect config from file for backends settings 2023-05-05 18:05:10 +02:00
mudler
64c0a7967f fix: pass prediction options when using the model 2023-05-05 15:56:02 +02:00
mudler
e96eadab40 feat: support deprecated embeddings API 2023-05-05 15:55:19 +02:00
mudler
e73283121b feat: support arrays for prompt and input
Signed-off-by: mudler <mudler@mocaccino.org>
2023-05-05 15:54:59 +02:00
mudler
857d13e8d6 debug: wire up go-fiber debugger 2023-05-05 15:53:57 +02:00
ci-robbot [bot]
91db3d4d5c
⬆️ Update go-skynet/go-llama.cpp (#194)
Signed-off-by: GitHub <noreply@github.com>
Co-authored-by: mudler <mudler@users.noreply.github.com>
2023-05-05 13:45:50 +02:00
Ettore Di Giacinto
961cf29217
feat: expose mirostat to config (#193) 2023-05-05 13:45:37 +02:00
Ettore Di Giacinto
c839b334eb
feat: add embeddings for go-llama.cpp backend (#190) 2023-05-05 11:20:06 +02:00