Krrish Dholakia
c69193c321
fix: move to using pydantic obj for setting values
2024-07-11 13:18:36 -07:00
corrm
93cb6d6175
chore: Improved OllamaConfig get_required_params and ollama_acompletion and ollama_async_streaming functions
2024-06-24 05:55:22 +03:00
Krish Dholakia
ea4334f760
Merge branch 'main' into litellm_cleanup_traceback
2024-06-06 16:32:08 -07:00
Krrish Dholakia
e391e30285
refactor: replace 'traceback.print_exc()' with logging library
...
allows error logs to be in json format for otel logging
2024-06-06 13:47:43 -07:00
sha-ahammed
93e7b9346c
feat: Add Ollama as a provider in the proxy UI
2024-06-05 16:48:38 +05:30
KX
ddb998fac1
fix: add missing seed parameter to ollama input
...
Current ollama interfacing does not allow for seed, which is supported in https://github.com/ollama/ollama/blob/main/docs/api.md#parameters and https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values
This resolves that by adding in handling of seed parameter.
2024-05-31 01:47:56 +08:00
frob
5ab5f2c29e
Merge branch 'BerriAI:main' into ollama-image-handling
2024-05-09 20:25:30 +02:00
Krrish Dholakia
5f93cae3ff
feat(proxy_server.py): return litellm version in response headers
2024-05-08 16:00:08 -07:00
frob
4a6867879d
Merge branch 'BerriAI:main' into ollama-image-handling
2024-05-09 00:14:29 +02:00
Ishaan Jaff
d399947111
Merge pull request #3470 from mbektas/fix-ollama-embeddings
...
support sync ollama embeddings
2024-05-07 19:21:37 -07:00
frob
c6e6efc902
Merge branch 'BerriAI:main' into ollama-image-handling
2024-05-06 18:06:45 +02:00
Mehmet Bektas
1236638266
support sync ollama embeddings
2024-05-05 19:44:25 -07:00
Jack Collins
218f15de60
Fix: get format from data not optional_params ollama non-stream completion
2024-05-05 18:59:26 -07:00
Jack Collins
5bc934303c
Add missing import itertools.chain
2024-05-05 18:54:08 -07:00
Jack Collins
5393c5459e
Fix: Set finish_reason to tool_calls for non-stream responses in ollama
2024-05-05 18:52:31 -07:00
Jack Collins
2d43423138
Parse streamed function calls as single delta in ollama
2024-05-05 18:52:20 -07:00
frob
74a0508682
Merge branch 'BerriAI:main' into ollama-image-handling
2024-05-01 22:29:37 +02:00
Krish Dholakia
52f43c8c2e
Merge branch 'main' into litellm_ollama_tool_call_reponse
2024-05-01 10:24:05 -07:00
frob
b986fbfa13
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-21 01:49:10 +02:00
frob
df4fd2a7bf
Disable special tokens in ollama completion when counting tokens
...
Some(?) models (eg, codegemma) don't return a prompt_eval_count field, so ollama.py tries to compute the value based on encoding of the prompt. Unfortunately FIM symbols used in the prompt (eg, "<|fim_prefix|>") cause the encoder to throw an exception, so we disable special processing.
2024-04-19 21:38:42 +02:00
frob
e0276feaf5
Update comment.
2024-04-16 01:12:24 +02:00
frob
8535e9eb9d
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-13 21:42:58 +02:00
frob
dadf356a8e
ollama also accepts PNG
2024-04-08 03:35:02 +02:00
frob
1732478592
Update ollama.py for image handling
...
ollama wants plain base64 jpeg images, and some clients send dataURI and/or webp. Remove prefixes and convert all non-jpeg images to jpeg.
2024-04-08 03:28:24 +02:00
Gregory Nwosu
0609da96e3
created defaults for response["eval_count"]
...
there is no way in litellm to disable the cache in ollama that is removing the eval_count response keys from the json.
This PR allows the code to create sensible defaults for when the response is empty
see
- https://github.com/ollama/ollama/issues/1573
- https://github.com/ollama/ollama/issues/2023
2024-04-08 02:03:54 +01:00
frob
5c000fb6b1
Update ollama.py for image handling
...
Some clients (eg librechat) send images in datauri format, not plain base64. Strip off the prerix when passing images to ollama.
2024-04-07 13:05:39 +02:00
DaxServer
947ba9d15b
docs: Update references to Ollama repository url
...
Updated references to the Ollama repository URL from https://github.com/jmorganca/ollama to https://github.com/ollama/ollama .
2024-03-31 19:35:37 +02:00
Krrish Dholakia
f7dd1758bb
fix(ollama.py): fix type issue
2024-03-28 15:01:56 -07:00
onukura
1bd60287ba
Add a feature to ollama aembedding to accept batch input
2024-03-27 21:39:19 +00:00
onukura
6ee8f26746
Fix ollama embedding response
2024-03-25 16:26:49 +00:00
Lunik
a1be265052
🐛 fix: Ollama vision models call arguments (like : llava)
...
Signed-off-by: Lunik <lunik@tiwabbit.fr>
2024-02-26 17:52:55 +01:00
Krrish Dholakia
220a90527f
fix(ollama.py): support format for ollama
2024-02-06 10:11:52 -08:00
Ishaan Jaff
175c4000da
Merge pull request #1750 from vanpelt/patch-2
...
Re-raise exception in async ollama streaming
2024-02-05 08:12:17 -08:00
Krrish Dholakia
a2bb95be59
refactor(ollama.py): trigger rebuild
2024-02-03 20:23:43 -08:00
Krrish Dholakia
56110188fd
fix(ollama.py): fix api connection error
...
https://github.com/BerriAI/litellm/issues/1735
2024-02-03 20:22:33 -08:00
Chris Van Pelt
547b9beefc
Re-raise exception in async ollama streaming
2024-02-01 16:14:07 -08:00
Krrish Dholakia
635a34b543
fix(utils.py): fix streaming chunks to not return role, unless set
2024-02-01 09:55:56 -08:00
TheDiscoMole
02a73e14a3
changing ollama response parsing to expected behaviour
2024-01-19 23:36:24 +01:00
ishaan-jaff
3081dc525a
(feat) litellm.completion - support ollama timeout
2024-01-09 10:34:41 +05:30
Krrish Dholakia
d89a58ec54
fix(ollama.py): use tiktoken as backup for prompt token counting
2024-01-09 09:47:18 +05:30
Krrish Dholakia
79978c44ba
refactor: add black formatting
2023-12-25 14:11:20 +05:30
Krrish Dholakia
b7a7c3a4e5
feat(ollama.py): add support for async ollama embeddings
2023-12-23 18:01:25 +05:30
Krrish Dholakia
a65dfdde94
test(test_completion.py-+-test_streaming.py): add ollama endpoint to ci/cd pipeline
2023-12-22 12:21:33 +05:30
Krrish Dholakia
ae288c97fb
fix(ollama.py): use litellm.request timeout for async call timeout
2023-12-22 11:22:24 +05:30
Krrish Dholakia
636ac9b605
feat(ollama.py): add support for ollama function calling
2023-12-20 14:59:55 +05:30
ishaan-jaff
3c37e0d58b
(fix) proxy + ollama - raise exception correctly
2023-12-19 18:48:34 +05:30
Joel Eriksson
afcc83bb15
Fix bug when iterating over lines in ollama response
...
async for line in resp.content.iter_any() will return
incomplete lines when the lines are long, and that
results in an exception being thrown by json.loads()
when it tries to parse the incomplete JSON
The default behavior of the stream reader for aiohttp
response objects is to iterate over lines, so just
removing .iter_any() fixes the bug
2023-12-17 20:23:26 +02:00
Krrish Dholakia
5f4310f592
fix(ollama.py): fix sync ollama streaming
2023-12-16 21:23:21 -08:00
Krrish Dholakia
87df233a19
fix(health.md): add background health check details to docs
2023-12-16 10:31:59 -08:00
Krrish Dholakia
1da7d35218
feat(proxy_server.py): enable infinite retries on rate limited requests
2023-12-15 20:03:41 -08:00
