diff --git a/docs/my-website/docs/completion/supported.md b/docs/my-website/docs/completion/supported.md deleted file mode 100644 index 777374fcb1..0000000000 --- a/docs/my-website/docs/completion/supported.md +++ /dev/null @@ -1,221 +0,0 @@ -# Supported Providers + Models - -## API Keys -liteLLM reads key naming, all keys should be named in the following format: -`_API_KEY` for example -* `OPENAI_API_KEY` Provider = OpenAI -* `TOGETHERAI_API_KEY` Provider = TogetherAI -* `HUGGINGFACE_API_KEY` Provider = HuggingFace - - -### OpenAI Chat Completion Models - -| Model Name | Function Call | Required OS Variables | -|------------------|----------------------------------------|--------------------------------------| -| gpt-3.5-turbo | `completion('gpt-3.5-turbo', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-3.5-turbo-0301 | `completion('gpt-3.5-turbo-0301', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-3.5-turbo-0613 | `completion('gpt-3.5-turbo-0613', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-3.5-turbo-16k | `completion('gpt-3.5-turbo-16k', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-3.5-turbo-16k-0613 | `completion('gpt-3.5-turbo-16k-0613', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-4 | `completion('gpt-4', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-4-0314 | `completion('gpt-4-0314', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-4-0613 | `completion('gpt-4-0613', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-4-32k | `completion('gpt-4-32k', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-4-32k-0314 | `completion('gpt-4-32k-0314', messages)` | `os.environ['OPENAI_API_KEY']` | -| gpt-4-32k-0613 | `completion('gpt-4-32k-0613', messages)` | `os.environ['OPENAI_API_KEY']` | - -These also support the `OPENAI_API_BASE` environment variable, which can be used to specify a custom API endpoint. - -### Azure OpenAI Chat Completion Models - -| Model Name | Function Call | Required OS Variables | -|------------------|-----------------------------------------|-------------------------------------------| -| gpt-3.5-turbo | `completion('gpt-3.5-turbo', messages, custom_llm_provider="azure")` | `os.environ['AZURE_API_KEY']`,`os.environ['AZURE_API_BASE']`,`os.environ['AZURE_API_VERSION']` | -| gpt-4 | `completion('gpt-4', messages, custom_llm_provider="azure")` | `os.environ['AZURE_API_KEY']`,`os.environ['AZURE_API_BASE']`,`os.environ['AZURE_API_VERSION']` | - -### OpenAI Text Completion Models - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|--------------------------------------| -| text-davinci-003 | `completion('text-davinci-003', messages)` | `os.environ['OPENAI_API_KEY']` | -| ada-001 | `completion('ada-001', messages)` | `os.environ['OPENAI_API_KEY']` | -| curie-001 | `completion('curie-001', messages)` | `os.environ['OPENAI_API_KEY']` | -| babbage-001 | `completion('babbage-001', messages)` | `os.environ['OPENAI_API_KEY']` | -| babbage-002 | `completion('ada-001', messages)` | `os.environ['OPENAI_API_KEY']` | -| davinci-002 | `completion('davinci-002', messages)` | `os.environ['OPENAI_API_KEY']` | - - -### Google VertexAI Models -Sample notebook for calling VertexAI models: https://github.com/BerriAI/litellm/blob/main/cookbook/liteLLM_VertextAI_Example.ipynb - -All calls using Vertex AI require the following parameters: -* Your Project ID -`litellm.vertex_project` = "hardy-device-38811" Your Project ID -* Your Project Location -`litellm.vertex_location` = "us-central1" - -Authentication: -VertexAI uses Application Default Credentials, see https://cloud.google.com/docs/authentication/external/set-up-adc for more information on setting this up - -VertexAI requires you to set `application_default_credentials.json`, this can be set by running `gcloud auth application-default login` in your terminal - -| Model Name | Function Call | -|------------------|----------------------------------------------------------| -| chat-bison | `completion('chat-bison', messages)` | -| chat-bison@001 | `completion('chat-bison@001', messages)` | -| text-bison | `completion('text-bison', messages)` | -| text-bison@001 | `completion('text-bison@001', messages)` | - -### Anthropic Models - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|--------------------------------------| -| claude-instant-1 | `completion('claude-instant-1', messages)` | `os.environ['ANTHROPIC_API_KEY']` | -| claude-instant-1.2 | `completion('claude-instant-1.2', messages)` | `os.environ['ANTHROPIC_API_KEY']` | -| claude-2 | `completion('claude-2', messages)` | `os.environ['ANTHROPIC_API_KEY']` | - -### Hugging Face Inference API - -All [`text2text-generation`](https://huggingface.co/models?library=transformers&pipeline_tag=text2text-generation&sort=downloads) and [`text-generation`](https://huggingface.co/models?library=transformers&pipeline_tag=text-generation&sort=downloads) models are supported by liteLLM. You can use any text model from Hugging Face with the following steps: - -* Copy the `model repo` URL from Hugging Face and set it as the `model` parameter in the completion call. -* Set `hugging_face` parameter to `True`. -* Make sure to set the hugging face API key - -Here are some examples of supported models: -**Note that the models mentioned in the table are examples, and you can use any text model available on Hugging Face by following the steps above.** - -| Model Name | Function Call | Required OS Variables | -|------------------|-------------------------------------------------------------------------------------|--------------------------------------| -| [stabilityai/stablecode-completion-alpha-3b-4k](https://huggingface.co/stabilityai/stablecode-completion-alpha-3b-4k) | `completion(model="stabilityai/stablecode-completion-alpha-3b-4k", messages=messages, custom_llm_provider="huggingface")` | `os.environ['HUGGINGFACE_API_KEY']` | -| [bigcode/starcoder](https://huggingface.co/bigcode/starcoder) | `completion(model="bigcode/starcoder", messages=messages, custom_llm_provider="huggingface")` | `os.environ['HUGGINGFACE_API_KEY']` | -| [google/flan-t5-xxl](https://huggingface.co/google/flan-t5-xxl) | `completion(model="google/flan-t5-xxl", messages=messages, custom_llm_provider="huggingface")` | `os.environ['HUGGINGFACE_API_KEY']` | -| [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) | `completion(model="google/flan-t5-large", messages=messages, custom_llm_provider="huggingface")` | `os.environ['HUGGINGFACE_API_KEY']` | - -### Replicate Models -liteLLM supports all replicate LLMs. For replicate models ensure to add a `replicate` prefix to the `model` arg. liteLLM detects it using this arg. -Below are examples on how to call replicate LLMs using liteLLM - -Model Name | Function Call | Required OS Variables | ------------------------------|----------------------------------------------------------------|--------------------------------------| - replicate/llama-2-70b-chat | `completion('replicate/replicate/llama-2-70b-chat', messages)` | `os.environ['REPLICATE_API_KEY']` | - a16z-infra/llama-2-13b-chat| `completion('replicate/a16z-infra/llama-2-13b-chat', messages)`| `os.environ['REPLICATE_API_KEY']` | - joehoover/instructblip-vicuna13b | `completion('replicate/joehoover/instructblip-vicuna13b', messages)` | `os.environ['REPLICATE_API_KEY']` | - replicate/dolly-v2-12b | `completion('replicate/replicate/dolly-v2-12b', messages)` | `os.environ['REPLICATE_API_KEY']` | - a16z-infra/llama-2-7b-chat | `completion('replicate/a16z-infra/llama-2-7b-chat', messages)` | `os.environ['REPLICATE_API_KEY']` | - replicate/vicuna-13b | `completion('replicate/replicate/vicuna-13b', messages)` | `os.environ['REPLICATE_API_KEY']` | - daanelson/flan-t5-large | `completion('replicate/daanelson/flan-t5-large', messages)` | `os.environ['REPLICATE_API_KEY']` | - replit/replit-code-v1-3b | `completion('replicate/replit/replit-code-v1-3b', messages)` | `os.environ['REPLICATE_API_KEY']` | - -### AI21 Models - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|--------------------------------------| -| j2-light | `completion('j2-light', messages)` | `os.environ['AI21_API_KEY']` | -| j2-mid | `completion('j2-mid', messages)` | `os.environ['AI21_API_KEY']` | -| j2-ultra | `completion('j2-ultra', messages)` | `os.environ['AI21_API_KEY']` | - -### Cohere Models - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|--------------------------------------| -| command-nightly | `completion('command-nightly', messages)` | `os.environ['COHERE_API_KEY']` | - -### Together AI Models -liteLLM supports `non-streaming` and `streaming` requests to all models on https://api.together.xyz/ - -Example TogetherAI Usage - Note: liteLLM supports all models deployed on TogetherAI - -| Model Name | Function Call | Required OS Variables | -|-----------------------------------|------------------------------------------------------------------------|---------------------------------| -| togethercomputer/llama-2-70b-chat | `completion('togethercomputer/llama-2-70b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` | -| togethercomputer/LLaMA-2-13b-chat | `completion('togethercomputer/LLaMA-2-13b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` | -| togethercomputer/code-and-talk-v1 | `completion('togethercomputer/code-and-talk-v1', messages)` | `os.environ['TOGETHERAI_API_KEY']` | -| togethercomputer/creative-v1 | `completion('togethercomputer/creative-v1', messages)` | `os.environ['TOGETHERAI_API_KEY']` | -| togethercomputer/yourmodel | `completion('togethercomputer/yourmodel', messages)` | `os.environ['TOGETHERAI_API_KEY']` | - -### AWS Sagemaker Models -https://aws.amazon.com/sagemaker/ Use liteLLM to easily call custom LLMs on Sagemaker - -#### Requirements using Sagemaker with LiteLLM - -* `pip install boto3` -* Set the following AWS credentials as .env variables (Sagemaker auth: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html) - * AWS_ACCESS_KEY_ID - * AWS_SECRET_ACCESS_KEY - * AWS_REGION_NAME - - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|------------------------------------| -| Llama2 7B | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b, messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | -| Custom LLM Endpoint | `completion(model='sagemaker/your-endpoint, messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | - -### Aleph Alpha Models -https://www.aleph-alpha.com/ - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|------------------------------------| -| luminous-base | `completion(model='luminous-base', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | -| luminous-extended | `completion(model='luminous-extended', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | -| luminous-supreme | `completion(model='luminous-supreme', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | -| luminous-base-control | `completion(model='luminous-base-control', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | -| luminous-extended-control | `completion(model='luminous-extended-control', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | -| luminous-supreme-control | `completion(model='luminous-supreme-control', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | - - - -### Baseten Models -Baseten provides infrastructure to deploy and serve ML models https://www.baseten.co/. Use liteLLM to easily call models deployed on Baseten. - -Example Baseten Usage - Note: liteLLM supports all models deployed on Baseten - -Usage: Pass `model=baseten/` - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|------------------------------------| -| Falcon 7B | `completion(model='baseten/qvv0xeq', messages=messages)` | `os.environ['BASETEN_API_KEY']` | -| Wizard LM | `completion(model='baseten/q841o8w', messages=messages)` | `os.environ['BASETEN_API_KEY']` | -| MPT 7B Base | `completion(model='baseten/31dxrj3', messages=messages)` | `os.environ['BASETEN_API_KEY']` | - - -### OpenRouter Completion Models - -All the text models from [OpenRouter](https://openrouter.ai/docs) are supported by liteLLM. - -| Model Name | Function Call | Required OS Variables | -|------------------|--------------------------------------------|--------------------------------------| -| openai/gpt-3.5-turbo | `completion('openai/gpt-3.5-turbo', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| openai/gpt-3.5-turbo-16k | `completion('openai/gpt-3.5-turbo-16k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| openai/gpt-4 | `completion('openai/gpt-4', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| openai/gpt-4-32k | `completion('openai/gpt-4-32k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| anthropic/claude-2 | `completion('anthropic/claude-2', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| anthropic/claude-instant-v1 | `completion('anthropic/claude-instant-v1', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| google/palm-2-chat-bison | `completion('google/palm-2-chat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| google/palm-2-codechat-bison | `completion('google/palm-2-codechat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| meta-llama/llama-2-13b-chat | `completion('meta-llama/llama-2-13b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | -| meta-llama/llama-2-70b-chat | `completion('meta-llama/llama-2-70b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | - -### Petals Models -Supported models on https://chat.petals.dev/ - -| Model Name | Function Call | Required OS Variables | -|----------------------|------------------------------------------------------------------------|--------------------------------| -| stabilityai/StableBeluga2 | `completion(model='stabilityai/StableBeluga2', messages, custom_llm_provider="petals")` | No API Key required | -| enoch/llama-65b-hf | `completion(model='enoch/llama-65b-hf', messages, custom_llm_provider="petals")` | No API Key required | -| bigscience/bloomz | `completion(model='bigscience/bloomz', messages, custom_llm_provider="petals")` | No API Key required | - -### Ollama Models -Ollama supported models: https://github.com/jmorganca/ollama - -| Model Name | Function Call | Required OS Variables | -|----------------------|-----------------------------------------------------------------------------------|--------------------------------| -| Llama2 7B | `completion(model='llama2', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Llama2 13B | `completion(model='llama2:13b', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Llama2 70B | `completion(model='llama2:70b', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Llama2 Uncensored | `completion(model='llama2-uncensored', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Orca Mini | `completion(model='orca-mini', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Vicuna | `completion(model='vicuna', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Nous-Hermes | `completion(model='nous-hermes', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Nous-Hermes 13B | `completion(model='nous-hermes:13b', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | -| Wizard Vicuna Uncensored | `completion(model='wizard-vicuna', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | diff --git a/docs/my-website/docs/providers/ai21.md b/docs/my-website/docs/providers/ai21.md new file mode 100644 index 0000000000..b0623b551a --- /dev/null +++ b/docs/my-website/docs/providers/ai21.md @@ -0,0 +1,19 @@ +# AI21 + +LiteLLM supports j2-light, j2-mid and j2-ultra from [AI21](https://www.ai21.com/studio/pricing). + +They're available to use without a waitlist. + +### API KEYS +```python +import os +os.environ["AI21_API_KEY"] = "" +``` + +### AI21 Models + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|--------------------------------------| +| j2-light | `completion('j2-light', messages)` | `os.environ['AI21_API_KEY']` | +| j2-mid | `completion('j2-mid', messages)` | `os.environ['AI21_API_KEY']` | +| j2-ultra | `completion('j2-ultra', messages)` | `os.environ['AI21_API_KEY']` | \ No newline at end of file diff --git a/docs/my-website/docs/providers/aleph_alpha.md b/docs/my-website/docs/providers/aleph_alpha.md new file mode 100644 index 0000000000..0d71619244 --- /dev/null +++ b/docs/my-website/docs/providers/aleph_alpha.md @@ -0,0 +1,23 @@ +# Aleph Alpha + +LiteLLM supports the 'luminous' + 'luminous-control' series of models from [Aleph Alpha](https://www.aleph-alpha.com/). + +Like AI21 and Cohere, you can use these models without a waitlist. + +### API KEYS +```python +import os +os.environ["ALEPHALPHA_API_KEY"] = "" +``` + +### Aleph Alpha Models +https://www.aleph-alpha.com/ + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|------------------------------------| +| luminous-base | `completion(model='luminous-base', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | +| luminous-base-control | `completion(model='luminous-base-control', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | +| luminous-extended | `completion(model='luminous-extended', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | +| luminous-extended-control | `completion(model='luminous-extended-control', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | +| luminous-supreme | `completion(model='luminous-supreme', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | +| luminous-supreme-control | `completion(model='luminous-supreme-control', messages=messages)` | `os.environ['ALEPHALPHA_API_KEY']` | diff --git a/docs/my-website/docs/providers/anthropic.md b/docs/my-website/docs/providers/anthropic.md new file mode 100644 index 0000000000..5af0307be4 --- /dev/null +++ b/docs/my-website/docs/providers/anthropic.md @@ -0,0 +1,18 @@ +# Anthropic +LiteLLM supports Claude-1, 1.2 and Claude-2. + +### API KEYS +``` +import os + +os.environ["ANTHROPIC_API_KEY"] = "" +``` + + +### Model Details + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|--------------------------------------| +| claude-instant-1 | `completion('claude-instant-1', messages)` | `os.environ['ANTHROPIC_API_KEY']` | +| claude-instant-1.2 | `completion('claude-instant-1.2', messages)` | `os.environ['ANTHROPIC_API_KEY']` | +| claude-2 | `completion('claude-2', messages)` | `os.environ['ANTHROPIC_API_KEY']` | diff --git a/docs/my-website/docs/providers/aws_sagemaker.md b/docs/my-website/docs/providers/aws_sagemaker.md new file mode 100644 index 0000000000..485601e3d6 --- /dev/null +++ b/docs/my-website/docs/providers/aws_sagemaker.md @@ -0,0 +1,19 @@ +# AWS Sagemaker +LiteLLM supports Llama2 on Sagemaker + +### API KEYS +```python +!pip install boto3 + +os.environ["AWS_ACCESS_KEY_ID"] = "" +os.environ["AWS_SECRET_ACCESS_KEY"] = "" +os.environ["AWS_REGION_NAME"] = "" +``` + +### AWS Sagemaker Models +Here's an example of using a sagemaker model with LiteLLM + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|------------------------------------| +| Llama2 7B | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b, messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | +| Custom LLM Endpoint | `completion(model='sagemaker/your-endpoint, messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | diff --git a/docs/my-website/docs/providers/azure.md b/docs/my-website/docs/providers/azure.md new file mode 100644 index 0000000000..1a8dfb4664 --- /dev/null +++ b/docs/my-website/docs/providers/azure.md @@ -0,0 +1,32 @@ +# Azure +LiteLLM supports Azure Chat + Embedding calls. + +### API KEYS +``` +import os + +os.environ["AZURE_API_KEY"] = "" +os.environ["AZURE_API_BASE"] = "" +os.environ["AZURE_API_VERSION"] = "" +``` + + +### Azure OpenAI Chat Completion Models + +```python + +from litellm import completion + +## set ENV variables +os.environ["OPENAI_API_KEY"] = "openai key" +os.environ["AZURE_API_KEY"] = "azure key" + + +messages = [{ "content": "Hello, how are you?","role": "user"}] + +# openai call +response = completion(model="gpt-3.5-turbo", messages=messages) + +# azure call +response = completion("azure/", messages) +``` \ No newline at end of file diff --git a/docs/my-website/docs/providers/baseten.md b/docs/my-website/docs/providers/baseten.md new file mode 100644 index 0000000000..902b1548fa --- /dev/null +++ b/docs/my-website/docs/providers/baseten.md @@ -0,0 +1,23 @@ +# Baseten +LiteLLM supports any Text-Gen-Interface models on Baseten. + +[Here's a tutorial on deploying a huggingface TGI model (Llama2, CodeLlama, WizardCoder, Falcon, etc.) on Baseten](https://truss.baseten.co/examples/performance/tgi-server) + +### API KEYS +```python +import os +os.environ["BASETEN_API_KEY"] = "" +``` + +### Baseten Models +Baseten provides infrastructure to deploy and serve ML models https://www.baseten.co/. Use liteLLM to easily call models deployed on Baseten. + +Example Baseten Usage - Note: liteLLM supports all models deployed on Baseten + +Usage: Pass `model=baseten/` + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|------------------------------------| +| Falcon 7B | `completion(model='baseten/qvv0xeq', messages=messages)` | `os.environ['BASETEN_API_KEY']` | +| Wizard LM | `completion(model='baseten/q841o8w', messages=messages)` | `os.environ['BASETEN_API_KEY']` | +| MPT 7B Base | `completion(model='baseten/31dxrj3', messages=messages)` | `os.environ['BASETEN_API_KEY']` | diff --git a/docs/my-website/docs/providers/cohere.md b/docs/my-website/docs/providers/cohere.md new file mode 100644 index 0000000000..dc2ab5e5ec --- /dev/null +++ b/docs/my-website/docs/providers/cohere.md @@ -0,0 +1,32 @@ +# Cohere + +LiteLLM supports 'command', 'command-light', 'command-medium', 'command-medium-beta', 'command-xlarge-beta', 'command-nightly' models from [Cohere](https://cohere.com/). + +Like AI21, these models are available without a waitlist. + +### API KEYS + +```python +import os +os.environ["COHERE_API_KEY"] = "" +``` + +### Example Usage + +```python + +from litellm import completion + +## set ENV variables +os.environ["OPENAI_API_KEY"] = "openai key" +os.environ["COHERE_API_KEY"] = "cohere key" + + +messages = [{ "content": "Hello, how are you?","role": "user"}] + +# openai call +response = completion(model="gpt-3.5-turbo", messages=messages) + +# cohere call +response = completion("command-nightly", messages) +``` \ No newline at end of file diff --git a/docs/my-website/docs/providers/ollama.md b/docs/my-website/docs/providers/ollama.md new file mode 100644 index 0000000000..8c1fd5ebd3 --- /dev/null +++ b/docs/my-website/docs/providers/ollama.md @@ -0,0 +1,17 @@ +# Ollama +LiteLLM supports all models from [Ollama](https://github.com/jmorganca/ollama) + +### Ollama Models +Ollama supported models: https://github.com/jmorganca/ollama + +| Model Name | Function Call | Required OS Variables | +|----------------------|-----------------------------------------------------------------------------------|--------------------------------| +| Llama2 7B | `completion(model='llama2', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Llama2 13B | `completion(model='llama2:13b', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Llama2 70B | `completion(model='llama2:70b', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Llama2 Uncensored | `completion(model='llama2-uncensored', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Orca Mini | `completion(model='orca-mini', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Vicuna | `completion(model='vicuna', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Nous-Hermes | `completion(model='nous-hermes', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Nous-Hermes 13B | `completion(model='nous-hermes:13b', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | +| Wizard Vicuna Uncensored | `completion(model='wizard-vicuna', messages, api_base="http://localhost:11434", custom_llm_provider="ollama", stream=True)` | No API Key required | diff --git a/docs/my-website/docs/providers/openai.md b/docs/my-website/docs/providers/openai.md new file mode 100644 index 0000000000..5d4be8df6c --- /dev/null +++ b/docs/my-website/docs/providers/openai.md @@ -0,0 +1,38 @@ +# OpenAI +LiteLLM supports OpenAI Chat + Text completion and embedding calls. + +### API KEYS +``` +import os + +os.environ["OPENAI_API_KEY"] = "" +``` + +### OpenAI Chat Completion Models + +| Model Name | Function Call | Required OS Variables | +|------------------|----------------------------------------|--------------------------------------| +| gpt-3.5-turbo | `completion('gpt-3.5-turbo', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-3.5-turbo-0301 | `completion('gpt-3.5-turbo-0301', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-3.5-turbo-0613 | `completion('gpt-3.5-turbo-0613', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-3.5-turbo-16k | `completion('gpt-3.5-turbo-16k', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-3.5-turbo-16k-0613 | `completion('gpt-3.5-turbo-16k-0613', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-4 | `completion('gpt-4', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-4-0314 | `completion('gpt-4-0314', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-4-0613 | `completion('gpt-4-0613', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-4-32k | `completion('gpt-4-32k', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-4-32k-0314 | `completion('gpt-4-32k-0314', messages)` | `os.environ['OPENAI_API_KEY']` | +| gpt-4-32k-0613 | `completion('gpt-4-32k-0613', messages)` | `os.environ['OPENAI_API_KEY']` | + +These also support the `OPENAI_API_BASE` environment variable, which can be used to specify a custom API endpoint. + +### OpenAI Text Completion Models + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|--------------------------------------| +| text-davinci-003 | `completion('text-davinci-003', messages)` | `os.environ['OPENAI_API_KEY']` | +| ada-001 | `completion('ada-001', messages)` | `os.environ['OPENAI_API_KEY']` | +| curie-001 | `completion('curie-001', messages)` | `os.environ['OPENAI_API_KEY']` | +| babbage-001 | `completion('babbage-001', messages)` | `os.environ['OPENAI_API_KEY']` | +| babbage-002 | `completion('ada-001', messages)` | `os.environ['OPENAI_API_KEY']` | +| davinci-002 | `completion('davinci-002', messages)` | `os.environ['OPENAI_API_KEY']` | \ No newline at end of file diff --git a/docs/my-website/docs/providers/openrouter.md b/docs/my-website/docs/providers/openrouter.md new file mode 100644 index 0000000000..3f651ab3f2 --- /dev/null +++ b/docs/my-website/docs/providers/openrouter.md @@ -0,0 +1,24 @@ +# OpenRouter +LiteLLM supports all the text models from [OpenRouter](https://openrouter.ai/docs) + +### API KEYS + +```python +import os +os.environ["OPENROUTER_API_KEYS"] = "" +``` + +### OpenRouter Completion Models + +| Model Name | Function Call | Required OS Variables | +|------------------|--------------------------------------------|--------------------------------------| +| openai/gpt-3.5-turbo | `completion('openai/gpt-3.5-turbo', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| openai/gpt-3.5-turbo-16k | `completion('openai/gpt-3.5-turbo-16k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| openai/gpt-4 | `completion('openai/gpt-4', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| openai/gpt-4-32k | `completion('openai/gpt-4-32k', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| anthropic/claude-2 | `completion('anthropic/claude-2', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| anthropic/claude-instant-v1 | `completion('anthropic/claude-instant-v1', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| google/palm-2-chat-bison | `completion('google/palm-2-chat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| google/palm-2-codechat-bison | `completion('google/palm-2-codechat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| meta-llama/llama-2-13b-chat | `completion('meta-llama/llama-2-13b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | +| meta-llama/llama-2-70b-chat | `completion('meta-llama/llama-2-70b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OPENROUTER_API_KEY']` | diff --git a/docs/my-website/docs/providers/replicate.md b/docs/my-website/docs/providers/replicate.md new file mode 100644 index 0000000000..f55408d359 --- /dev/null +++ b/docs/my-website/docs/providers/replicate.md @@ -0,0 +1,25 @@ +# Replicate + +LiteLLM supports all models on Replicate + +### API KEYS +```python +import os +os.environ["REPLICATE_API_KEY"] = "" +``` + + +### Replicate Models +liteLLM supports all replicate LLMs. For replicate models ensure to add a `replicate` prefix to the `model` arg. liteLLM detects it using this arg. +Below are examples on how to call replicate LLMs using liteLLM + +Model Name | Function Call | Required OS Variables | +-----------------------------|----------------------------------------------------------------|--------------------------------------| + replicate/llama-2-70b-chat | `completion('replicate/replicate/llama-2-70b-chat', messages)` | `os.environ['REPLICATE_API_KEY']` | + a16z-infra/llama-2-13b-chat| `completion('replicate/a16z-infra/llama-2-13b-chat', messages)`| `os.environ['REPLICATE_API_KEY']` | + joehoover/instructblip-vicuna13b | `completion('replicate/joehoover/instructblip-vicuna13b', messages)` | `os.environ['REPLICATE_API_KEY']` | + replicate/dolly-v2-12b | `completion('replicate/replicate/dolly-v2-12b', messages)` | `os.environ['REPLICATE_API_KEY']` | + a16z-infra/llama-2-7b-chat | `completion('replicate/a16z-infra/llama-2-7b-chat', messages)` | `os.environ['REPLICATE_API_KEY']` | + replicate/vicuna-13b | `completion('replicate/replicate/vicuna-13b', messages)` | `os.environ['REPLICATE_API_KEY']` | + daanelson/flan-t5-large | `completion('replicate/daanelson/flan-t5-large', messages)` | `os.environ['REPLICATE_API_KEY']` | + replit/replit-code-v1-3b | `completion('replicate/replit/replit-code-v1-3b', messages)` | `os.environ['REPLICATE_API_KEY']` | diff --git a/docs/my-website/docs/providers/togetherai.md b/docs/my-website/docs/providers/togetherai.md new file mode 100644 index 0000000000..fb5f1b27a4 --- /dev/null +++ b/docs/my-website/docs/providers/togetherai.md @@ -0,0 +1,22 @@ +# Together AI +LiteLLM supports all models on Together AI. + +### API KEYS + +```python +import os +os.environ["TOGETHERAI_API_KEY"] = "" +``` + +### Together AI Models +liteLLM supports `non-streaming` and `streaming` requests to all models on https://api.together.xyz/ + +Example TogetherAI Usage - Note: liteLLM supports all models deployed on TogetherAI + +| Model Name | Function Call | Required OS Variables | +|-----------------------------------|------------------------------------------------------------------------|---------------------------------| +| togethercomputer/llama-2-70b-chat | `completion('togethercomputer/llama-2-70b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` | +| togethercomputer/LLaMA-2-13b-chat | `completion('togethercomputer/LLaMA-2-13b-chat', messages)` | `os.environ['TOGETHERAI_API_KEY']` | +| togethercomputer/code-and-talk-v1 | `completion('togethercomputer/code-and-talk-v1', messages)` | `os.environ['TOGETHERAI_API_KEY']` | +| togethercomputer/creative-v1 | `completion('togethercomputer/creative-v1', messages)` | `os.environ['TOGETHERAI_API_KEY']` | +| togethercomputer/yourmodel | `completion('togethercomputer/yourmodel', messages)` | `os.environ['TOGETHERAI_API_KEY']` | diff --git a/docs/my-website/docs/providers/vertex.md b/docs/my-website/docs/providers/vertex.md new file mode 100644 index 0000000000..d94059536c --- /dev/null +++ b/docs/my-website/docs/providers/vertex.md @@ -0,0 +1,24 @@ +# Google Palm/VertexAI +LiteLLM supports chat-bison, chat-bison@001, text-bison, text-bison@001 + +### Google VertexAI Models +Sample notebook for calling VertexAI models: https://github.com/BerriAI/litellm/blob/main/cookbook/liteLLM_VertextAI_Example.ipynb + +All calls using Vertex AI require the following parameters: +* Your Project ID +`litellm.vertex_project` = "hardy-device-38811" Your Project ID +* Your Project Location +`litellm.vertex_location` = "us-central1" + +Authentication: +VertexAI uses Application Default Credentials, see https://cloud.google.com/docs/authentication/external/set-up-adc for more information on setting this up + +VertexAI requires you to set `application_default_credentials.json`, this can be set by running `gcloud auth application-default login` in your terminal + +| Model Name | Function Call | +|------------------|----------------------------------------------------------| +| chat-bison | `completion('chat-bison', messages)` | +| chat-bison@001 | `completion('chat-bison@001', messages)` | +| text-bison | `completion('text-bison', messages)` | +| text-bison@001 | `completion('text-bison@001', messages)` | + diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js index 552384fda5..3eb3c92a7f 100644 --- a/docs/my-website/sidebars.js +++ b/docs/my-website/sidebars.js @@ -29,18 +29,17 @@ const sidebars = { label: "Embedding()", items: ["embedding/supported_embedding"], }, - 'completion/supported', - // { - // type: "category", - // label: "Providers", - // link: { - // type: 'generated-index', - // title: 'Providers', - // description: 'Learn how to deploy + call models from different providers on LiteLLM', - // slug: '/providers', - // }, - // items: ["providers/huggingface"], - // }, + { + type: "category", + label: "Supported Models + Providers", + link: { + type: 'generated-index', + title: 'Providers', + description: 'Learn how to deploy + call models from different providers on LiteLLM', + slug: '/providers', + }, + items: ["providers/huggingface", "providers/openai", "providers/azure", "providers/vertex", "providers/anthropic", "providers/ai21", "providers/replicate", "providers/cohere", "providers/togetherai", "providers/aws_sagemaker", "providers/aleph_alpha", "providers/baseten", "providers/openrouter", "providers/ollama"] + }, "token_usage", "exception_mapping", 'debugging/local_debugging',