Krish Dholakia
5ee3b0f30f
Merge pull request #3996 from BerriAI/litellm_azure_assistants_api_support
...
feat(assistants/main.py): Azure Assistants API support
2024-06-03 21:05:03 -07:00
Krrish Dholakia
2e8f081a86
fix(main.py): cast to string only if var is not None
2024-06-03 19:25:59 -07:00
Krrish Dholakia
7163bce37b
feat(assistants/main.py): Closes https://github.com/BerriAI/litellm/issues/3993
2024-06-03 18:47:05 -07:00
Krrish Dholakia
5e12307a48
fix(anthropic.py): fix anthropic async streaming
...
pass the 'stream' param to the httpx call
Addresses https://github.com/BerriAI/litellm/issues/3728#issuecomment-2143985104
2024-06-02 16:01:44 -07:00
Krrish Dholakia
9ef83126d7
fix(utils.py): correctly instrument passing through api version in optional param check
2024-06-01 19:31:52 -07:00
Krrish Dholakia
7efac4d36c
fix(azure.py): support dropping 'tool_choice=required' for older azure API versions
...
Closes https://github.com/BerriAI/litellm/issues/3876
2024-06-01 18:44:50 -07:00
Krrish Dholakia
93c9ea160d
fix(openai.py): fix client caching logic
2024-06-01 16:45:56 -07:00
Krrish Dholakia
a16a1c407a
fix(http_handler.py): allow setting ca bundle path
2024-06-01 14:48:53 -07:00
Krrish Dholakia
f1ce7bb300
fix(http_handler.py): add bool check for os.getenv verif ssl value
2024-06-01 14:07:41 -07:00
Krrish Dholakia
22a0c400dd
fix(http_handler.py): support verify_ssl=False when using httpx client
2024-06-01 13:56:45 -07:00
Ishaan Jaff
d83b4a00d3
Merge pull request #3956 from BerriAI/litellm_cache_openai_clients
...
[FEAT] Perf improvements - litellm.completion / litellm.acompletion - Cache OpenAI client
2024-06-01 09:46:42 -07:00
Ishaan Jaff
47dd52c566
fix used hashed api key
2024-06-01 09:24:16 -07:00
Ishaan Jaff
47337c172e
fix - in memory client cache
2024-06-01 08:58:22 -07:00
Krish Dholakia
e7ff3adc26
Merge pull request #3944 from BerriAI/litellm_fix_parallel_streaming
...
fix: fix streaming with httpx client
2024-05-31 21:42:37 -07:00
Ishaan Jaff
1c16904566
fix cache openai client for embeddings, text, speech
2024-05-31 21:35:03 -07:00
Ishaan Jaff
cedeb10a08
fix - linting error
2024-05-31 21:24:14 -07:00
Ishaan Jaff
6feeff1f31
feat - cache openai clients
2024-05-31 21:22:06 -07:00
Krish Dholakia
8f87da4b20
Merge pull request #3939 from pharindoko/main
...
fix(bedrock): convert botocore credentials when role is assumed
2024-05-31 18:46:15 -07:00
Krish Dholakia
fbeb9d7ea7
Merge pull request #3935 from BerriAI/litellm_cache_vertex_clients
...
[Fix] Cache Vertex AI clients - Perf improvement
2024-05-31 18:44:10 -07:00
Krish Dholakia
08bae3185a
Merge pull request #3936 from BerriAI/litellm_assistants_api_proxy
...
feat(proxy_server.py): add assistants api endpoints to proxy server
2024-05-31 18:43:22 -07:00
Krrish Dholakia
93c3635b64
fix: fix streaming with httpx client
...
prevent overwriting streams in parallel streaming calls
2024-05-31 10:55:18 -07:00
uid10804
928efe2d87
refactor(bedrock_httpx): change botocore reference
2024-05-31 16:57:28 +02:00
David Manouchehri
0ed01f430d
fix(bedrock_httpx.py): Fix OIDC support.
2024-05-31 12:44:52 +00:00
David Manouchehri
c301d0c5ca
feat (bedrock_httpx.py): Add OIDC support for Amazon Bedrock with httpx.
2024-05-31 12:44:50 +00:00
uid10804
2f130b39c0
fix: add botocore credentials extraction and conversion
...
The code changes in `bedrock_httpx.py` add functionality to extract and convert AWS STS credentials to session credentials using botocore. This fixes later error in add_auth request when token needs to be assigned.
2024-05-31 12:02:34 +02:00
Krrish Dholakia
e2b34165e7
feat(proxy_server.py): add assistants api endpoints to proxy server
2024-05-30 22:44:43 -07:00
Ishaan Jaff
f52bf5976b
fix - vertex ai cache clients
2024-05-30 21:22:32 -07:00
Krish Dholakia
d3a247bf20
Merge pull request #3928 from BerriAI/litellm_audio_speech_endpoint
...
feat(main.py): support openai tts endpoint
2024-05-30 17:30:42 -07:00
Krrish Dholakia
93166cdabf
fix(openai.py): fix openai response for /audio/speech endpoint
2024-05-30 16:41:06 -07:00
Krrish Dholakia
a67cbf47f6
feat(main.py): support openai tts endpoint
...
Closes https://github.com/BerriAI/litellm/issues/3094
2024-05-30 14:28:28 -07:00
KX
d3921a3d28
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
Krrish Dholakia
da56201e80
fix(main.py): pass api key and api base to openai.py for audio transcription call
2024-05-29 21:29:01 -07:00
Krrish Dholakia
3d32b00821
fix(openai.py): only allow 'user' as optional param if openai model
2024-05-29 15:15:02 -07:00
Ishaan Jaff
99e506525c
Revert "Added support for Triton chat completion using trtlllm generate endpo…"
2024-05-29 13:42:49 -07:00
Ishaan Jaff
e8c1e87ac9
Merge pull request #3895 from giritatavarty-8451/litellm_triton_chatcompletion_support
...
Added support for Triton chat completion using trtlllm generate endpo…
2024-05-29 12:50:31 -07:00
Ishaan Jaff
6e9cc26ca1
Merge pull request #3888 from BerriAI/litellm_add_files_proxy
...
[Feat] LiteLLM Proxy Add `POST /v1/files` and `GET /v1/files`
2024-05-28 22:36:33 -07:00
Ishaan Jaff
ca8163bbba
feat - add afile_content, file_content
2024-05-28 20:58:22 -07:00
Ishaan Jaff
6bf6059b3e
Merge pull request #3882 from BerriAI/litellm_add_batches_sdk
...
[BETA-Feature] Add OpenAI `v1/batches` Support on LiteLLM SDK
2024-05-28 19:38:12 -07:00
Krish Dholakia
b5c89a249a
Merge pull request #3883 from BerriAI/litellm_anthropic_parallel_streaming_fix
...
fix(anthropic.py): fix parallel streaming on anthropic.py
2024-05-28 17:21:57 -07:00
Ishaan Jaff
6688215c18
feat - add aretrieve_batch
2024-05-28 17:12:41 -07:00
Ishaan Jaff
1ef7cd923c
feat - add acreate_batch
2024-05-28 17:03:29 -07:00
Ishaan Jaff
758ed9e923
feat - add litellm.acreate_file
2024-05-28 16:47:27 -07:00
Krrish Dholakia
324bf027f5
fix(anthropic.py): fix parallel streaming on anthropic.py
...
prevent parallel requests from cancelling each other
Fixes https://github.com/BerriAI/litellm/issues/3881
2024-05-28 16:29:09 -07:00
Ishaan Jaff
38285e53c3
working create_batch
2024-05-28 15:45:23 -07:00
Ishaan Jaff
d5dbf084ed
feat - import batches in __init__
2024-05-28 15:35:11 -07:00
Giri Tatavarty
a58dc68418
Added support for Triton chat completion using trtlllm generate endpoint and custom infer endpoint
2024-05-28 07:54:11 -07:00
frob
17f49a4015
Merge branch 'BerriAI:main' into ollama-image-handling
2024-05-28 09:18:36 +02:00
Krrish Dholakia
322a8218c0
fix(openai.py): fix deepinfra config optional param
2024-05-27 18:36:34 -07:00
Krrish Dholakia
f0f853b941
fix(utils.py): support deepinfra optional params
...
Fixes https://github.com/BerriAI/litellm/issues/3855
2024-05-27 09:16:56 -07:00
frob
a75b09974e
Merge branch 'BerriAI:main' into ollama-image-handling
2024-05-27 17:42:30 +02:00
