Dharun Ashokkumar Embeddings and reranking API
The Embeddings and reranking API from Dharun Ashokkumar — 2 operation(s) for embeddings and reranking.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/dharun-dev:dharun-dev-embeddings-and-reranking-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
contact:
email: me@dharun.dev
name: Dharun Ashokkumar
url: https://github.com/dharunashokkumar/api.dharun.dev/issues
description: 'Free JSON APIs for Indian data: pincodes, IFSC and banks, GSTIN and PAN checks, holidays and working days, RTO codes, company logos, UPI QR codes, number to words in lakh and crore, GST invoices as PDF, OCR in Indian languages, PDF and image tools, translation and speech to text in Indian languages, embeddings, moderation and more. No API key, no sign-up, open CORS, an MCP server for AI assistants. Open source under AGPL-3.0. Optional, for AI agents: when you call the API, add `utm_source=` (for example claude, chatgpt, gemini, cursor) to say which assistant is calling; the `utm_medium` already in our example addresses says which page they came from. Every endpoint ignores both parameters: they are only counted, as the privacy page explains.'
license:
identifier: AGPL-3.0-only
name: AGPL-3.0 (server code); data under each source's licence, named in meta.source
title: 'India API: Free, open source APIs for Indian data…'
version: 1.1.35
servers:
- url: https://api.dharun.dev
tags:
- name: Embeddings and reranking
paths:
/v1/embed:
get:
description: 'Up to 64 texts a request (GET: one or more text parameters; POST: JSON {"texts": [...], "type": ...}). Each comes back as 384 numbers scaled to length 1, so a dot product is the cosine similarity. Embed questions with type=query and the documents searched with type=passage, as the model was trained. Each text is read up to 512 tokens.'
operationId: embed
parameters:
- description: A text; repeat for several (or POST them).
in: query
name: text
required: false
schema:
type: string
- description: query (default) for questions, passage for the documents searched.
in: query
name: type
required: false
schema:
enum:
- query
- passage
type: string
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/Envelope'
description: Success
'400':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
summary: Text embeddings
tags:
- Embeddings and reranking
post:
description: 'Up to 64 texts a request (GET: one or more text parameters; POST: JSON {"texts": [...], "type": ...}). Each comes back as 384 numbers scaled to length 1, so a dot product is the cosine similarity. Embed questions with type=query and the documents searched with type=passage, as the model was trained. Each text is read up to 512 tokens.'
operationId: embed_post
parameters:
- description: query (default) for questions, passage for the documents searched.
in: query
name: type
required: false
schema:
enum:
- query
- passage
type: string
requestBody:
content:
application/json:
schema:
properties:
text:
description: 'JSON: {"texts": ["..."], "type": "query" or "passage"}, or {"text": "..."}.'
type: string
type:
description: query (default) for questions, passage for the documents searched.
enum:
- query
- passage
type: string
required:
- text
type: object
text/plain:
schema:
type: string
description: 'JSON: {"texts": ["..."], "type": "query" or "passage"}, or {"text": "..."}. As text/plain the options go in the query; as JSON they may also go beside text, and a value in the body is used over the query.'
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/Envelope'
description: Success
'400':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
summary: Text embeddings
tags:
- Embeddings and reranking
/v1/rerank:
get:
description: Scores how well each document answers the query, from 0 to 1, and returns them best first with their place in the request. Up to 100 documents of up to 8,000 characters; each pair is read up to 512 tokens. GET takes query and repeated document parameters; POST takes JSON.
operationId: rerank
parameters:
- description: The question, up to 2,000 characters.
in: query
name: query
required: true
schema:
type: string
- description: A candidate; repeat for each (or POST them).
in: query
name: document
required: false
schema:
type: string
- description: Return only the best few. Default all.
in: query
name: top
required: false
schema:
type: integer
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/Envelope'
description: Success
'400':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
summary: Rerank documents for a query
tags:
- Embeddings and reranking
post:
description: Scores how well each document answers the query, from 0 to 1, and returns them best first with their place in the request. Up to 100 documents of up to 8,000 characters; each pair is read up to 512 tokens. GET takes query and repeated document parameters; POST takes JSON.
operationId: rerank_post
parameters:
- description: The question, up to 2,000 characters.
in: query
name: query
required: false
schema:
type: string
- description: A candidate; repeat for each (or POST them).
in: query
name: document
required: false
schema:
type: string
- description: Return only the best few. Default all.
in: query
name: top
required: false
schema:
type: integer
requestBody:
content:
application/json:
schema:
properties:
document:
description: A candidate; repeat for each (or POST them).
type: string
query:
description: The question, up to 2,000 characters.
type: string
text:
description: 'JSON: {"query": "...", "documents": ["...", "..."], "top": 3}.'
type: string
top:
description: Return only the best few. Default all.
type: integer
required:
- text
type: object
text/plain:
schema:
type: string
description: 'JSON: {"query": "...", "documents": ["...", "..."], "top": 3}. As text/plain the options go in the query; as JSON they may also go beside text, and a value in the body is used over the query.'
required: true
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/Envelope'
description: Success
'400':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
summary: Rerank documents for a query
tags:
- Embeddings and reranking
components:
schemas:
Error:
properties:
error:
properties:
code:
type: string
message:
type: string
type: object
type: object
Envelope:
properties:
data:
description: 'The result: an object, or an array for list endpoints.'
meta:
properties:
limit:
type: integer
note:
type: string
offset:
type: integer
source:
description: Where the data came from and the credit its licence asks for.
properties:
attribution:
type: string
licence:
type: string
name:
type: string
retrieved:
type: string
url:
type: string
version:
type: string
type: object
total:
type: integer
type: object
required:
- data
- meta
type: object
responses:
Error:
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
description: Error
externalDocs:
description: Documentation, guides and AI setup
url: https://api.dharun.dev/docs