From 7585b58d2d41e3b193993dcc16a151802cf44d06 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Thu, 7 Dec 2023 11:42:44 -0800 Subject: [PATCH] docs: sagemaker embedding model added to docs --- .../docs/providers/aws_sagemaker.md | 23 +++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/docs/my-website/docs/providers/aws_sagemaker.md b/docs/my-website/docs/providers/aws_sagemaker.md index 606268ad103..328981c7012 100644 --- a/docs/my-website/docs/providers/aws_sagemaker.md +++ b/docs/my-website/docs/providers/aws_sagemaker.md @@ -42,7 +42,7 @@ response = completion( ) ``` -### Specifying HF Model Name +### Applying Prompt Templates To apply the correct prompt template for your sagemaker deployment, pass in it's hf model name as well. ```python @@ -62,6 +62,7 @@ response = completion( ) ``` +You can also pass in your own [custom prompt template](../completion/prompt_formatting.md#format-prompt-yourself) ### Usage - Streaming Sagemaker currently does not support streaming - LiteLLM fakes streaming by returning chunks of the response string @@ -85,14 +86,32 @@ for chunk in response: print(chunk) ``` -### AWS Sagemaker Models +### Completion Models Here's an example of using a sagemaker model with LiteLLM | Model Name | Function Call | |-------------------------------|-------------------------------------------------------------------------------------------| +| Your Custom Huggingface Model | `completion(model='sagemaker/', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | Meta Llama 2 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']` | | Meta Llama 2 7B (Chat/Fine-tuned) | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b-f', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | | Meta Llama 2 13B | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-13b', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | | Meta Llama 2 13B (Chat/Fine-tuned) | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-13b-f', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | | Meta Llama 2 70B | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-70b', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | | Meta Llama 2 70B (Chat/Fine-tuned) | `completion(model='sagemaker/jumpstart-dft-meta-textgeneration-llama-2-70b-b-f', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | + +### Embedding Models + +LiteLLM supports all Sagemaker Jumpstart Huggingface Embedding models. Here's how to call it: + +```python +from litellm import completion + +os.environ["AWS_ACCESS_KEY_ID"] = "" +os.environ["AWS_SECRET_ACCESS_KEY"] = "" +os.environ["AWS_REGION_NAME"] = "" + +response = litellm.embedding(model="sagemaker/", input=["good morning from litellm", "this is another item"]) +print(f"response: {response}") +``` + +