Krrish Dholakia
93463565fb
fix(replicate.py): pass version if passed in
2024-04-26 17:11:21 -07:00
Krish Dholakia
4b0f73500f
Merge branch 'main' into litellm_default_router_retries
2024-04-26 14:52:24 -07:00
frob
2cc0990c1c
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-26 12:57:18 +02:00
pwm
6fedcb873b
add safety_settings parameters to Vertex vision async_completion function
2024-04-26 14:35:01 +08:00
Krrish Dholakia
54241f2551
test(test_router_fallbacks.py): fix testing
2024-04-25 17:43:40 -07:00
Krrish Dholakia
ccb864bbea
fix(factory.py): correctly apply bos token for llama3 instruct prompt template
2024-04-25 17:37:17 -07:00
Krrish Dholakia
5f8d88d363
fix(vertex_ai.py): handle stream=false
...
also adds unit testing for vertex ai calls with langchain
2024-04-25 13:59:37 -07:00
Krrish Dholakia
160acc085a
fix(router.py): fix default retry logic
2024-04-25 11:57:27 -07:00
Lucca Zenobio
6127d9f488
merge
2024-04-25 15:00:07 -03:00
aswny
781af56f48
check model type chat/instruct to apply template
2024-04-25 17:52:38 +00:00
aswny
9ead717531
fix Llama models message to prompt conversion in for AWS Bedrock provider
2024-04-25 17:19:55 +00:00
Krrish Dholakia
4f46b4c397
fix(factory.py): add replicate meta llama prompt templating support
2024-04-25 08:25:00 -07:00
Krish Dholakia
435a4b5ed4
Merge pull request #3267 from BerriAI/litellm_openai_streaming_fix
...
fix(utils.py): fix streaming to not return usage dict
2024-04-24 21:08:33 -07:00
Krrish Dholakia
df7db2b870
fix(factory.py): support llama3 instuct chat template
...
allows automatic templating for llama3 instruct requests
2024-04-24 20:35:10 -07:00
Krrish Dholakia
b918f58262
fix(vertex_ai.py): raise explicit error when image url fails to download - prevents silent failure
2024-04-24 09:23:15 -07:00
Krrish Dholakia
48c2c3d78a
fix(utils.py): fix streaming to not return usage dict
...
Fixes https://github.com/BerriAI/litellm/issues/3237
2024-04-24 08:06:07 -07:00
Simon Sanchez Viloria
777b4b2bbc
(feat) make manage_response work with request.request instead of httpx.Request
2024-04-24 12:55:25 +02:00
Krish Dholakia
8d2e411df6
Merge pull request #3124 from elisalimli/bugfix/add-missing-tool-calls-mistral-messages
...
Add missing tool_calls and name to messages
2024-04-23 17:25:12 -07:00
frob
2ee5251622
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-23 23:28:12 +02:00
Simon Sanchez Viloria
d72b725273
Fixed bugs in prompt factory for ibm-mistral and llama 3 models.
2024-04-23 16:20:49 +02:00
Simon S. Viloria
2ef4fb2efa
Merge branch 'BerriAI:main' into feature/watsonx-integration
2024-04-23 12:18:34 +02:00
Simon Sanchez Viloria
e64aceea91
(feat) Update WatsonX credentials and variable names
2024-04-23 12:16:04 +02:00
Simon Sanchez Viloria
74d2ba0a23
feat - watsonx refractoring, removed dependency, and added support for embedding calls
2024-04-23 12:01:13 +02:00
Krrish Dholakia
ec2c70e362
fix(vertex_ai.py): fix streaming logic
2024-04-22 19:15:20 -07:00
Krrish Dholakia
0bb8a4434e
fix(vertex_ai.py): remove ExtendedGenerationConfig usage
2024-04-22 18:23:21 -07:00
David Manouchehri
c643e04ada
improve(vertex_ai.py): Add frequency_penalty and presence_penalty.
2024-04-22 18:02:59 +00:00
David Manouchehri
1a7eec5786
improve(vertex_ai.py): Switch to simpler dict type.
2024-04-22 17:00:37 +00:00
Ishaan Jaff
b88a21b094
Revert "Load google ADC before init AnthropicVertex"
2024-04-21 16:44:23 -07:00
Simon S. Viloria
a77537ddd4
Merge branch 'BerriAI:main' into feature/watsonx-integration
2024-04-21 10:35:51 +02:00
frob
ae87cb3a31
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-21 01:49:10 +02:00
Krish Dholakia
9f91f9919f
Merge pull request #3115 from elisalimli/litellm_fix/missing-spaces-between-prompts-cohere-chat
...
Fix new line issue in cohere_message_pt
2024-04-20 13:15:20 -07:00
Krish Dholakia
3faada32d5
Merge pull request #3118 from n1lanjan/2833-anthropic-tool-call-fix
...
Fix tool call errors using anthropic
2024-04-20 13:14:29 -07:00
Krish Dholakia
a9828b1e13
Merge pull request #3150 from ushuz/anthropic-vertex-adc
...
Load google ADC before init AnthropicVertex
2024-04-20 13:00:10 -07:00
Simon S. Viloria
7b2bd2e0e8
Merge branch 'BerriAI:main' into feature/watsonx-integration
2024-04-20 21:02:54 +02:00
Krish Dholakia
78579d4a24
Merge pull request #3170 from rick-github/ollama-special-symbol
...
Disable special tokens in ollama completion when counting tokens
2024-04-20 11:57:01 -07:00
Krish Dholakia
8a2f8c0418
Merge pull request #3189 from merefield/main
...
FIX: ollama chat completion proxy internal server 500
2024-04-20 11:56:34 -07:00
Simon Sanchez Viloria
6edb133733
Added support for IBM watsonx.ai models
2024-04-20 20:06:46 +02:00
Ishaan Jaff
200f58c1e7
(fix) missing PIL import
2024-04-20 08:27:00 -07:00
merefield
50a917a096
FIX: use value not param name when mapping frequency_penalty
2024-04-20 09:25:35 +01:00
frob
5fb5bce780
Merge branch 'BerriAI:main' into ollama-special-symbol
2024-04-20 00:49:57 +02:00
frob
848d1a0be8
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-20 00:49:41 +02:00
Krrish Dholakia
62a8bf134f
fix(http_handler.py): fix linting error
2024-04-19 15:45:24 -07:00
Josh Mandel
f411443e58
fix: Stream completion responses from anthropic. (Fix 3129)
2024-04-19 16:13:19 -05:00
Krrish Dholakia
3c6b6355c7
fix(ollama_chat.py): accept api key as a param for ollama calls
...
allows user to call hosted ollama endpoint using bearer token for auth
2024-04-19 13:02:13 -07:00
frob
3df7231fa5
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
02831b546f
Merge branch 'BerriAI:main' into ollama-image-handling
2024-04-19 20:45:12 +02:00
John HU
6724bf6419
Load google ADC before init AnthropicVertex
2024-04-18 19:48:57 -07:00
Krrish Dholakia
cf1cc71b87
fix(factory.py): add mistral config to known tokenizer configs
2024-04-18 17:11:52 -07:00
David Manouchehri
f65c02d43a
(feat) - Add seed to Cohere Chat.
2024-04-18 20:57:06 +00:00
Nilanjan De
ca3d2fea56
fix for #2904 , remove XML characters in content
2024-04-18 22:42:32 +04:00
