API for Llama and Open-Source Models
Write Python and use any of the 350k+ PyPi packages available. Refer to the Pipedream Python docs to learn more.
The Llama AI API provides powerful machine learning capabilities, enabling users to harness advanced AI for image recognition, natural language processing, and predictive modeling. By leveraging this API on Pipedream, you can automate complex workflows that require AI-driven insights, enhancing data analysis and decision-making processes across various business applications.
import { axios } from "@pipedream/platform"
export default defineComponent({
props: {
llama_ai: {
type: "app",
app: "llama_ai",
}
},
async run({steps, $}) {
const data = {
"messages": [
{"role": "user", "content": "What is the weather like in Boston?"},
],
"functions": [
{
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"days": {
"type": "number",
"description": "for how many days ahead you wants the forecast",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
},
"required": ["location", "days"],
}
],
"stream": "false",
"function_call": "get_current_weather",
}
return await axios($, {
method: "post",
url: `https://api.llama-api.com/chat/completions`,
headers: {
Authorization: `Bearer ${this.llama_ai.$auth.api_token}`,
},
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}}