phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

LiteLLM Minor Fixes & Improvements (09/24/2024) (#5880)

Browse source 
* LiteLLM Minor Fixes & Improvements (09/23/2024)  (#5842)

* feat(auth_utils.py): enable admin to allow client-side credentials to be passed

Makes it easier for devs to experiment with finetuned fireworks ai models

* feat(router.py): allow setting configurable_clientside_auth_params for a model

Closes https://github.com/BerriAI/litellm/issues/5843

* build(model_prices_and_context_window.json): fix anthropic claude-3-5-sonnet max output token limit

Fixes https://github.com/BerriAI/litellm/issues/5850

* fix(azure_ai/): support content list for azure ai

Fixes https://github.com/BerriAI/litellm/issues/4237

* fix(litellm_logging.py): always set saved_cache_cost

Set to 0 by default

* fix(fireworks_ai/cost_calculator.py): add fireworks ai default pricing

handles calling 405b+ size models

* fix(slack_alerting.py): fix error alerting for failed spend tracking

Fixes regression with slack alerting error monitoring

* fix(vertex_and_google_ai_studio_gemini.py): handle gemini no candidates in streaming chunk error

* docs(bedrock.md): add llama3-1 models

* test: fix tests

* fix(azure_ai/chat): fix transformation for azure ai calls

* feat(azure_ai/embed): Add azure ai embeddings support

Closes https://github.com/BerriAI/litellm/issues/5861

* fix(azure_ai/embed): enable async embedding

* feat(azure_ai/embed): support azure ai multimodal embeddings

* fix(azure_ai/embed): support async multi modal embeddings

* feat(together_ai/embed): support together ai embedding calls

* feat(rerank/main.py): log source documents for rerank endpoints to langfuse

improves rerank endpoint logging

* fix(langfuse.py): support logging `/audio/speech` input to langfuse

* test(test_embedding.py): fix test

* test(test_completion_cost.py): fix helper util
This commit is contained in:
Krish Dholakia 2024-09-25 22:11:57 -07:00 • committed by GitHub
parent 5bc5eaff8a
commit 16c0307eab
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 1675 additions and 340 deletions
Download patch file Download diff file Expand all files Collapse all files

59
model_prices_and_context_window.json
View file

@ -990,6 +990,26 @@
"mode": "chat",
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice"
},
"azure_ai/Cohere-embed-v3-english": {
"max_tokens": 512,
"max_input_tokens": 512,
"output_vector_size": 1024,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
"mode": "embedding",
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice"
},
"azure_ai/Cohere-embed-v3-multilingual": {
"max_tokens": 512,
"max_input_tokens": 512,
"output_vector_size": 1024,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0,
"litellm_provider": "azure_ai",
"mode": "embedding",
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice"
},
"babbage-002": {
"max_tokens": 16384,
"max_input_tokens": 16384,
@ -4964,50 +4984,71 @@
"together-ai-up-to-4b": {
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000001,
"litellm_provider": "together_ai"
"litellm_provider": "together_ai",
"mode": "chat"
},
"together-ai-4.1b-8b": {
"input_cost_per_token": 0.0000002,
"output_cost_per_token": 0.0000002,
"litellm_provider": "together_ai"
"litellm_provider": "together_ai",
"mode": "chat"
},
"together-ai-8.1b-21b": {
"max_tokens": 1000,
"input_cost_per_token": 0.0000003,
"output_cost_per_token": 0.0000003,
"litellm_provider": "together_ai"
"litellm_provider": "together_ai",
"mode": "chat"
},
"together-ai-21.1b-41b": {
"input_cost_per_token": 0.0000008,
"output_cost_per_token": 0.0000008,
"litellm_provider": "together_ai"
"litellm_provider": "together_ai",
"mode": "chat"
},
"together-ai-41.1b-80b": {
"input_cost_per_token": 0.0000009,
"output_cost_per_token": 0.0000009,
"litellm_provider": "together_ai"
"litellm_provider": "together_ai",
"mode": "chat"
},
"together-ai-81.1b-110b": {
"input_cost_per_token": 0.0000018,
"output_cost_per_token": 0.0000018,
"litellm_provider": "together_ai"
"litellm_provider": "together_ai",
"mode": "chat"
},
"together-ai-embedding-up-to-150m": {
"input_cost_per_token": 0.000000008,
"output_cost_per_token": 0.0,
"litellm_provider": "together_ai",
"mode": "embedding"
},
"together-ai-embedding-151m-to-350m": {
"input_cost_per_token": 0.000000016,
"output_cost_per_token": 0.0,
"litellm_provider": "together_ai",
"mode": "embedding"
},
"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
"input_cost_per_token": 0.0000006,
"output_cost_per_token": 0.0000006,
"litellm_provider": "together_ai",
"supports_function_calling": true,
"supports_parallel_function_calling": true
"supports_parallel_function_calling": true,
"mode": "chat"
},
"together_ai/mistralai/Mistral-7B-Instruct-v0.1": {
"litellm_provider": "together_ai",
"supports_function_calling": true,
"supports_parallel_function_calling": true
"supports_parallel_function_calling": true,
"mode": "chat"
},
"together_ai/togethercomputer/CodeLlama-34b-Instruct": {
"litellm_provider": "together_ai",
"supports_function_calling": true,
"supports_parallel_function_calling": true
"supports_parallel_function_calling": true,
"mode": "chat"
},
"ollama/codegemma": {
"max_tokens": 8192,