Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: improve messages api docs content and formatting (#1506) 

This PR simply updates the messages api docs to address content changes
and make format consistent
This commit is contained in:
drbh 2024-01-31 11:26:22 -05:00 committed by GitHub
parent 0595bf3e9a
commit 2ae36a97fd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
docs/source/messages_api.md
View File

@ -1,8 +1,8 @@
# Messages API # Messages API
_Messages API is compatible to OpenAI Chat Completion API_ Text Generation Inference (TGI) now supports the Messages API, which is fully compatible with the OpenAI Chat Completion API. This feature is available starting from version 1.4.0. You can use OpenAI's client libraries or third-party libraries expecting OpenAI schema to interact with TGI's Messages API. Below are some examples of how to utilize this compatibility.
Text Generation Inference (TGI) now supports the Message API which is fully compatible with the OpenAI Chat Completion API. This means you can use OpenAI's client libraries to interact with TGI's Messages API. Below are some examples of how to utilize this compatibility. > **Note:** The Messages API is supported from TGI version 1.4.0 and above. Ensure you are using a compatible version to access this feature.
## Making a Request ## Making a Request
@ -87,7 +87,7 @@ TGI can be deployed on various cloud providers for scalable and robust text gene
## Amazon SageMaker ## Amazon SageMaker
To enable the Messages API in Amazon SageMaker you need to set the environment variable `MESSAGES_API_ENABLED=true`. To enable the Messages API in Amazon SageMaker you need to set the environment variable `MESSAGES_API_ENABLED=true`.
This will modify the `/invocations` route to accept Messages dictonaries consisting out of role and content. See the example below on how to deploy Llama with the new Messages API. This will modify the `/invocations` route to accept Messages dictonaries consisting out of role and content. See the example below on how to deploy Llama with the new Messages API.
@ -98,30 +98,30 @@ import boto3
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
try: try:
role = sagemaker.get_execution_role() role = sagemaker.get_execution_role()
except ValueError: except ValueError:
iam = boto3.client('iam') iam = boto3.client('iam')
role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn'] role = iam.get_role(RoleName='sagemaker_execution_role')['Role']['Arn']
# Hub Model configuration. https://huggingface.co/models # Hub Model configuration. https://huggingface.co/models
hub = { hub = {
'HF_MODEL_ID':'HuggingFaceH4/zephyr-7b-beta', 'HF_MODEL_ID':'HuggingFaceH4/zephyr-7b-beta',
'SM_NUM_GPUS': json.dumps(1), 'SM_NUM_GPUS': json.dumps(1),
'MESSAGES_API_ENABLED': True 'MESSAGES_API_ENABLED': True
} }
# create Hugging Face Model Class # create Hugging Face Model Class
huggingface_model = HuggingFaceModel( huggingface_model = HuggingFaceModel(
image_uri=get_huggingface_llm_image_uri("huggingface",version="1.4.0"), image_uri=get_huggingface_llm_image_uri("huggingface",version="1.4.0"),
env=hub, env=hub,
role=role, role=role,
) )
# deploy model to SageMaker Inference # deploy model to SageMaker Inference
predictor = huggingface_model.deploy( predictor = huggingface_model.deploy(
initial_instance_count=1, initial_instance_count=1,
instance_type="ml.g5.2xlarge", instance_type="ml.g5.2xlarge",
container_startup_health_check_timeout=300, container_startup_health_check_timeout=300,
) )
# send request # send request
@ -131,4 +131,4 @@ predictor.predict({
{"role": "user", "content": "What is deep learning?"} {"role": "user", "content": "What is deep learning?"}
] ]
}) })
``` ```