Hugging Face

Obiguard provides a robust and secure gateway to facilitate the integration of various Large Language Models (LLMs) into your applications, including all the text generation models supported by Hugging Face’s Inference endpoints. With Obiguard, you can take advantage of features like fast AI gateway access, observability, prompt management, and more, all while ensuring your provider credentials stay in Obiguard and callers authenticate with access keys.

Provider Slug. Hugging Face

Obiguard SDK Integration with Hugging Face

Obiguard provides a consistent API to interact with models from various providers. To integrate Hugging Face with Obiguard:

1. Install the Obiguard SDK

Add the Obiguard SDK to your application to interact with Hugging Face’s API through Obiguard’s gateway.

Python SDK

pip install obiguard

2. Initialize Obiguard with an access key

To use Hugging Face with Obiguard, get your Hugging Face Access token from here. Add it to Obiguard as a provider credential, then create an access key for the agent or project that will call it.

Python SDK
OpenAI Python SDK

from obiguard import Obiguard

client = Obiguard(
  obiguard_api_key="ak***", # Your Obiguard access key # Replace with your Obiguard API key
  huggingface_base_url="Hugging Face_DEDICATED_URL" # Optional: Use this if you have a dedicated server hosted on Hugging Face
)

from openai import OpenAI
from obiguard import OBIGUARD_GATEWAY_URL, createHeaders

client = OpenAI(
  api_key="Hugging Face_ACCESS_TOKEN",
  base_url=OBIGUARD_GATEWAY_URL,
  default_headers=createHeaders(
    obiguard_api_key="ak***", # Your Obiguard access key
    provider="Hugging Face",
    huggingface_base_url="Hugging Face_DEDICATED_URL"
  )
)

3. Invoke Chat Completions with Hugging Face

Use the Obiguard instance to send requests to Hugging Face.

Python SDK
OpenAI Python SDK

chat_completion = client.chat.completions.create(
  messages = [{"role": 'user', "content": 'Say this is a test'}],
  model = 'meta-llama/meta-llama-3.1-8b-instruct', # make sure your model is hot
)

print(chat_completion.choices[0].message.content)

chat_completion = client.chat.completions.create(
  messages = [{"role": 'user', "content": 'Say this is a test'}],
  model = 'meta-llama/meta-llama-3.1-8b-instruct', # make sure your model is hot
)

print(chat_completion.choices[0].message.content)

Using Provider Credentials and Access Keys

Obiguard stores the credentials for your provider in its vault as a provider credential, and your application authenticates to the gateway with an access key. This simplifies the use of multiple providers and Obiguard features within your application. For self-hosted LLMs, you can configure custom authentication requirements including authorization keys, bearer tokens, or any other headers needed to access your model.

Add your self-hosted model to Obiguard as a provider credential
Configure your deployment:
- Select the matching provider API specification (typically OpenAI)
- Enter your model’s base URL as the custom host
- Add required authentication headers and their values
Create an access key for the agent or project that will call it

You can now use the access key in your requests:

Python SDK

client = Obiguard(
  obiguard_api_key="ak***",  # Your Obiguard access key
)

response = client.chat.completions.create(
  model="your-self-hosted-model-name",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

For more information about managing self-hosted LLMs with Obiguard, see Bring Your Own LLM.

Next Steps

The complete list of features supported in the SDK are available on the link below.

Obiguard SDK Client

Learn more about the Obiguard SDK Client

Ecosystem

AI Apps

Agents

LLMs

Vector Databases

Obiguard SDK Integration with Hugging Face

1. Install the Obiguard SDK

2. Initialize Obiguard with an access key

3. Invoke Chat Completions with Hugging Face

Using Provider Credentials and Access Keys

Next Steps

Obiguard SDK Client

​Obiguard SDK Integration with Hugging Face

​1. Install the Obiguard SDK

​2. Initialize Obiguard with an access key

​3. Invoke Chat Completions with Hugging Face

​Using Provider Credentials and Access Keys

​Next Steps

Obiguard SDK Client

Obiguard SDK Integration with Hugging Face

1. Install the Obiguard SDK

2. Initialize Obiguard with an access key

3. Invoke Chat Completions with Hugging Face

Using Provider Credentials and Access Keys

Next Steps