Knowledge Bases

Query Relevant Chunks

Description

Query a knowledge base for text chunks that are most semantically relevant to the query.

Details

Given a query expressed as an embedding, this API runs a similarity search amongst the embeddings indexed in the knowledge base to find the most relevant chunk embeddings. To use this API, specify the knowledge_base_id of the knowledge base you want to query, pass in the natural language query that you want to search for, specify the value top_k, which is the number of similar chunks that will be returned, and specify whether you want the returned chunks to include_embeddings.

Similarity search is used to efficiently find, retrieve, and rank chunks based on their similarity to a given query, which is also expressed as an embedding. Similarity scores ( using the cosine similarity metric) are calculated between each chunk embedding and the embedded query, and the chunks are ranked based on similarity score. The top-ranked chunks are returned as the query results.

We are using the Hierarchical Navigable Small World (HNSW) algorithm to perform a k nearest neighbors search in the vector space. This algorithm returns an estimate of the best k nearest neighbors and is optimized for datasets with hundreds of thousands of vectors. You can read more about the specifics of this algorithm here.

Backwards Compatibility

V2 and V1 Knowledge Bases are entirely separate and not backwards compatible. Users who have existing V1 knowledge bases will need to migrate their data to V2 knowledge bases.

POST

knowledge-bases

{knowledge_base_id}

query

import SGPClient from 'sgp';

const client = new SGPClient({
  apiKey: process.env['SGP_API_KEY'], // This is the default and can be omitted
});

async function main() {
  // Automatically fetches more pages as needed.
  for await (const chunk of client.knowledgeBases.query('knowledge_base_id', { query: 'query', top_k: 1 })) {
    console.log(chunk.chunk_id);
  }
}

main();

{
  "chunks": [
    {
      "chunk_id": "<string>",
      "text": "<string>",
      "embedding": [
        123
      ],
      "metadata": {},
      "user_supplied_metadata": {},
      "attachment_url": "<string>",
      "title": "<string>",
      "score": 123
    }
  ],
  "started_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "request_id": "<string>"
}

Authorizations

x-api-key

string

header

required

Path Parameters

knowledge_base_id

string

required

Body

application/json

query

string

required

The natural language query to be answered by referencing the data ingested into the knowledge base

top_k

integer

required

Number of chunks to return. Must be greater than 0 if specified. If not specified, all chunks will be returned.

Required range: 0 < x < 10000

include_embeddings

boolean

default:

true

Whether or not to include the embeddings for each chunk

metadata_filters

object

Optional filter by metadata fields, encoded as a JSON object

wildcard_filters

object

Optional wildcard filter for fields. Only fields that are part of the metadata will be accepted.

verbose

boolean

default:

false

Enable or disable verbose logging

Response

200

application/json

Successful Response

chunks

object[]

required

An ordered list of the k most similar chunks and their similarity scores from most to least similar

started_at

string

Timestamp at which the query was begun by the server.

completed_at

string

Timestamp at which the query was completed by the server.

request_id

string

query request ID for verbose logging

Get Chunks Delete Knowledge Base Data Source Connection

import SGPClient from 'sgp';

const client = new SGPClient({
  apiKey: process.env['SGP_API_KEY'], // This is the default and can be omitted
});

async function main() {
  // Automatically fetches more pages as needed.
  for await (const chunk of client.knowledgeBases.query('knowledge_base_id', { query: 'query', top_k: 1 })) {
    console.log(chunk.chunk_id);
  }
}

main();

{
  "chunks": [
    {
      "chunk_id": "<string>",
      "text": "<string>",
      "embedding": [
        123
      ],
      "metadata": {},
      "user_supplied_metadata": {},
      "attachment_url": "<string>",
      "title": "<string>",
      "score": 123
    }
  ],
  "started_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "request_id": "<string>"
}

Knowledge Bases

Chunks

Agents

Completions

Chat Completions

Models

Users

Accounts

Organizations

Question Sets

Evaluations

Evaluation Configs

Evaluation Datasets

Studio Projects

Application Specs

Questions

Knowledge Base Data Sources

Model Templates V3 (Beta)

Model server

API Reference

Fine Tuning Jobs V3 (Beta)

Training Datasets V3 (Beta)

package deployments

Beta

Applications

ChatThreads

Interactions

MonitoringDashboard

Chat Themes

account groups

account

Guardrails

Query Relevant Chunks

Description

Details

Backwards Compatibility

Authorizations

Path Parameters

Body

Response