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
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
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
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
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
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
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
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
Nilanjan De
ecfae6d465
update factory.py
2024-04-18 22:31:08 +04:00
Nilanjan De
e1fd463f8c
update factory.py
2024-04-18 22:27:11 +04:00
alisalim17
a3f90ab735
fix: add missing tool_calls and function name to messages in mistral_api_pt
2024-04-18 20:49:01 +04:00
Nilanjan De
c85018c780
update factory.py
2024-04-18 18:13:20 +04:00
Nilanjan De
4c7d94b2b4
update factory.py
2024-04-18 17:35:52 +04:00
Nilanjan De
7ca213e92f
update factory.py
2024-04-18 15:12:31 +04:00
Nilanjan De
f1f2204c2a
fix tool call errors using anthropic
2024-04-18 15:04:54 +04:00
alisalim17
5060d8d64f
fix: newline issue in cohere_message_pt
2024-04-18 11:10:31 +04:00
Krrish Dholakia
c47b39c032
fix(vertex_ai.py): fix faulty async completion function call tool check
2024-04-17 16:30:28 -07:00
Krrish Dholakia
32d94feddd
refactor(utils.py): make it clearer how vertex ai params are handled '
...
'
2024-04-17 16:20:56 -07:00
Krrish Dholakia
060ac995d6
fix(vertex_ai.py): accept credentials as a json string
2024-04-16 17:34:25 -07:00
Krish Dholakia
2837b6b2f3
Merge pull request #3019 from ligaz/fix-anthropic-system-msg-handling
...
Fix Anthropic system message handling
2024-04-16 07:18:47 -07:00
Ishaan Jaff
abf365b3ac
Merge pull request #3054 from BerriAI/litellm_supports_vision
...
[Feat] view models that `supports_vision`
2024-04-15 18:31:32 -07:00
Ishaan Jaff
462da5a778
fix - support base 64 image conversion for all gemini model
2024-04-15 18:18:55 -07:00
Krrish Dholakia
1ec7118e1f
fix(vertex_ai_anthropic.py): set vertex_credentials for vertex ai anthropic calls
...
allows setting vertex credentials as a json string for vertex ai anthropic calls
2024-04-15 14:16:28 -07:00
Krrish Dholakia
50081479f9
fix(main.py): accept vertex service account credentials as json string
...
allows us to dynamically set vertex ai credentials
2024-04-15 13:28:59 -07:00
Krrish Dholakia
dce1f5466f
fix(anthropic_text.py): return process_response value
2024-04-15 08:51:26 -07:00
Krrish Dholakia
26286a54b8
fix(anthropic_text.py): add support for async text completion calls
2024-04-15 08:15:00 -07:00
Stefan Dobrev
1cfea955aa
Fix Anthropic system message handling
2024-04-14 16:23:59 +03:00
Krrish Dholakia
7a3821e0f6
fix(gemini.py): log system prompt in verbose output
2024-04-11 23:15:58 -07:00
Krrish Dholakia
77d6b882b8
fix(vertex_ai.py): check if 'response_mime_type' in generation config before passing it in
2024-04-11 23:10:59 -07:00
David Manouchehri
05350037be
(feat) - Extreme dirty hack for response_mime_type in Vertex AI.
2024-04-12 00:03:31 +00:00
David Manouchehri
d08674bf2f
(feat) - Dirty hack to get response_mime_type working before it's released in the Python SDK.
2024-04-12 00:03:30 +00:00
