4d9568172d
api: add optional hints to errors for troubleshooting
...
Introduces structured error responses that pair error messages with user-friendly
troubleshooting hints. This improves error handling across the codebase and
provides better guidance to users when things go wrong.
Key changes:
- Add ErrorResponse type with Err and Hint fields
- Update client to handle structured errors in streaming and regular responses
- Add specific error handling for common cases like missing models
- Improve CLI output to clearly show both errors and hints
- Add comprehensive test coverage for new error formats
Maintains backward compatibility with existing error handling while making error
messages more helpful and actionable for users.
2025-02-11 13:47:32 -08:00
00ba065e90
api: document client stream behavior with a test
...
Added unit tests to verify error handling behavior in the Client.stream and Client.do methods.
Tests cover various error scenarios including:
- Error responses with status codes >= 400
- Error messages with successful status codes
- Empty error messages
- Successful responses
2025-02-11 13:47:09 -08:00
0189bdd0b7
readme: add Abso SDK to community integrations ( #8973 )
2025-02-11 00:14:45 -08:00
f4711da7bd
ml/backend/ggml: fix crash on dlopen for non-AVX systems ( #8976 )
2025-02-10 09:52:12 -08:00
38117fba83
readme: add Lunary to observability community integrations ( #8975 )
2025-02-09 22:08:46 -08:00
1f766c36fb
ci: use windows-2022 to sign and bundle ( #8941 )
...
ollama requires vcruntime140_1.dll which isn't found on 2019. previously
the job used the windows runner (2019) but it explicitly installs
2022 to build the app. since the sign job doesn't actually build
anything, it can use the windows-2022 runner instead.
2025-02-08 13:07:00 -08:00
484a99e428
docs: add LocalLLM app to community integrations ( #8953 )
2025-02-08 12:28:01 -08:00
ec6121c331
docs: ollama zig community lib ( #8688 )
2025-02-08 11:10:47 -08:00
b86c0a1500
docs: link directly to latest release page for tdm-gcc ( #8939 )
2025-02-08 00:21:10 -08:00
7e402ebb8c
readme: add deepseek to supported models
2025-02-07 11:28:28 -08:00
b901a712c6
docs: improve syntax highlighting in code blocks ( #8854 )
2025-02-07 09:55:07 -08:00
abb8dd57f8
add gfx instinct gpus ( #8933 )
2025-02-07 09:51:22 -08:00
a400df48c0
docs: include port in faq.md OLLAMA_HOST examples ( #8905 )
2025-02-06 18:45:09 -08:00
6ab4ba4c26
readme: add React Native client to community integrations ( #8877 )
2025-02-06 17:15:48 -08:00
e8d4eb3e68
readme: add ChibiChat to community integrations ( #8883 )
2025-02-06 16:08:46 -08:00
ae7e368f75
build(rocm): add numa, elf ( #8900 )
2025-02-06 15:46:30 -08:00
31acd1ebf9
readme: add Ollama Chat WebUI for Docker to community integrations ( #8084 )
2025-02-06 15:41:02 -08:00
9a4757ae66
build(rocm): add tinfo ( #8899 )
2025-02-06 15:08:12 -08:00
7814019708
docs: add step for removing libraries in linux.md ( #8897 )
2025-02-06 14:54:58 -08:00
b698f9a0d8
build: add missing dependencies ( #8896 )
2025-02-06 13:12:16 -08:00
32285a6d19
format: rename test file from byte_test.go to bytes_test.go ( #8865 )
2025-02-06 13:06:15 -08:00
1c198977ec
ci: fix linux archive ( #8862 )
...
the find returns intermediate directories which pulls the parent
directories. it also omits files under lib/ollama.
switch back to globbing
2025-02-05 19:45:58 -08:00
330b6c50b0
readme: add simple-discord-ai to community integrations ( #8659 )
2025-02-05 18:35:04 -08:00
928911bc68
runner: avoid buffer overwrite when generating multiple embeddings ( #8714 )
...
Shield the code processing the embedding result
from subsequent calls that may overwrite the same
buffer to process a second input when retrieving
model embeddings.
2025-02-05 16:53:33 -08:00
5b446cc815
chore: update gitattributes ( #8860 )
...
* chore: update gitattributes
* chore: add build info source
2025-02-05 16:37:18 -08:00
451c1596af
readme: add MLflow Tracing as an observability integration ( #8811 )
2025-02-05 16:04:24 -08:00
932bded12f
chore: add optional field for server logs
2025-02-05 15:55:32 -08:00
070ad913ac
ci: fix linux archive
2025-02-05 15:08:02 -08:00
8d8b9f83ae
format: byte formatting test coverage ( #8692 )
...
Removed redundant checks and streamlined the switch-case structure.
Added test cases for both HumanBytes and HumanBytes2 to cover a wide range of scenarios.
2025-02-05 12:23:07 -08:00
f00d359a67
docs: add section in development.md on library detection ( #8855 )
2025-02-05 11:16:27 -08:00
291def6adb
server: increase timeout in stall detection from 5s to 30s ( #8831 )
...
In some cases, downloads slow due to disk i/o or other factors,
causing the download to restart a part. This causes the download
to "reverse" in percent completion. By increasing the timeout to 30s,
this should happen less frequently.
2025-02-05 10:00:26 -08:00
cd3fbf1c49
llama: use dynamic backend loading for mllama and clip ( #8835 )
2025-02-05 09:46:56 -08:00
c852b8e021
server: always print upload/download part info ( #8832 )
2025-02-04 19:30:49 -08:00
d8932c55e7
server: fix out of bounds exception on model download ( #8746 )
2025-02-04 18:52:47 -08:00
63f0269f7f
ci: split docker build by platform
...
this improves build reliability and concurrency
2025-02-04 17:04:27 -08:00
4759ecae19
ml/backend/ggml: fix library loading on macOS amd64 ( #8827 )
2025-02-04 15:05:39 -08:00
65b7ecac7b
fix extra quote
2025-02-04 08:35:30 -08:00
f9d2d89135
fix linux archive
2025-02-03 16:12:33 -08:00
669dc31cf3
fix build
2025-02-03 15:10:51 -08:00
d4d338c224
readme: add Chipper to community integrations ( #8803 )
2025-02-03 14:18:19 -08:00
bfdeffc375
docs: use OLLAMA_VERSION=0.5.7 for install version override ( #8802 )
2025-02-03 13:54:08 -08:00
e806184023
fix release workflow
2025-02-03 13:19:57 -08:00
50566113ac
llm: do not error if LibOllamaPath does not exist ( #8801 )
2025-02-03 12:27:48 -08:00
ad22ace439
docs: add missing json and shell code blocks in api.md ( #8766 )
2025-02-02 13:12:55 -08:00
f4321a421c
readme: add MinimalNextOllamaChat to community integrations ( #8767 )
2025-02-02 12:56:10 -08:00
475333d533
fix docker build-args
...
env context is not accessible from job.*.strategy. since it's in the
environment, just tell docker to use the environment variable[1]
[1]: https://docs.docker.com/reference/cli/docker/buildx/build/#build-arg
2025-01-31 14:56:02 -08:00
39fd89308c
build: set CFLAGS=-O3 specifically for cpu.go
2025-01-31 10:25:39 -08:00
548a9f56a6
Revert "cgo: use O3"
...
This reverts commit bea1f1fac6
2025-01-31 10:25:39 -08:00
3f0cb36bdb
build: set goflags in linux release
2025-01-30 13:07:32 -08:00
bea1f1fac6
cgo: use O3
2025-01-30 12:21:50 -08:00
Bruce MacDonald
Hugues Chocart
Jeffrey Morgan
Michael Yang
Qusai Ismael
DravenK
Guddu Kumar
Azis Alvriyanto
Leisure Linux
annilq
CosmicEventHorizon
oslook
Abhinav Pant
zyphixor
Diego Pereira
Daniel Lok
Yashwanth A
William
Tilman Griesel
Melroy van den Berg
Davide Bertoni
Anıl Kaynar