Quick start

Index Network API allows you to interact with our platform and build products leveraging our services. Below, you will find detailed information about the available endpoints, their purposes, and how to use them.

You can either use the API directly or the client available. Here is a quick start to discover it.

Using Index Client SDK

The Index Network offers an SDK to facilitate various operations on our platform. In this example, we'll demonstrate how to authenticate, create an Index, and add an Item to it.

Index is a fundamental component of the Index Network, designed to facilitate context management and enable semantic interoperability within your system. It serves as a structured way to organize and store data related to specific contexts.

Item represents a graph node within an Index. It provides a standardized approach to representing and managing various types of data.

Installation

First, install the sdk via your package manager:

Node.js | Python

Usage

Next, import it in your project:

JavaScript

import IndexClient from "@indexnetwork/sdk"

Python

from indexnetwork-sdk import IndexClient

Create an instance of IndexClient:

JavaScript

const indexClient = new IndexClient({
  network: "dev", // Or mainnet
  wallet, // Wallet that interacts
});

Python

index_client = IndexClient(
    wallet=your_wallet_object,  # Provide your wallet instance
    network="dev"  # Or mainnet
)

Authenticate it. Check out Authentication for details and explanation on how to initiate a session.

JavaScript

await indexClient.authenticate(); 

Python

index_client.authenticate()

Creating an Index

We're ready. Now, let's create an Index with a title.

JavaScript

const indexId = await indexClient.createIndex("Future of publishing");

Python

index_id = client.create_index("Future of publishing")

Now you have a truly decentralized index to interact with! Though it's empty, which means we need to create and add an Item into it so we can interact. Let's do that.

JavaScript

const webPageId = await indexClient.crawlWebPage("http://www.paulgraham.com/publishing.html");

await indexClient.addItemToIndex(indexId, webPageId);

Python

web_page = index_client.crawl_web_page("http://www.paulgraham.com/publishing.html")
index_client.add_item(index_id, web_page["id"])

Using Custom Schemas

If you want to use your own schema, you can do so by creating and deploying a custom model. Below are the methods and examples of how to use them.

Creating a Custom Model

Use the createModel method to create a custom model using a GraphQL schema.

JavaScript

const modelResponse = await indexClient.createModel(`
  type CustomObject {
    title: String! @string(maxLength: 50)
  }

  type YourModel @createModel(accountRelation: LIST, description: "Full schema for models") {
    id: ID!
    booleanValue: Boolean!
    intValue: Int!
    floatValue: Float!
    did: DID!
    streamId: StreamID!
    commitId: CommitID!
    cid: CID!
    chainId: ChainID!
    accountId: AccountID!
    uri: URI! @string(maxLength: 2000)
    date: Date!
    dateTime: DateTime!
    time: Time!
    localDate: LocalDate!
    localTime: LocalTime!
    timeZone: TimeZone!
    utcOffset: UTCOffset!
    duration: Duration!
    stringValue: String! @string(maxLength: 10)
    objectArray: [CustomObject!] @list(maxLength: 30)
    singleObject: CustomObject
  }
`);

Python

graphQLSchema = """
type CustomObject {
    title: String! @string(maxLength: 50)
}

type YourModel @createModel(accountRelation: LIST, description: "Full schema for models") {
    id: ID!
    booleanValue: Boolean!
    intValue: Int!
    floatValue: Float!
    did: DID!
    streamId: StreamID!
    commitId: CommitID!
    cid: CID!
    chainId: ChainID!
    accountId: AccountID!
    uri: URI! @string(maxLength: 2000)
    date: Date!
    dateTime: DateTime!
    time: Time!
    localDate: LocalDate!
    localTime: LocalTime!
    timeZone: TimeZone!
    utcOffset: UTCOffset!
    duration: Duration!
    stringValue: String! @string(maxLength: 10)
    objectArray: [CustomObject!] @list(maxLength: 30)
    singleObject: CustomObject
}
"""

model_response = index_client.create_model(graphQLSchema)

Deploying a Custom Model

After creating a custom model, use the deployModel method to deploy it.

JavaScript

await indexClient.deployModel(modelResponse.models[0]);

Python

index_client.deploy_model(model_response["models"][0]["id"])

Using Your Model

To use it, create a node with your model and required data.

JavaScript

const sampleNodeData = { } // Fill with your data

const createdNode = await indexClient.createNode(
  modelResponse.models[0],
  sampleNodeData,
);

const newIndex = await indexClient.createIndex("Index with your model");

const addedItem = await indexClient.addItemToIndex(
  newIndex.id,
  createdNode.id,
);

Python

message = "hello world"
print(message)

Interact with your index

Your index is now ready for interaction! To start a conversation and interact with the data, follow these steps:

JavaScript

// Create a conversation
const conversationParams = {
  sources: [index.id],
  summary: "Mock summary",
};
const conversation = await indexClient.createConversation(conversationParams);

// Add a message to the conversation
const messageParams = {
  role: "user",
  content: "How do you do this?",
};
const message = await indexClient.createMessage(conversation.id, messageParams);

// Retrieve messages from the conversation
const { messages } = await indexClient.getConversation(conversation.id);

Python

conversation_params = {
  "sources": [index["id"]],
  "summary": "Mock summary"
}
conversation = index_client.create_conversation(conversation_params)

message_params = {
  "role": "user",
  "content": "How do you do this?"
}
message = index_client.create_message(conversation["id"], message_params)

messages = index_client.get_conversation(conversation["id"])
print("Retrieved Messages:", messages)

The response should look something like this:

{
  "id": "message-id",
  "content": "How do you do this?",
  "role": "user",
  "createdAt": "timestamp"
}

Listening to Conversation Updates

The Index Client SDK allows you to listen for updates to a conversation in real-time. This is useful for applications that need to react to new messages or changes in a conversation.

Here is an example of how you can use the listenToConversationUpdates method to handle real-time updates in a conversation:

JavaScript

const conversationId = "your-conversation-id";

const handleMessage = (data: any) => {
  console.log("New message received:", data);
  // Handle the new message data
};

const handleError = (error: any) => {
  console.error("Error receiving updates:", error);
  // Handle the error
};

const stopListening = indexClient.listenToConversationUpdates(
  conversationId,
  handleMessage,
  handleError,
);

Python

conversation_id = "your-conversation-id"

def handle_message(data):
  print("New message received:", data)

def handle_error(error):
  print("Error receiving updates:", error)

index_client.listen_to_conversation_updates(
  conversation_id=conversation_id,
  handle_message=handle_message,
  handle_error=handle_error
)

Listening to Index Updates

The Index Client SDK allows you to listen for updates to miltiple indexes in real-time. This is useful for applications that need to react to new data events, using natural language.

Here is an example of how you can use the listenToIndexUpdates method to handle real-time updates in a conversation:

JavaScript

const sources = ["did:pkh:eip155:1:0x1b9Aceb609a62bae0c0a9682A9268138Faff4F5f"];

const query = "if it is relevant to decentralized AI";

const handleMessage = (data: any) => {
  console.log("New event received:", data);
  // Handle the new message data
};

const handleError = (error: any) => {
  console.error("Error receiving updates:", error);
  // Handle the error
};

const stopListening = indexClient.listenToIndexUpdates(
  sources,
  query
  handleMessage,
  handleError,
);

Python

sources = ["did:pkh:eip155:1:0x1b9Aceb609a62bae0c0a9682A9268138Faff4F5f"]
query = "if it is relevant to decentralized AI"

def handle_message(data):
  print("New event received:", data)

def handle_error(error):
  print("Error receiving updates:", error)

index_client.listen_to_index_updates(
  sources=sources,
  query=query,
  handle_message=handle_message,
  handle_error=handle_error
)