phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'BerriAI:main' into main

Browse source
This commit is contained in:
Raymond1415926 2024-06-06 10:12:20 -07:00 • committed by GitHub
commit f9368228c0
19 changed files with 237 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

62
README.md
View file

@ -225,37 +225,37 @@ curl 'http://0.0.0.0:4000/key/generate' \
## Supported Providers ([Docs](https://docs.litellm.ai/docs/providers)) ## Supported Providers ([Docs](https://docs.litellm.ai/docs/providers))
| Provider | [Completion](https://docs.litellm.ai/docs/#basic-usage) | [Streaming](https://docs.litellm.ai/docs/completion/stream#streaming-responses) | [Async Completion](https://docs.litellm.ai/docs/completion/stream#async-completion) | [Async Streaming](https://docs.litellm.ai/docs/completion/stream#async-streaming) | [Async Embedding](https://docs.litellm.ai/docs/embedding/supported_embedding) | [Async Image Generation](https://docs.litellm.ai/docs/image_generation) | | Provider | [Completion](https://docs.litellm.ai/docs/#basic-usage) | [Streaming](https://docs.litellm.ai/docs/completion/stream#streaming-responses) | [Async Completion](https://docs.litellm.ai/docs/completion/stream#async-completion) | [Async Streaming](https://docs.litellm.ai/docs/completion/stream#async-streaming) | [Async Embedding](https://docs.litellm.ai/docs/embedding/supported_embedding) | [Async Image Generation](https://docs.litellm.ai/docs/image_generation) |
| ----------------------------------------------------------------------------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------- | |-------------------------------------------------------------------------------------|---------------------------------------------------------|---------------------------------------------------------------------------------|-------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------|-------------------------------------------------------------------------|
| [openai](https://docs.litellm.ai/docs/providers/openai) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | [openai](https://docs.litellm.ai/docs/providers/openai) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| [azure](https://docs.litellm.ai/docs/providers/azure) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | [azure](https://docs.litellm.ai/docs/providers/azure) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| [aws - sagemaker](https://docs.litellm.ai/docs/providers/aws_sagemaker) | ✅ | ✅ | ✅ | ✅ | ✅ | | [aws - sagemaker](https://docs.litellm.ai/docs/providers/aws_sagemaker) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [aws - bedrock](https://docs.litellm.ai/docs/providers/bedrock) | ✅ | ✅ | ✅ | ✅ | ✅ | | [aws - bedrock](https://docs.litellm.ai/docs/providers/bedrock) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [google - vertex_ai](https://docs.litellm.ai/docs/providers/vertex) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | [google - vertex_ai](https://docs.litellm.ai/docs/providers/vertex) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| [google - palm](https://docs.litellm.ai/docs/providers/palm) | ✅ | ✅ | ✅ | ✅ | | [google - palm](https://docs.litellm.ai/docs/providers/palm) | ✅ | ✅ | ✅ | ✅ | | |
| [google AI Studio - gemini](https://docs.litellm.ai/docs/providers/gemini) | ✅ | ✅ | ✅ | ✅ | | | [google AI Studio - gemini](https://docs.litellm.ai/docs/providers/gemini) | ✅ | ✅ | ✅ | ✅ | | |
| [mistral ai api](https://docs.litellm.ai/docs/providers/mistral) | ✅ | ✅ | ✅ | ✅ | ✅ | | [mistral ai api](https://docs.litellm.ai/docs/providers/mistral) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [cloudflare AI Workers](https://docs.litellm.ai/docs/providers/cloudflare_workers) | ✅ | ✅ | ✅ | ✅ | | [cloudflare AI Workers](https://docs.litellm.ai/docs/providers/cloudflare_workers) | ✅ | ✅ | ✅ | ✅ | | |
| [cohere](https://docs.litellm.ai/docs/providers/cohere) | ✅ | ✅ | ✅ | ✅ | ✅ | | [cohere](https://docs.litellm.ai/docs/providers/cohere) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [anthropic](https://docs.litellm.ai/docs/providers/anthropic) | ✅ | ✅ | ✅ | ✅ | | [anthropic](https://docs.litellm.ai/docs/providers/anthropic) | ✅ | ✅ | ✅ | ✅ | | |
| [huggingface](https://docs.litellm.ai/docs/providers/huggingface) | ✅ | ✅ | ✅ | ✅ | ✅ | | [huggingface](https://docs.litellm.ai/docs/providers/huggingface) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [replicate](https://docs.litellm.ai/docs/providers/replicate) | ✅ | ✅ | ✅ | ✅ | | [replicate](https://docs.litellm.ai/docs/providers/replicate) | ✅ | ✅ | ✅ | ✅ | | |
| [together_ai](https://docs.litellm.ai/docs/providers/togetherai) | ✅ | ✅ | ✅ | ✅ | | [together_ai](https://docs.litellm.ai/docs/providers/togetherai) | ✅ | ✅ | ✅ | ✅ | | |
| [openrouter](https://docs.litellm.ai/docs/providers/openrouter) | ✅ | ✅ | ✅ | ✅ | | [openrouter](https://docs.litellm.ai/docs/providers/openrouter) | ✅ | ✅ | ✅ | ✅ | | |
| [ai21](https://docs.litellm.ai/docs/providers/ai21) | ✅ | ✅ | ✅ | ✅ | | [ai21](https://docs.litellm.ai/docs/providers/ai21) | ✅ | ✅ | ✅ | ✅ | | |
| [baseten](https://docs.litellm.ai/docs/providers/baseten) | ✅ | ✅ | ✅ | ✅ | | [baseten](https://docs.litellm.ai/docs/providers/baseten) | ✅ | ✅ | ✅ | ✅ | | |
| [vllm](https://docs.litellm.ai/docs/providers/vllm) | ✅ | ✅ | ✅ | ✅ | | [vllm](https://docs.litellm.ai/docs/providers/vllm) | ✅ | ✅ | ✅ | ✅ | | |
| [nlp_cloud](https://docs.litellm.ai/docs/providers/nlp_cloud) | ✅ | ✅ | ✅ | ✅ | | [nlp_cloud](https://docs.litellm.ai/docs/providers/nlp_cloud) | ✅ | ✅ | ✅ | ✅ | | |
| [aleph alpha](https://docs.litellm.ai/docs/providers/aleph_alpha) | ✅ | ✅ | ✅ | ✅ | | [aleph alpha](https://docs.litellm.ai/docs/providers/aleph_alpha) | ✅ | ✅ | ✅ | ✅ | | |
| [petals](https://docs.litellm.ai/docs/providers/petals) | ✅ | ✅ | ✅ | ✅ | | [petals](https://docs.litellm.ai/docs/providers/petals) | ✅ | ✅ | ✅ | ✅ | | |
| [ollama](https://docs.litellm.ai/docs/providers/ollama) | ✅ | ✅ | ✅ | ✅ | ✅ | | [ollama](https://docs.litellm.ai/docs/providers/ollama) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [deepinfra](https://docs.litellm.ai/docs/providers/deepinfra) | ✅ | ✅ | ✅ | ✅ | | [deepinfra](https://docs.litellm.ai/docs/providers/deepinfra) | ✅ | ✅ | ✅ | ✅ | | |
| [perplexity-ai](https://docs.litellm.ai/docs/providers/perplexity) | ✅ | ✅ | ✅ | ✅ | | [perplexity-ai](https://docs.litellm.ai/docs/providers/perplexity) | ✅ | ✅ | ✅ | ✅ | | |
| [Groq AI](https://docs.litellm.ai/docs/providers/groq) | ✅ | ✅ | ✅ | ✅ | | [Groq AI](https://docs.litellm.ai/docs/providers/groq) | ✅ | ✅ | ✅ | ✅ | | |
| [Deepseek](https://docs.litellm.ai/docs/providers/deepseek) | ✅ | ✅ | ✅ | ✅ | | [Deepseek](https://docs.litellm.ai/docs/providers/deepseek) | ✅ | ✅ | ✅ | ✅ | | |
| [anyscale](https://docs.litellm.ai/docs/providers/anyscale) | ✅ | ✅ | ✅ | ✅ | | [anyscale](https://docs.litellm.ai/docs/providers/anyscale) | ✅ | ✅ | ✅ | ✅ | | |
| [IBM - watsonx.ai](https://docs.litellm.ai/docs/providers/watsonx) | ✅ | ✅ | ✅ | ✅ | ✅ | [IBM - watsonx.ai](https://docs.litellm.ai/docs/providers/watsonx) | ✅ | ✅ | ✅ | ✅ | ✅ | |
| [voyage ai](https://docs.litellm.ai/docs/providers/voyage) | | | | | ✅ | | [voyage ai](https://docs.litellm.ai/docs/providers/voyage) | | | | | ✅ | |
| [xinference [Xorbits Inference]](https://docs.litellm.ai/docs/providers/xinference) | | | | | ✅ | | [xinference [Xorbits Inference]](https://docs.litellm.ai/docs/providers/xinference) | | | | | ✅ | |
[**Read the Docs**](https://docs.litellm.ai/docs/) [**Read the Docs**](https://docs.litellm.ai/docs/)

20
docs/my-website/docs/observability/langfuse_integration.md
View file

@ -144,6 +144,26 @@ print(response)
``` ```
You can also pass `metadata` as part of the request header with a `langfuse_*` prefix:
```shell
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'langfuse_trace_id: trace-id22' \
--header 'langfuse_trace_user_id: user-id2' \
--header 'langfuse_trace_metadata: {"key":"value"}' \
--data '{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
]
}'
```
### Trace & Generation Parameters ### Trace & Generation Parameters
#### Trace Specific Parameters #### Trace Specific Parameters

12
docs/my-website/docs/providers/groq.md
View file

@ -46,13 +46,13 @@ for chunk in response:
## Supported Models - ALL Groq Models Supported! ## Supported Models - ALL Groq Models Supported!
We support ALL Groq models, just set `groq/` as a prefix when sending completion requests We support ALL Groq models, just set `groq/` as a prefix when sending completion requests
| Model Name | Function Call | | Model Name | Function Call |
|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------| |--------------------|---------------------------------------------------------|
| llama3-8b-8192 | `completion(model="groq/llama3-8b-8192", messages)` | | llama3-8b-8192 | `completion(model="groq/llama3-8b-8192", messages)` |
| llama3-70b-8192 | `completion(model="groq/llama3-70b-8192", messages)` | | llama3-70b-8192 | `completion(model="groq/llama3-70b-8192", messages)` |
| llama2-70b-4096 | `completion(model="groq/llama2-70b-4096", messages)` | | llama2-70b-4096 | `completion(model="groq/llama2-70b-4096", messages)` |
| mixtral-8x7b-32768 | `completion(model="groq/mixtral-8x7b-32768", messages)` | | mixtral-8x7b-32768 | `completion(model="groq/mixtral-8x7b-32768", messages)` |
| gemma-7b-it | `completion(model="groq/gemma-7b-it", messages)` | | gemma-7b-it | `completion(model="groq/gemma-7b-it", messages)` |
## Groq - Tool / Function Calling Example ## Groq - Tool / Function Calling Example

68
docs/my-website/docs/providers/togetherai.md
View file

@ -26,52 +26,52 @@ Example TogetherAI Usage - Note: liteLLM supports all models deployed on Togethe
### Llama LLMs - Chat ### Llama LLMs - Chat
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |-----------------------------------|-------------------------------------------------------------------------|------------------------------------|
| togethercomputer/llama-2-70b-chat | `completion('together_ai/togethercomputer/llama-2-70b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/llama-2-70b-chat | `completion('together_ai/togethercomputer/llama-2-70b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
### Llama LLMs - Language / Instruct ### Llama LLMs - Language / Instruct
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |------------------------------------------|--------------------------------------------------------------------------------|------------------------------------|
| togethercomputer/llama-2-70b | `completion('together_ai/togethercomputer/llama-2-70b', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/llama-2-70b | `completion('together_ai/togethercomputer/llama-2-70b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| togethercomputer/LLaMA-2-7B-32K | `completion('together_ai/togethercomputer/LLaMA-2-7B-32K', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/LLaMA-2-7B-32K | `completion('together_ai/togethercomputer/LLaMA-2-7B-32K', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| togethercomputer/Llama-2-7B-32K-Instruct | `completion('together_ai/togethercomputer/Llama-2-7B-32K-Instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/Llama-2-7B-32K-Instruct | `completion('together_ai/togethercomputer/Llama-2-7B-32K-Instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| togethercomputer/llama-2-7b | `completion('together_ai/togethercomputer/llama-2-7b', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/llama-2-7b | `completion('together_ai/togethercomputer/llama-2-7b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
### Falcon LLMs ### Falcon LLMs
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |--------------------------------------|----------------------------------------------------------------------------|------------------------------------|
| togethercomputer/falcon-40b-instruct | `completion('together_ai/togethercomputer/falcon-40b-instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/falcon-40b-instruct | `completion('together_ai/togethercomputer/falcon-40b-instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| togethercomputer/falcon-7b-instruct | `completion('together_ai/togethercomputer/falcon-7b-instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/falcon-7b-instruct | `completion('together_ai/togethercomputer/falcon-7b-instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
### Alpaca LLMs ### Alpaca LLMs
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |----------------------------|------------------------------------------------------------------|------------------------------------|
| togethercomputer/alpaca-7b | `completion('together_ai/togethercomputer/alpaca-7b', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/alpaca-7b | `completion('together_ai/togethercomputer/alpaca-7b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
### Other Chat LLMs ### Other Chat LLMs
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |------------------------------|--------------------------------------------------------------------|------------------------------------|
| HuggingFaceH4/starchat-alpha | `completion('together_ai/HuggingFaceH4/starchat-alpha', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | HuggingFaceH4/starchat-alpha | `completion('together_ai/HuggingFaceH4/starchat-alpha', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
### Code LLMs ### Code LLMs
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |-----------------------------------------|-------------------------------------------------------------------------------|------------------------------------|
| togethercomputer/CodeLlama-34b | `completion('together_ai/togethercomputer/CodeLlama-34b', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/CodeLlama-34b | `completion('together_ai/togethercomputer/CodeLlama-34b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| togethercomputer/CodeLlama-34b-Instruct | `completion('together_ai/togethercomputer/CodeLlama-34b-Instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/CodeLlama-34b-Instruct | `completion('together_ai/togethercomputer/CodeLlama-34b-Instruct', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| togethercomputer/CodeLlama-34b-Python | `completion('together_ai/togethercomputer/CodeLlama-34b-Python', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | togethercomputer/CodeLlama-34b-Python | `completion('together_ai/togethercomputer/CodeLlama-34b-Python', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| defog/sqlcoder | `completion('together_ai/defog/sqlcoder', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | defog/sqlcoder | `completion('together_ai/defog/sqlcoder', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| NumbersStation/nsql-llama-2-7B | `completion('together_ai/NumbersStation/nsql-llama-2-7B', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | NumbersStation/nsql-llama-2-7B | `completion('together_ai/NumbersStation/nsql-llama-2-7B', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| WizardLM/WizardCoder-15B-V1.0 | `completion('together_ai/WizardLM/WizardCoder-15B-V1.0', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | WizardLM/WizardCoder-15B-V1.0 | `completion('together_ai/WizardLM/WizardCoder-15B-V1.0', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| WizardLM/WizardCoder-Python-34B-V1.0 | `completion('together_ai/WizardLM/WizardCoder-Python-34B-V1.0', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | WizardLM/WizardCoder-Python-34B-V1.0 | `completion('together_ai/WizardLM/WizardCoder-Python-34B-V1.0', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
### Language LLMs ### Language LLMs
| Model Name | Function Call | Required OS Variables | | Model Name | Function Call | Required OS Variables |
|-----------------------------------|------------------------------------------------------------------------|---------------------------------| |-------------------------------------|---------------------------------------------------------------------------|------------------------------------|
| NousResearch/Nous-Hermes-Llama2-13b | `completion('together_ai/NousResearch/Nous-Hermes-Llama2-13b', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | NousResearch/Nous-Hermes-Llama2-13b | `completion('together_ai/NousResearch/Nous-Hermes-Llama2-13b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| Austism/chronos-hermes-13b | `completion('together_ai/Austism/chronos-hermes-13b', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | Austism/chronos-hermes-13b | `completion('together_ai/Austism/chronos-hermes-13b', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| upstage/SOLAR-0-70b-16bit | `completion('together_ai/upstage/SOLAR-0-70b-16bit', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | upstage/SOLAR-0-70b-16bit | `completion('together_ai/upstage/SOLAR-0-70b-16bit', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
| WizardLM/WizardLM-70B-V1.0 | `completion('together_ai/WizardLM/WizardLM-70B-V1.0', messages)` | `os.environ['TOGETHERAI_API_KEY']` | | WizardLM/WizardLM-70B-V1.0 | `completion('together_ai/WizardLM/WizardLM-70B-V1.0', messages)` | `os.environ['TOGETHERAI_API_KEY']` |
## Prompt Templates ## Prompt Templates

16
docs/my-website/docs/providers/vllm.md
View file

@ -155,14 +155,14 @@ def default_pt(messages):
#### Models we already have Prompt Templates for #### Models we already have Prompt Templates for
| Model Name | Works for Models | Function Call | | Model Name | Works for Models | Function Call |
| -------- | -------- | -------- | |--------------------------------------|-----------------------------------|------------------------------------------------------------------------------------------------------------------|
| meta-llama/Llama-2-7b-chat | All meta-llama llama2 chat models| `completion(model='vllm/meta-llama/Llama-2-7b', messages=messages, api_base="your_api_endpoint")` | | meta-llama/Llama-2-7b-chat | All meta-llama llama2 chat models | `completion(model='vllm/meta-llama/Llama-2-7b', messages=messages, api_base="your_api_endpoint")` |
| tiiuae/falcon-7b-instruct | All falcon instruct models | `completion(model='vllm/tiiuae/falcon-7b-instruct', messages=messages, api_base="your_api_endpoint")` | | tiiuae/falcon-7b-instruct | All falcon instruct models | `completion(model='vllm/tiiuae/falcon-7b-instruct', messages=messages, api_base="your_api_endpoint")` |
| mosaicml/mpt-7b-chat | All mpt chat models | `completion(model='vllm/mosaicml/mpt-7b-chat', messages=messages, api_base="your_api_endpoint")` | | mosaicml/mpt-7b-chat | All mpt chat models | `completion(model='vllm/mosaicml/mpt-7b-chat', messages=messages, api_base="your_api_endpoint")` |
| codellama/CodeLlama-34b-Instruct-hf | All codellama instruct models | `completion(model='vllm/codellama/CodeLlama-34b-Instruct-hf', messages=messages, api_base="your_api_endpoint")` | | codellama/CodeLlama-34b-Instruct-hf | All codellama instruct models | `completion(model='vllm/codellama/CodeLlama-34b-Instruct-hf', messages=messages, api_base="your_api_endpoint")` |
| WizardLM/WizardCoder-Python-34B-V1.0 | All wizardcoder models | `completion(model='vllm/WizardLM/WizardCoder-Python-34B-V1.0', messages=messages, api_base="your_api_endpoint")` | | WizardLM/WizardCoder-Python-34B-V1.0 | All wizardcoder models | `completion(model='vllm/WizardLM/WizardCoder-Python-34B-V1.0', messages=messages, api_base="your_api_endpoint")` |
| Phind/Phind-CodeLlama-34B-v2 | All phind-codellama models | `completion(model='vllm/Phind/Phind-CodeLlama-34B-v2', messages=messages, api_base="your_api_endpoint")` | | Phind/Phind-CodeLlama-34B-v2 | All phind-codellama models | `completion(model='vllm/Phind/Phind-CodeLlama-34B-v2', messages=messages, api_base="your_api_endpoint")` |
#### Custom prompt templates #### Custom prompt templates

42
docs/my-website/docs/providers/watsonx.md
View file

@ -251,23 +251,23 @@ response = completion(
Here are some examples of models available in IBM watsonx.ai that you can use with LiteLLM: Here are some examples of models available in IBM watsonx.ai that you can use with LiteLLM:
| Mode Name | Command | | Mode Name | Command |
| ---------- | --------- | |------------------------------------|------------------------------------------------------------------------------------------|
| Flan T5 XXL | `completion(model=watsonx/google/flan-t5-xxl, messages=messages)` | | Flan T5 XXL | `completion(model=watsonx/google/flan-t5-xxl, messages=messages)` |
| Flan Ul2 | `completion(model=watsonx/google/flan-ul2, messages=messages)` | | Flan Ul2 | `completion(model=watsonx/google/flan-ul2, messages=messages)` |
| Mt0 XXL | `completion(model=watsonx/bigscience/mt0-xxl, messages=messages)` | | Mt0 XXL | `completion(model=watsonx/bigscience/mt0-xxl, messages=messages)` |
| Gpt Neox | `completion(model=watsonx/eleutherai/gpt-neox-20b, messages=messages)` | | Gpt Neox | `completion(model=watsonx/eleutherai/gpt-neox-20b, messages=messages)` |
| Mpt 7B Instruct2 | `completion(model=watsonx/ibm/mpt-7b-instruct2, messages=messages)` | | Mpt 7B Instruct2 | `completion(model=watsonx/ibm/mpt-7b-instruct2, messages=messages)` |
| Starcoder | `completion(model=watsonx/bigcode/starcoder, messages=messages)` | | Starcoder | `completion(model=watsonx/bigcode/starcoder, messages=messages)` |
| Llama 2 70B Chat | `completion(model=watsonx/meta-llama/llama-2-70b-chat, messages=messages)` | | Llama 2 70B Chat | `completion(model=watsonx/meta-llama/llama-2-70b-chat, messages=messages)` |
| Llama 2 13B Chat | `completion(model=watsonx/meta-llama/llama-2-13b-chat, messages=messages)` | | Llama 2 13B Chat | `completion(model=watsonx/meta-llama/llama-2-13b-chat, messages=messages)` |
| Granite 13B Instruct | `completion(model=watsonx/ibm/granite-13b-instruct-v1, messages=messages)` | | Granite 13B Instruct | `completion(model=watsonx/ibm/granite-13b-instruct-v1, messages=messages)` |
| Granite 13B Chat | `completion(model=watsonx/ibm/granite-13b-chat-v1, messages=messages)` | | Granite 13B Chat | `completion(model=watsonx/ibm/granite-13b-chat-v1, messages=messages)` |
| Flan T5 XL | `completion(model=watsonx/google/flan-t5-xl, messages=messages)` | | Flan T5 XL | `completion(model=watsonx/google/flan-t5-xl, messages=messages)` |
| Granite 13B Chat V2 | `completion(model=watsonx/ibm/granite-13b-chat-v2, messages=messages)` | | Granite 13B Chat V2 | `completion(model=watsonx/ibm/granite-13b-chat-v2, messages=messages)` |
| Granite 13B Instruct V2 | `completion(model=watsonx/ibm/granite-13b-instruct-v2, messages=messages)` | | Granite 13B Instruct V2 | `completion(model=watsonx/ibm/granite-13b-instruct-v2, messages=messages)` |
| Elyza Japanese Llama 2 7B Instruct | `completion(model=watsonx/elyza/elyza-japanese-llama-2-7b-instruct, messages=messages)` | | Elyza Japanese Llama 2 7B Instruct | `completion(model=watsonx/elyza/elyza-japanese-llama-2-7b-instruct, messages=messages)` |
| Mixtral 8X7B Instruct V01 Q | `completion(model=watsonx/ibm-mistralai/mixtral-8x7b-instruct-v01-q, messages=messages)` | | Mixtral 8X7B Instruct V01 Q | `completion(model=watsonx/ibm-mistralai/mixtral-8x7b-instruct-v01-q, messages=messages)` |
For a list of all available models in watsonx.ai, see [here](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx&locale=en&audience=wdp). For a list of all available models in watsonx.ai, see [here](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx&locale=en&audience=wdp).
@ -275,10 +275,10 @@ For a list of all available models in watsonx.ai, see [here](https://dataplatfor
## Supported IBM watsonx.ai Embedding Models ## Supported IBM watsonx.ai Embedding Models
| Model Name | Function Call | | Model Name | Function Call |
|----------------------|---------------------------------------------| |------------|------------------------------------------------------------------------|
| Slate 30m | `embedding(model="watsonx/ibm/slate-30m-english-rtrvr", input=input)` | | Slate 30m | `embedding(model="watsonx/ibm/slate-30m-english-rtrvr", input=input)` |
| Slate 125m | `embedding(model="watsonx/ibm/slate-125m-english-rtrvr", input=input)` | | Slate 125m | `embedding(model="watsonx/ibm/slate-125m-english-rtrvr", input=input)` |
For a list of all available embedding models in watsonx.ai, see [here](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models-embed.html?context=wx). For a list of all available embedding models in watsonx.ai, see [here](https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models-embed.html?context=wx).

40
docs/my-website/docs/providers/xinference.md
View file

@ -37,26 +37,26 @@ print(response)
## Supported Models ## Supported Models
All models listed here https://inference.readthedocs.io/en/latest/models/builtin/embedding/index.html are supported All models listed here https://inference.readthedocs.io/en/latest/models/builtin/embedding/index.html are supported
| Model Name | Function Call | | Model Name | Function Call |
|------------------------------|--------------------------------------------------------| |-----------------------------|--------------------------------------------------------------------|
| bge-base-en | `embedding(model="xinference/bge-base-en", input)` | | bge-base-en | `embedding(model="xinference/bge-base-en", input)` |
| bge-base-en-v1.5 | `embedding(model="xinference/bge-base-en-v1.5", input)` | | bge-base-en-v1.5 | `embedding(model="xinference/bge-base-en-v1.5", input)` |
| bge-base-zh | `embedding(model="xinference/bge-base-zh", input)` | | bge-base-zh | `embedding(model="xinference/bge-base-zh", input)` |
| bge-base-zh-v1.5 | `embedding(model="xinference/bge-base-zh-v1.5", input)` | | bge-base-zh-v1.5 | `embedding(model="xinference/bge-base-zh-v1.5", input)` |
| bge-large-en | `embedding(model="xinference/bge-large-en", input)` | | bge-large-en | `embedding(model="xinference/bge-large-en", input)` |
| bge-large-en-v1.5 | `embedding(model="xinference/bge-large-en-v1.5", input)` | | bge-large-en-v1.5 | `embedding(model="xinference/bge-large-en-v1.5", input)` |
| bge-large-zh | `embedding(model="xinference/bge-large-zh", input)` | | bge-large-zh | `embedding(model="xinference/bge-large-zh", input)` |
| bge-large-zh-noinstruct | `embedding(model="xinference/bge-large-zh-noinstruct", input)` | | bge-large-zh-noinstruct | `embedding(model="xinference/bge-large-zh-noinstruct", input)` |
| bge-large-zh-v1.5 | `embedding(model="xinference/bge-large-zh-v1.5", input)` | | bge-large-zh-v1.5 | `embedding(model="xinference/bge-large-zh-v1.5", input)` |
| bge-small-en-v1.5 | `embedding(model="xinference/bge-small-en-v1.5", input)` | | bge-small-en-v1.5 | `embedding(model="xinference/bge-small-en-v1.5", input)` |
| bge-small-zh | `embedding(model="xinference/bge-small-zh", input)` | | bge-small-zh | `embedding(model="xinference/bge-small-zh", input)` |
| bge-small-zh-v1.5 | `embedding(model="xinference/bge-small-zh-v1.5", input)` | | bge-small-zh-v1.5 | `embedding(model="xinference/bge-small-zh-v1.5", input)` |
| e5-large-v2 | `embedding(model="xinference/e5-large-v2", input)` | | e5-large-v2 | `embedding(model="xinference/e5-large-v2", input)` |
| gte-base | `embedding(model="xinference/gte-base", input)` | | gte-base | `embedding(model="xinference/gte-base", input)` |
| gte-large | `embedding(model="xinference/gte-large", input)` | | gte-large | `embedding(model="xinference/gte-large", input)` |
| jina-embeddings-v2-base-en | `embedding(model="xinference/jina-embeddings-v2-base-en", input)` | | jina-embeddings-v2-base-en | `embedding(model="xinference/jina-embeddings-v2-base-en", input)` |
| jina-embeddings-v2-small-en | `embedding(model="xinference/jina-embeddings-v2-small-en", input)` | | jina-embeddings-v2-small-en | `embedding(model="xinference/jina-embeddings-v2-small-en", input)` |
| multilingual-e5-large | `embedding(model="xinference/multilingual-e5-large", input)` | | multilingual-e5-large | `embedding(model="xinference/multilingual-e5-large", input)` |

2
docs/my-website/docs/proxy/deploy.md
View file

@ -260,7 +260,7 @@ Requirements:
<TabItem value="docker-deploy" label="Dockerfile"> <TabItem value="docker-deploy" label="Dockerfile">
We maintain a [seperate Dockerfile](https://github.com/BerriAI/litellm/pkgs/container/litellm-database) for reducing build time when running LiteLLM proxy with a connected Postgres Database We maintain a [separate Dockerfile](https://github.com/BerriAI/litellm/pkgs/container/litellm-database) for reducing build time when running LiteLLM proxy with a connected Postgres Database
```shell ```shell
docker pull ghcr.io/berriai/litellm-database:main-latest docker pull ghcr.io/berriai/litellm-database:main-latest

2
docs/my-website/docs/proxy/enterprise.md
View file

@ -459,7 +459,7 @@ Step 1 Set a `LAKERA_API_KEY` in your env
LAKERA_API_KEY="7a91a1a6059da*******" LAKERA_API_KEY="7a91a1a6059da*******"
``` ```
Step 2. Add `lakera_prompt_injection` to your calbacks Step 2. Add `lakera_prompt_injection` to your callbacks
```yaml ```yaml
litellm_settings: litellm_settings:

4
docs/my-website/docs/proxy/logging.md
View file

@ -41,7 +41,9 @@ litellm_settings:
**Step 3**: Set required env variables for logging to langfuse **Step 3**: Set required env variables for logging to langfuse
```shell ```shell
export LANGFUSE_PUBLIC_KEY="pk_kk" export LANGFUSE_PUBLIC_KEY="pk_kk"
export LANGFUSE_SECRET_KEY="sk_ss export LANGFUSE_SECRET_KEY="sk_ss"
# Optional, defaults to https://cloud.langfuse.com
export LANGFUSE_HOST="https://xxx.langfuse.com"
``` ```
**Step 4**: Start the proxy, make a test request **Step 4**: Start the proxy, make a test request

4
docs/my-website/docs/tutorials/finetuned_chat_gpt.md
View file

@ -1,8 +1,8 @@
# Using Fine-Tuned gpt-3.5-turbo # Using Fine-Tuned gpt-3.5-turbo
LiteLLM allows you to call `completion` with your fine-tuned gpt-3.5-turbo models LiteLLM allows you to call `completion` with your fine-tuned gpt-3.5-turbo models
If you're trying to create your custom finetuned gpt-3.5-turbo model following along on this tutorial: https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset If you're trying to create your custom fine-tuned gpt-3.5-turbo model following along on this tutorial: https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset
Once you've created your fine tuned model, you can call it with `litellm.completion()` Once you've created your fine-tuned model, you can call it with `litellm.completion()`
## Usage ## Usage
```python ```python

38
litellm/integrations/langfuse.py
View file

@ -69,6 +69,43 @@ class LangFuseLogger:
else: else:
self.upstream_langfuse = None self.upstream_langfuse = None
@staticmethod
def add_metadata_from_header(litellm_params: dict, metadata: dict) -> dict:
"""
Adds metadata from proxy request headers to Langfuse logging if keys start with "langfuse_"
and overwrites litellm_params.metadata if already included.
For example if you want to append your trace to an existing `trace_id` via header, send
`headers: { ..., langfuse_existing_trace_id: your-existing-trace-id }` via proxy request.
"""
if litellm_params is None:
return metadata
if litellm_params.get("proxy_server_request") is None:
return metadata
if metadata is None:
metadata = {}
proxy_headers = (
litellm_params.get("proxy_server_request", {}).get("headers", {}) or {}
)
for metadata_param_key in proxy_headers:
if metadata_param_key.startswith("langfuse_"):
trace_param_key = metadata_param_key.replace("langfuse_", "", 1)
if trace_param_key in metadata:
verbose_logger.warning(
f"Overwriting Langfuse `{trace_param_key}` from request header"
)
else:
verbose_logger.debug(
f"Found Langfuse `{trace_param_key}` in request header"
)
metadata[trace_param_key] = proxy_headers.get(metadata_param_key)
return metadata
# def log_error(kwargs, response_obj, start_time, end_time): # def log_error(kwargs, response_obj, start_time, end_time):
# generation = trace.generation( # generation = trace.generation(
# level ="ERROR" # can be any of DEBUG, DEFAULT, WARNING or ERROR # level ="ERROR" # can be any of DEBUG, DEFAULT, WARNING or ERROR
@ -97,6 +134,7 @@ class LangFuseLogger:
metadata = ( metadata = (
litellm_params.get("metadata", {}) or {} litellm_params.get("metadata", {}) or {}
) # if litellm_params['metadata'] == None ) # if litellm_params['metadata'] == None
metadata = self.add_metadata_from_header(litellm_params, metadata)
optional_params = copy.deepcopy(kwargs.get("optional_params", {})) optional_params = copy.deepcopy(kwargs.get("optional_params", {}))
prompt = {"messages": kwargs.get("messages")} prompt = {"messages": kwargs.get("messages")}

15
litellm/llms/ollama.py
View file

@ -2,8 +2,9 @@ from itertools import chain
import requests, types, time # type: ignore import requests, types, time # type: ignore
import json, uuid import json, uuid
import traceback import traceback
from typing import Optional from typing import Optional, List
import litellm import litellm
from litellm.types.utils import ProviderField
import httpx, aiohttp, asyncio # type: ignore import httpx, aiohttp, asyncio # type: ignore
from .prompt_templates.factory import prompt_factory, custom_prompt from .prompt_templates.factory import prompt_factory, custom_prompt
@ -124,6 +125,18 @@ class OllamaConfig:
) )
and v is not None and v is not None
} }
def get_required_params(self) -> List[ProviderField]:
"""For a given provider, return it's required fields with a description"""
return [
ProviderField(
field_name="base_url",
field_type="string",
field_description="Your Ollama API Base",
field_value="http://10.10.11.249:11434",
)
]
def get_supported_openai_params( def get_supported_openai_params(
self, self,
): ):

4
litellm/llms/prompt_templates/factory.py
View file

@ -833,7 +833,7 @@ def anthropic_messages_pt_xml(messages: list):
) # either string or none ) # either string or none
if messages[msg_i].get( if messages[msg_i].get(
"tool_calls", [] "tool_calls", []
): # support assistant tool invoke convertion ): # support assistant tool invoke conversion
assistant_text += convert_to_anthropic_tool_invoke_xml( # type: ignore assistant_text += convert_to_anthropic_tool_invoke_xml( # type: ignore
messages[msg_i]["tool_calls"] messages[msg_i]["tool_calls"]
) )
@ -1224,7 +1224,7 @@ def anthropic_messages_pt(messages: list):
if messages[msg_i].get( if messages[msg_i].get(
"tool_calls", [] "tool_calls", []
): # support assistant tool invoke convertion ): # support assistant tool invoke conversion
assistant_content.extend( assistant_content.extend(
convert_to_anthropic_tool_invoke(messages[msg_i]["tool_calls"]) convert_to_anthropic_tool_invoke(messages[msg_i]["tool_calls"])
) )

25
litellm/llms/vertex_ai.py
View file

@ -297,24 +297,29 @@ def _convert_gemini_role(role: str) -> Literal["user", "model"]:
def _process_gemini_image(image_url: str) -> PartType: def _process_gemini_image(image_url: str) -> PartType:
try: try:
if "gs://" in image_url: if ".mp4" in image_url and "gs://" in image_url:
# Case 1: Images with Cloud Storage URIs # Case 1: Videos with Cloud Storage URIs
part_mime = "video/mp4"
_file_data = FileDataType(mime_type=part_mime, file_uri=image_url)
return PartType(file_data=_file_data)
elif ".pdf" in image_url and "gs://" in image_url:
# Case 2: PDF's with Cloud Storage URIs
part_mime = "application/pdf"
_file_data = FileDataType(mime_type=part_mime, file_uri=image_url)
return PartType(file_data=_file_data)
elif "gs://" in image_url:
# Case 3: Images with Cloud Storage URIs
# The supported MIME types for images include image/png and image/jpeg. # The supported MIME types for images include image/png and image/jpeg.
part_mime = "image/png" if "png" in image_url else "image/jpeg" part_mime = "image/png" if "png" in image_url else "image/jpeg"
_file_data = FileDataType(mime_type=part_mime, file_uri=image_url) _file_data = FileDataType(mime_type=part_mime, file_uri=image_url)
return PartType(file_data=_file_data) return PartType(file_data=_file_data)
elif "https:/" in image_url: elif "https:/" in image_url:
# Case 2: Images with direct links # Case 4: Images with direct links
image = _load_image_from_url(image_url) image = _load_image_from_url(image_url)
_blob = BlobType(data=image.data, mime_type=image._mime_type) _blob = BlobType(data=image.data, mime_type=image._mime_type)
return PartType(inline_data=_blob) return PartType(inline_data=_blob)
elif ".mp4" in image_url and "gs://" in image_url:
# Case 3: Videos with Cloud Storage URIs
part_mime = "video/mp4"
_file_data = FileDataType(mime_type=part_mime, file_uri=image_url)
return PartType(file_data=_file_data)
elif "base64" in image_url: elif "base64" in image_url:
# Case 4: Images with base64 encoding # Case 5: Images with base64 encoding
import base64, re import base64, re
# base 64 is passed as data:image/jpeg;base64,<base-64-encoded-image> # base 64 is passed as data:image/jpeg;base64,<base-64-encoded-image>
@ -390,7 +395,7 @@ def _gemini_convert_messages_with_history(messages: list) -> List[ContentType]:
assistant_content.extend(_parts) assistant_content.extend(_parts)
elif messages[msg_i].get( elif messages[msg_i].get(
"tool_calls", [] "tool_calls", []
): # support assistant tool invoke convertion ): # support assistant tool invoke conversion
assistant_content.extend( assistant_content.extend(
convert_to_gemini_tool_call_invoke(messages[msg_i]["tool_calls"]) convert_to_gemini_tool_call_invoke(messages[msg_i]["tool_calls"])
) )

4
litellm/utils.py
View file

@ -7352,6 +7352,10 @@ def get_provider_fields(custom_llm_provider: str) -> List[ProviderField]:
if custom_llm_provider == "databricks": if custom_llm_provider == "databricks":
return litellm.DatabricksConfig().get_required_params() return litellm.DatabricksConfig().get_required_params()
elif custom_llm_provider == "ollama":
return litellm.OllamaConfig().get_required_params()
else: else:
return [] return []

14
poetry.lock generated
View file

@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand. # This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
[[package]] [[package]]
name = "aiohttp" name = "aiohttp"
@ -2114,6 +2114,7 @@ files = [
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
{file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
{file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"}, {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
{file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"}, {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"}, {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@ -2121,8 +2122,15 @@ files = [
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
{file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
{file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"}, {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
{file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
{file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
{file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
{file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
{file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"}, {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@ -2139,6 +2147,7 @@ files = [
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
{file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
{file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"}, {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
{file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"}, {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"}, {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@ -2146,6 +2155,7 @@ files = [
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
{file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
{file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"}, {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
{file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"}, {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
{file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"}, {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@ -3140,4 +3150,4 @@ proxy = ["PyJWT", "apscheduler", "backoff", "cryptography", "fastapi", "fastapi-
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = ">=3.8.1,<4.0, !=3.9.7" python-versions = ">=3.8.1,<4.0, !=3.9.7"
content-hash = "a54d969a1a707413e7cd3ce869d14ef73dd41bb9d36ebf0fb878d9e929bc15b3" content-hash = "6a37992b63b11d254f5f40687bd96898b1d9515728f663f30dcc81c4ef8df7b7"

3
pyproject.toml
View file

@ -62,7 +62,8 @@ extra_proxy = [
"azure-identity", "azure-identity",
"azure-keyvault-secrets", "azure-keyvault-secrets",
"google-cloud-kms", "google-cloud-kms",
"resend" "resend",
"pynacl"
] ]
[tool.poetry.scripts] [tool.poetry.scripts]

3
ui/litellm-dashboard/src/components/model_dashboard.tsx
View file

@ -145,6 +145,7 @@ enum Providers {
OpenAI_Compatible = "OpenAI-Compatible Endpoints (Groq, Together AI, Mistral AI, etc.)", OpenAI_Compatible = "OpenAI-Compatible Endpoints (Groq, Together AI, Mistral AI, etc.)",
Vertex_AI = "Vertex AI (Anthropic, Gemini, etc.)", Vertex_AI = "Vertex AI (Anthropic, Gemini, etc.)",
Databricks = "Databricks", Databricks = "Databricks",
Ollama = "Ollama",
} }
const provider_map: Record<string, string> = { const provider_map: Record<string, string> = {
@ -156,6 +157,7 @@ const provider_map: Record<string, string> = {
OpenAI_Compatible: "openai", OpenAI_Compatible: "openai",
Vertex_AI: "vertex_ai", Vertex_AI: "vertex_ai",
Databricks: "databricks", Databricks: "databricks",
Ollama: "ollama",
}; };
const retry_policy_map: Record<string, string> = { const retry_policy_map: Record<string, string> = {
@ -1747,6 +1749,7 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
)} )}
{selectedProvider != Providers.Bedrock && {selectedProvider != Providers.Bedrock &&
selectedProvider != Providers.Vertex_AI && selectedProvider != Providers.Vertex_AI &&
selectedProvider != Providers.Ollama &&
(dynamicProviderForm === undefined || (dynamicProviderForm === undefined ||
dynamicProviderForm.fields.length == 0) && ( dynamicProviderForm.fields.length == 0) && (
<Form.Item <Form.Item