Docs / Language and text

Search your own documents API

Upload documents, ask a question, get the best passages back: retrieval for your own AI app.

Make a collection, add documents (plain text or Markdown; take a PDF's text with POST /v1/pdf/text first), and query it: the documents are cut into passages, embedded with the multilingual model on this server, and each query's nearest passages are reranked by the cross-encoder. Collections are private to their secret, kept in memory for a day, up to 1,000 passages. The collection demo (secret demo) holds a few facts about India, for trying. Needs a free API key once keys are required (see /keys).

Base URL https://api.dharun.devNo key needed for most600 units a minute, 3000 with a free keyThis page as Markdown

Make a collection

POST/v1/rag

Send: Nothing, or {} .

Model endpoint: it will need a free API key, sent as Authorization: Bearer <key> or X-API-Key. Until the date on API keys it answers without one and says so in the X-Key-Notice header. With a key: 500 model requests a day.

What you send here is never written to the log, and the answer is not cached.

curl

curl -H "Content-Type: application/json" --data '{}' "https://api.dharun.dev/v1/rag?utm_medium=docs"

JavaScript

const response = await fetch("https://api.dharun.dev/v1/rag?utm_medium=docs", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({}),
});
const body = await response.json();
if (!response.ok) throw new Error(body.error.message);
console.log(body.data);

Python

import requests

response = requests.post("https://api.dharun.dev/v1/rag?utm_medium=docs", data="{}", headers={"Content-Type": "application/json"}, timeout=60)
body = response.json()
if not response.ok:
    raise RuntimeError(body["error"]["message"])
print(body["data"])

invoice.json

{}

Try it here

Change the values and send the request from your browser. Needs JavaScript.

Add documents

POST/v1/rag/{id}/documents

Send: JSON {"documents": [{"name": "...", "text": "..."}], "size": 800}: up to 2 MB of text.

What you send here is never written to the log, and the answer is not cached.

curl

curl -H "Content-Type: application/json" --data '{"documents": [{"name": "shop rules", "text": "Returns are accepted within 7 days with the bill."}]}' "https://api.dharun.dev/v1/rag/demo/documents?secret=demo&utm_medium=docs"

JavaScript

const response = await fetch("https://api.dharun.dev/v1/rag/demo/documents?secret=demo&utm_medium=docs", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({"documents": [{"name": "shop rules", "text": "Returns are accepted within 7 days with the bill."}]}),
});
const body = await response.json();
if (!response.ok) throw new Error(body.error.message);
console.log(body.data);

Python

import requests

response = requests.post("https://api.dharun.dev/v1/rag/demo/documents?secret=demo&utm_medium=docs", data="{\"documents\": [{\"name\": \"shop rules\", \"text\": \"Returns are accepted within 7 days with the bill.\"}]}", headers={"Content-Type": "application/json"}, timeout=60)
body = response.json()
if not response.ok:
    raise RuntimeError(body["error"]["message"])
print(body["data"])

invoice.json

{"documents": [{"name": "shop rules", "text": "Returns are accepted within 7 days with the bill."}]}

Try it here

Change the values and send the request from your browser. Needs JavaScript.

Response

{
  "data": {
    "added": 0,
    "passages": 6
  },
  "meta": {
    "note": "The demo collection is read-only. Make your own with POST /v1/rag."
  }
}

Ask a question

POST/v1/rag/{id}/query

Send: JSON {"query": "...", "top": 5, "rerank": true}.

What you send here is never written to the log, and the answer is not cached.

curl

curl -H "Content-Type: application/json" --data '{"query": "How many digits does a pincode have?", "top": 2}' "https://api.dharun.dev/v1/rag/demo/query?secret=demo&utm_medium=docs"

JavaScript

const response = await fetch("https://api.dharun.dev/v1/rag/demo/query?secret=demo&utm_medium=docs", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({"query": "How many digits does a pincode have?", "top": 2}),
});
const body = await response.json();
if (!response.ok) throw new Error(body.error.message);
console.log(body.data);

Python

import requests

response = requests.post("https://api.dharun.dev/v1/rag/demo/query?secret=demo&utm_medium=docs", data="{\"query\": \"How many digits does a pincode have?\", \"top\": 2}", headers={"Content-Type": "application/json"}, timeout=60)
body = response.json()
if not response.ok:
    raise RuntimeError(body["error"]["message"])
print(body["data"])

invoice.json

{"query": "How many digits does a pincode have?", "top": 2}

Try it here

Change the values and send the request from your browser. Needs JavaScript.

Response, with lists and long text shortened

{
  "data": {
    "passages": [
      {
        "document": "India API facts",
        "passage": 0,
        "text": "Pincodes are six digits. The first digit is the postal region, the first two the postal circle, and the first three the sorting district. Tamil Nadu's pincodes …",
        "similarity": 0.8904000000000001,
        "rerankScore": 0.997982
      },
      {
        "document": "India API facts",
        "passage": 2,
        "text": "A GSTIN is fifteen characters: the two-digit state code, the holder's PAN, an entity number, the letter Z by default, and a check character.",
        "similarity": 0.8344,
        "rerankScore": 0.023465
      }
    ],
    "query": "How many digits does a pincode have?",
    "reranked": true
  },
  "meta": {
    "note": "The passages nearest the query by embedding, then reranked by the cross-encoder. Give these to a language model as context, with their document names."
  }
}

Delete a collection

POST/v1/rag/{id}/delete

Send: Nothing, or {} .

What you send here is never written to the log, and the answer is not cached.

curl

curl -H "Content-Type: application/json" --data '{}' "https://api.dharun.dev/v1/rag/demo/delete?secret=demo&utm_medium=docs"

JavaScript

const response = await fetch("https://api.dharun.dev/v1/rag/demo/delete?secret=demo&utm_medium=docs", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({}),
});
const body = await response.json();
if (!response.ok) throw new Error(body.error.message);
console.log(body.data);

Python

import requests

response = requests.post("https://api.dharun.dev/v1/rag/demo/delete?secret=demo&utm_medium=docs", data="{}", headers={"Content-Type": "application/json"}, timeout=60)
body = response.json()
if not response.ok:
    raise RuntimeError(body["error"]["message"])
print(body["data"])

invoice.json

{}

Try it here

Change the values and send the request from your browser. Needs JavaScript.

Response

{
  "data": {
    "deleted": false,
    "id": "demo"
  },
  "meta": {
    "note": "The demo collection is never deleted."
  }
}

Using an AI assistant? Connect the MCP server and it can call this API by itself. Want every endpoint on one bench? Open the playground.