Chunking
Parse
Split large text documents into smaller, manageable chunks using different chunking strategies optimized for RAG (Retrieval-Augmented Generation) workflows. This endpoint supports multiple chunking algorithms including token-based, sentence-based, recursive, semantic, and specialized strategies.from orq_ai_sdk import Orq
import os
with Orq(
api_key=os.getenv("ORQ_API_KEY", ""),
) as orq:
res = orq.chunking.parse(request={
"text": "The quick brown fox jumps over the lazy dog. This is a sample text that will be chunked into smaller pieces. Each chunk will maintain context while respecting the maximum chunk size.",
"metadata": True,
"strategy": "semantic",
"chunk_size": 256,
"threshold": 0.8,
"embedding_model": "openai/text-embedding-3-small",
"dimensions": 512,
"mode": "window",
"similarity_window": 1,
})
# Handle response
print(res)
import { Orq } from "@orq-ai/node";
const orq = new Orq({
apiKey: process.env["ORQ_API_KEY"] ?? "",
});
async function run() {
const result = await orq.chunking.parse({
text: "The quick brown fox jumps over the lazy dog. This is a sample text that will be chunked into smaller pieces. Each chunk will maintain context while respecting the maximum chunk size.",
metadata: true,
strategy: "semantic",
chunkSize: 256,
threshold: 0.8,
embeddingModel: "openai/text-embedding-3-small",
dimensions: 512,
mode: "window",
similarityWindow: 1,
});
console.log(result);
}
run();
Show Parameters
Show Parameters
{
"text": str, # required
"metadata": Optional[bool],
"return_type": Optional[Literal["chunks", "texts"]],
"strategy": Literal["token"], # required
"chunk_size": Optional[int],
"chunk_overlap": Optional[int],
}
{
text: string; // required
metadata?: boolean | undefined;
return_type?: "chunks" | "texts" | undefined;
strategy: "token"; // required
chunk_size?: number | undefined;
chunk_overlap?: number | undefined;
}
Show Response
Show Response
{
"chunks": {
"text": str,
"index": float,
"metadata": { # optional
"start_index": Nullable[float],
"end_index": Nullable[float],
"token_count": Nullable[float],
},
},
}
{
chunks: {
text: string;
index: number;
metadata?: {
startIndex: number;
endIndex: number;
tokenCount: number;
};
};
}