Hyperfast LLM running on custom built GPU and the fastest interface in the world.
Creates a model response for the given chat conversation. See the documentation
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
groqcloud: {
type: "app",
app: "groqcloud",
}
},
async run({steps, $}) {
const data = {"messages": [{"role": "user", "content": "What is Pipedream?"}], "model": "llama3-8b-8192"}
return await axios($, {
method: "post",
url: `https://api.groq.com/openai/v1/chat/completions`,
headers: {
Authorization: `Bearer ${this.groqcloud.$auth.api_key}`,
},
data,
})
},
})
Develop, run and deploy your Python code in Pipedream workflows. Integrate seamlessly between no-code steps, with connected accounts, or integrate Data Stores and manipulate files within a workflow.
This includes installing PyPI packages, within your code without having to manage a requirements.txt
file or running pip
.
Below is an example of using Python to access data from the trigger of the workflow, and sharing it with subsequent workflow steps:
def handler(pd: "pipedream"):
# Reference data from previous steps
print(pd.steps["trigger"]["context"]["id"])
# Return data for use in future steps
return {"foo": {"test":True}}