Pricing

Pay per event

Try for free

Go to Apify Store

Text Chunker & Embeddings for RAG (LangChain, LlamaIndex)

Try for free

Split Markdown, text and web pages into heading-aware, token-sized chunks with overlap, and optionally embed them with a local CPU model (bge-small, MiniLM). No API key. Output works with LangChain, LlamaIndex, Pinecone, Qdrant and pgvector.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Nick Hellmich

Actor stats

Bookmarked

Total users

Monthly active users

8 days ago

Last modified

Categories

Developer tools

You can access the Text Chunker & Embeddings for RAG (LangChain, LlamaIndex) programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4# Replace '<YOUR_API_TOKEN>' with your token.
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7# Prepare the Actor input
8run_input = {
9    "documents": [{
10            "source": "help-center/refunds.md",
11            "text": """# Refund policy
12
13Customers can request a full refund within 30 days of purchase. Refunds go back to the original payment method within 5 business days.
14
15## Exceptions
16
17Gift cards and downloadable software are not refundable once the license key has been revealed.
18
19# Shipping
20
21Orders ship within 2 business days. Express shipping arrives in 1 to 2 days in the continental US.""",
22            "metadata": { "lang": "en" },
23        }],
24    "embeddingModel": "BAAI/bge-small-en-v1.5",
25}
26
27# Run the Actor and wait for it to finish
28run = client.actor("steady_kahikatea/text-chunker-embeddings").call(run_input=run_input)
29
30# Fetch and print Actor results from the run's dataset (if there are any)
31print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
32for item in client.dataset(run.default_dataset_id).iterate_items():
33    print(item)
34
35# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

Text Chunker & Embeddings for RAG: LangChain, LlamaIndex API in Python

The Apify API client for Python is the official library that allows you to use Text Chunker & Embeddings for RAG (LangChain, LlamaIndex) API in Python, providing convenience functions and automatic retries on errors.

Install the apify-client

$pip install apify-client

Other API clients include:

Text Chunker & Embeddings for RAG (LangChain, LlamaIndex) API in JavaScript

Text Chunker & Embeddings for RAG (LangChain, LlamaIndex) API through CLI

Text Chunker & Embeddings for RAG (LangChain, LlamaIndex) OpenAPI definition

Text Chunker & Embeddings for RAG (LangChain, LlamaIndex) API

Pinecone Integration

apify/pinecone-integration

This integration transfers data from Apify Actors to a Pinecone and is a good starting point for a question-answering, search, or RAG use case.

Apify

558

3.2

(6)

Qdrant Integration

apify/qdrant-integration

Transfer data from Apify Actors to a Qdrant vector database.

Apify

5.0

(7)

PGVector Integration

apify/pgvector-integration

This integration transfers data from Apify Actors to a Postgres SQL database (with PGVector extension).

Apify

4.6

(5)

Docs to Markdown for RAG (PDF, Word, PowerPoint, Excel)

tillwork/docs-to-markdown

Turn PDF, Word, PowerPoint, Excel, CSV and HTML files into clean Markdown with real tables, then split it into token-counted chunks with heading paths, ready for embeddings, RAG and AI agents.

Kapil sarma

Document Text Extractor: PDF, Word, Excel to Markdown

pipwort/document-text-extractor

Turn PDF, DOCX, PPTX, XLSX, HTML, CSV and EPUB files into clean Markdown or plain text, with page counts, metadata and optional RAG-ready chunks. Failed documents are free.

Pipwort Data

Documents to Markdown for LLMs: PDF, Office, HTML, OCR

rado-dev/documents-to-llm-markdown

Convert PDF, Word, PowerPoint, Excel, HTML, text and scanned documents into clean Markdown with tables, token counts and RAG-ready chunks with page numbers. Tesseract OCR for scans. Failed documents are free.

RADO

PDF to Text and Markdown (No OCR, Pay per PDF)

ataism/pdf-to-text

Convert your PDFs (URLs or uploads) to clean text and markdown with page markers and RAG chunks. $0.0025/PDF, no start fee. No OCR.

Kaizoku Data

Image to Text OCR – 100+ Languages, Scanned PDFs, Word Boxes

kris_fili/image-to-text-ocr

Extract text from photos, scans, screenshots and scanned PDFs with Tesseract OCR in 100+ languages. Bulk URLs or uploads, confidence scores, auto-rotation, optional line and word bounding boxes.

Krzysztof Filipiak

PDF & DOCX to Markdown Converter for AI Agents

owlabee/pdf-to-markdown

Convert PDF, DOCX, HTML and text documents from URLs into clean Markdown with headings, lists, tables, links and metadata, plus optional heading-aware RAG chunks and OCR for scanned pages. No browser, no external API. Pay per page converted ($0.001).

Owlabee

PDF to Text and Markdown Extractor with Reading Order

bepolabs/pdf-to-text

Get headings, lists and body text from a stack of PDFs. Running headers, footers and numbers are stripped; chunks of a size you set carry their section path.