Use LangChain with AI Proxy in Kong Gateway

Enable the AI Proxy plugin with your OpenAI API key and the model details. In this example, we’ll use the GPT-4o model.

echo '
_format_version: "3.0"
plugins:
  - name: ai-proxy
    config:
      route_type: llm/v1/chat
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
      model:
        provider: openai
        name: gpt-4o
' | deck gateway apply -

To secure the access to your Route, create a Consumer and set up an authentication plugin.

Note that LangChain expects authentication as an Authorization header with a value starting with Bearer. You can use plugins like OAuth 2.0 Authentication or OpenID Connect to generate Bearer tokens. In this example, for testing purposes, we’ll recreate this pattern using the Key Authentication plugin.

echo '
_format_version: "3.0"
plugins:
  - name: key-auth
    route: example-route
    config:
      key_names:
      - Authorization
consumers:
  - username: ai-user
    keyauth_credentials:
    - key: Bearer my-api-key
' | deck gateway apply -

Load the LangChain SDK into your Python dependencies:

pip3 install -U langchain-openai

python3 -m venv .venv
source .venv/bin/activate
pip install -U langchain-openai

Use the following command to create a file named app.py containing a LangChain Python script:

echo 'from langchain_openai import ChatOpenAI

kong_url = "http://127.0.0.1:8000"
kong_route = "anything"

llm = ChatOpenAI(
    base_url=f"{kong_url}/{kong_route}",
    model="gpt-4o",
    api_key="my-api-key"
)

response = llm.invoke("What are you?")
print(f"$ ChainAnswer:> {response.content}")' > app.py

echo 'from langchain_openai import ChatOpenAI
import os

kong_url = os.environ['KONNECT_PROXY_URL']
kong_route = "anything"

llm = ChatOpenAI(
    base_url=f"{kong_url}/{kong_route}",
    model="gpt-4o",
    api_key="my-api-key"
)

response = llm.invoke("What are you?")
print(f"$ ChainAnswer:> {response.content}")' > app.py

With the base_url parameter, we can override the OpenAI base URL that LangChain uses by default with the URL to our Kong Gateway Route. This way, we can proxy requests and apply Kong Gateway plugins, while also using LangChain integrations and tools.

In the api_key parameter, we’ll add the API key we created, without the Bearer prefix, which is added automatically by LangChain.

Run your script to validate that LangChain can access the Route:

python3 ./app.py

The response should look like this:

ChainAnswer:> I am an AI language model created by OpenAI, designed to assist with understanding and generating human-like text based on the input I receive. I can help answer questions, provide explanations, and assist with a variety of tasks involving language. What would you like to know or discuss today?