AI Data Applications are often complex workflows that ingest and process data continuously. A single data application might involve running inference using multiple open source LLMs, call LLM APIs, do post-processing like masking PIIs on a heteregenous pool of compute resources.

Existing open source tools and libraries like Airflow, Temporal, Prefect, etc, are not designed to handle all aspects of a modern data stack for AI Engineering Teams.

We have open-sourced Indexify to democratize the infrastructure for building data applications for engineering teams who wants to own the infrastructure for their data applications.

Our Document AI Engine is built on Indexify as well.

​
Quick Start

Let’s create a simple workflow to summarize a website on-demand! It demonstrates how to build and serve a workflow as a remote Python API.

1

Install

Install the Indexify SDK.

pip install indexify openai requests
2

Define the Graph

We will write two functions, scrape_website and summarize_text. We create a Graph website-summarizer that executes the scrape function, and then executes the summarizer with the outputs of the scraper.

from indexify import indexify_function, Graph

@indexify_function()
def scrape_website(url: str) -> str:
    import requests
    return requests.get(f"http://r.jina.ai/{url}").text

@indexify_function()
def summarize_text(text: str) -> str:
    from openai import OpenAI
    completion = OpenAI().chat.completions.create(
        model="gpt-4o-mini-2024-07-18",
        messages=[
            {"role": "system", "content": "You are a helpful assistant. Generate a summary of this website"},
            {"role": "user", "content": text},
        ],
    )
    return completion.choices[0].message.content

g = Graph(name="website-summarizer", start_node=scrape_website)
g.add_edge(scrape_website, summarize_text)
3

Test the Graph In-Process

The graph can be run as-is, this is useful for testing.

invocation_id = g.run(url="https://en.wikipedia.org/wiki/Golden_State_Warriors")
results = g.output(invocation_id, "summarize_text")
print(results)
4

Deploying a Graph as an Remote API

When it’s time to consume your graph from other applications, you can serve it as an API. You can run the server in production in many ways, but here we run this in our laptop to show how it works.

indexify-cli server-dev-mode

Note: The indexify-cli command is part of the indexify python package previously installed.

This starts the following processes -

  • Server: Orchestrates functions in the graph, stores execution state, and hosts Remote Graph APIs.
  • Executor: Runs the individual functions in the graph.

Once the server is ready, you can deploy the graph -

from indexify import RemoteGraph
RemoteGraph.deploy(g, server_url="http://localhost:8900")
5

Call a Graph Endpoint

Once the graph is deployed, you can get a reference of the Graph in any application.

graph = RemoteGraph.by_name(name="website-summarizer", server_url="http://localhost:8900")

You can now call the graph as a remote API.

invocation_id = graph.run(block_until_done=True, url="https://en.wikipedia.org/wiki/Golden_State_Warriors")
results = graph.output(invocation_id, "summarize_text")

Was this page helpful?

Structured ExtractionDeployment