Text Generation Inference
Text Generation Webserver
Fork copies the collection into your workspace, without the publisher's secrets, so you can add your own key and send requests. Star saves it to your starred APIs (Account › Marketplace) and helps others find it.
Overview
Text Generation Webserver
Endpoints 12
Text Generation Inference
- POSTGenerate tokens if `stream == false` or a stream of token if `stream == true`
/ - POSTTemplate and tokenize ChatRequest
/chat_tokenize - POSTGenerate tokens
/generate - POSTGenerate a stream of token using Server-Sent Events
/generate_stream - GETHealth check method
/health - GETText Generation Inference endpoint info
/info - POSTGenerate tokens from Sagemaker request
/invocations - GETPrometheus metrics scrape endpoint
/metrics - POSTTokenize inputs
/tokenize - POSTGenerate tokens
/v1/chat/completions - POSTGenerate tokens
/v1/completions - GETGet model info
/v1/models
API details
- Authentication
- None declared in the description
- Operations
- 12 operations on 12 pathsPOST 8GET 4
- Main resources
- Text Generation Inference 12
- Response formats
application/jsontext/event-streamtext/plain- Description format
- OpenAPI 3.0.3, API version
3.3.6-dev0 - Links
- OpenAPI document
- Listed from
- Hugging Face TGI's published OpenAPI description (huggingface/text-generation-inference) (Apache-2.0)
How to test the Text Generation Inference in Swastik Codes
- Open the APISelect “Fork & run in Swastik Codes” on this page. Sign in or create a free account if asked.
- Fork it into your workspaceChoose a workspace. You get your own copy of the Text Generation Inference collection, without the publisher's secrets.
- Add your credentialsOpen the collection's variables or an environment and enter your API key or token, if the API needs one.
- Send a requestPick an endpoint, for example “Generate tokens if `stream == false` or a stream of token if `stream == true`” (POST /), and press Send. Check the response, add tests and run the whole collection with the runner.
Frequently asked questions
What is the Text Generation Inference?
Text Generation Webserver It is listed under AI & machine learning and has 12 endpoints.
Who publishes the Text Generation Inference?
It is listed from Hugging Face's public API description (an OpenAPI document), not published by Hugging Face on Swastik Codes. Anyone who controls huggingface.co can claim the profile by adding a DNS TXT record.
How do I authenticate with the Text Generation Inference?
Its OpenAPI description does not declare an authentication scheme. Some endpoints may be open; check the provider's documentation before relying on that.
How many endpoints does the Text Generation Inference have?
12 operations on 12 paths (8 POST, 4 GET). The largest groups are Text Generation Inference.
Is forking the Text Generation Inference free?
Yes. Forking copies the collection into your workspace for free. It has been starred 0 times and forked 0 times.