This integration is only for
Keywords AI LLM proxy user. If you only want to log LLM calls and responses, you can use the
Logging API to log LLM calls.
Keywords AI provides a robust and flexible LLM proxy with 250+ LLMs. You can use Keywords AI with OpenAI SDK by just passing the base_url and api_key to the OpenAI SDK.
Integration examples
from openai import OpenAI
client = OpenAI(
base_url="https://api.keywordsai.co/api/",
api_key=YOUR_KEYWORDSAI_API_KEY,
)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role":"user", "content":"Tell me a long story"}],
)
from openai import OpenAI
client = OpenAI(
base_url="https://api.keywordsai.co/api/",
api_key=YOUR_KEYWORDSAI_API_KEY,
)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role":"user", "content":"Tell me a long story"}],
)
import { OpenAI } from "openai";
const client = new OpenAI({
baseURL: "https://api.keywordsai.co/api",
apiKey: process.env.KEYWORDS_AI_API_KEY,
});
const response = await client.chat.completions
.create({
messages: [{ role: "user", content: "Say this is a test" }],
model: "gpt-4o-mini",
})
.asResponse();
console.log(await response.json());
package main
import (
"context"
"fmt"
"github.com/openai/openai-go"
"github.com/openai/openai-go/option"
)
func main() {
client := openai.NewClient(
options.WithBaseURL("https://api.keywordsai.co/api"),
option.WithAPIKey("KEYWORDSAI_API_KEY"), // defaults to os.LookupEnv("OPENAI_API_KEY")
)
chatCompletion, err := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Messages: openai.F([]openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Say this is a test"),
}),
Model: openai.F(openai.ChatModelGPT4o),
})
if err != nil {
panic(err.Error())
}
println(chatCompletion.Choices[0].Message.Content)
}
Supported parameters
OpenAI parameters
We support all the OpenAI parameters. You can pass them directly in the request body.
You can pass Keywords AI parameters in the extra_body parameter.
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Tell me a story"}],
stream=True,
)
You can pass Keywords AI parameters in the extra_body parameter.
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Tell me a story"}],
stream=True,
)
For TypeScript, you should add a // @ts-expect-error to the parameter.
const response = await client.chat.completions.create({
messages: [{ role: "user", content: "Tell me a story" }],
model: "gpt-4o-mini",
stream: true,
})
Keywords AI parameters
Keywords AI parameters can be passed differently depending on your programming language:
You can pass Keywords AI parameters in the extra_body parameter.
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Tell me a story"}],
extra_body={"customer_identifier": "test_user_1"}
)
You can pass Keywords AI parameters in the extra_body parameter.
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "Tell me a story"}],
extra_body={"customer_identifier": "test_user_1"}
)
For TypeScript, you should add a // @ts-expect-error to the parameter.
const response = await client.chat.completions.create({
messages: [{ role: "user", content: "Tell me a story" }],
model: "gpt-4o-mini",
// @ts-expect-error
customer_identifier: "test_user_1",
})
These parameters will take precedence over the OpenAI parameters if they are conflicting.
Call Azure OpenAI with OpenAI SDK
To call Azure OpenAI models, instead of using azure OpenAI’s client, the easier way is to use the OpenAI client.
from openai import AsyncOpenAI
azureaclient = AsyncOpenAI(
api_key=KEYWORDSAI_API_KEY,
base_url="https://api.keywordsai.co/api"
)
response = await azureaclient.chat.completions.create(**kwargs)
Then You can upload your Azure credentials to Keywords AI platform to use those models. Check out our Providers integration.
