Get Config

Retrieve available readers, chunkers, and configuration options for content processing. This endpoint provides metadata about supported file types, processing strategies, and filters.

GET /knowledge/config

Get Config

cURL

curl --request GET \
  --url https://api.example.com/knowledge/config \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.example.com/knowledge/config"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.example.com/knowledge/config', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/knowledge/config",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/knowledge/config"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.example.com/knowledge/config")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/knowledge/config")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

200

{
  "readers": {
    "website": {
      "id": "website",
      "name": "WebsiteReader",
      "description": "Reads website files",
      "chunkers": [
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker",
        "SemanticChunker",
        "FixedSizeChunker"
      ]
    },
    "firecrawl": {
      "id": "firecrawl",
      "name": "FirecrawlReader",
      "description": "Reads firecrawl files",
      "chunkers": [
        "SemanticChunker",
        "FixedSizeChunker",
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker"
      ]
    },
    "youtube": {
      "id": "youtube",
      "name": "YoutubeReader",
      "description": "Reads youtube files",
      "chunkers": [
        "RecursiveChunker",
        "AgenticChunker",
        "DocumentChunker",
        "SemanticChunker",
        "FixedSizeChunker"
      ]
    },
    "web_search": {
      "id": "web_search",
      "name": "WebSearchReader",
      "description": "Reads web_search files",
      "chunkers": [
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker",
        "SemanticChunker",
        "FixedSizeChunker"
      ]
    },
    "arxiv": {
      "id": "arxiv",
      "name": "ArxivReader",
      "description": "Reads arxiv files",
      "chunkers": [
        "FixedSizeChunker",
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker",
        "SemanticChunker"
      ]
    },
    "csv": {
      "id": "csv",
      "name": "CsvReader",
      "description": "Reads csv files",
      "chunkers": [
        "RowChunker",
        "FixedSizeChunker",
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker"
      ]
    },
    "docx": {
      "id": "docx",
      "name": "DocxReader",
      "description": "Reads docx files",
      "chunkers": [
        "DocumentChunker",
        "FixedSizeChunker",
        "SemanticChunker",
        "AgenticChunker",
        "RecursiveChunker"
      ]
    },
    "gcs": {
      "id": "gcs",
      "name": "GcsReader",
      "description": "Reads gcs files",
      "chunkers": [
        "FixedSizeChunker",
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker",
        "SemanticChunker"
      ]
    },
    "json": {
      "id": "json",
      "name": "JsonReader",
      "description": "Reads json files",
      "chunkers": [
        "FixedSizeChunker",
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker",
        "SemanticChunker"
      ]
    },
    "markdown": {
      "id": "markdown",
      "name": "MarkdownReader",
      "description": "Reads markdown files",
      "chunkers": [
        "MarkdownChunker",
        "DocumentChunker",
        "AgenticChunker",
        "RecursiveChunker",
        "SemanticChunker",
        "FixedSizeChunker"
      ]
    },
    "pdf": {
      "id": "pdf",
      "name": "PdfReader",
      "description": "Reads pdf files",
      "chunkers": [
        "DocumentChunker",
        "FixedSizeChunker",
        "AgenticChunker",
        "SemanticChunker",
        "RecursiveChunker"
      ]
    },
    "text": {
      "id": "text",
      "name": "TextReader",
      "description": "Reads text files",
      "chunkers": [
        "CodeChunker",
        "FixedSizeChunker",
        "AgenticChunker",
        "DocumentChunker",
        "RecursiveChunker",
        "SemanticChunker"
      ]
    }
  },
  "readersForType": {
    "url": [
      "url",
      "website",
      "firecrawl",
      "youtube",
      "web_search",
      "gcs"
    ],
    "youtube": [
      "youtube"
    ],
    "text": [
      "web_search"
    ],
    "topic": [
      "arxiv"
    ],
    "file": [
      "csv",
      "gcs"
    ],
    ".csv": [
      "csv",
      "field_labeled_csv"
    ],
    ".xlsx": [
      "excel"
    ],
    ".xls": [
      "excel"
    ],
    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": [
      "excel"
    ],
    "application/vnd.ms-excel": [
      "excel"
    ],
    ".docx": [
      "docx"
    ],
    ".doc": [
      "docx"
    ],
    ".json": [
      "json"
    ],
    ".md": [
      "markdown"
    ],
    ".pdf": [
      "pdf"
    ],
    ".txt": [
      "text"
    ]
  },
  "chunkers": {
    "AgenticChunker": {
      "key": "AgenticChunker",
      "name": "AgenticChunker",
      "description": "Chunking strategy that uses an LLM to determine natural breakpoints in the text",
      "metadata": {
        "chunk_size": 5000
      }
    },
    "CodeChunker": {
      "key": "CodeChunker",
      "name": "CodeChunker",
      "description": "The CodeChunker splits code into chunks based on its structure, leveraging Abstract Syntax Trees (ASTs) to create contextually relevant segments",
      "metadata": {
        "chunk_size": 2048
      }
    },
    "DocumentChunker": {
      "key": "DocumentChunker",
      "name": "DocumentChunker",
      "description": "A chunking strategy that splits text based on document structure like paragraphs and sections",
      "metadata": {
        "chunk_size": 5000,
        "chunk_overlap": 0
      }
    },
    "FixedSizeChunker": {
      "key": "FixedSizeChunker",
      "name": "FixedSizeChunker",
      "description": "Chunking strategy that splits text into fixed-size chunks with optional overlap",
      "metadata": {
        "chunk_size": 5000,
        "chunk_overlap": 0
      }
    },
    "MarkdownChunker": {
      "key": "MarkdownChunker",
      "name": "MarkdownChunker",
      "description": "A chunking strategy that splits markdown based on structure like headers, paragraphs and sections",
      "metadata": {
        "chunk_size": 5000,
        "chunk_overlap": 0
      }
    },
    "RecursiveChunker": {
      "key": "RecursiveChunker",
      "name": "RecursiveChunker",
      "description": "Chunking strategy that recursively splits text into chunks by finding natural break points",
      "metadata": {
        "chunk_size": 5000,
        "chunk_overlap": 0
      }
    },
    "RowChunker": {
      "key": "RowChunker",
      "name": "RowChunker",
      "description": "RowChunking chunking strategy",
      "metadata": {}
    },
    "SemanticChunker": {
      "key": "SemanticChunker",
      "name": "SemanticChunker",
      "description": "Chunking strategy that splits text into semantic chunks using chonkie",
      "metadata": {
        "chunk_size": 5000
      }
    }
  },
  "vector_dbs": [
    {
      "id": "vector_db_1",
      "name": "Vector DB 1",
      "description": "Vector DB 1 description",
      "search_types": [
        "vector",
        "keyword",
        "hybrid"
      ]
    }
  ],
  "filters": [
    "filter_tag_1",
    "filter_tag2"
  ]
}

{
  "detail": "Bad request",
  "error_code": "BAD_REQUEST"
}

{
  "detail": "Unauthenticated access",
  "error_code": "UNAUTHENTICATED"
}

{
  "detail": "Not found",
  "error_code": "NOT_FOUND"
}

{
  "detail": "Validation error",
  "error_code": "VALIDATION_ERROR"
}

{
  "detail": "Internal server error",
  "error_code": "INTERNAL_SERVER_ERROR"
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

db_id · string | null

Database ID to use

knowledge_id · string | null

Knowledge base ID to use

Response

200

application/json

Knowledge configuration retrieved successfully

readers · Readers · object | null

Available content readers

Show child attributes

readersForType · Readersfortype · object | null

Mapping of content types to reader IDs

Show child attributes

chunkers · Chunkers · object | null

Available chunking strategies

Show child attributes

filters · string[] | null

Available filter tags

vector_dbs · VectorDbSchema · object[] | null

Configured vector databases

Show child attributes

remote_content_sources · RemoteContentSourceSchema · object[] | null

Configured remote content sources (S3, GCS, SharePoint, GitHub)

Show child attributes