Search Index, REST: SearchIndex.List

Статья создана

Обновлена 17 декабря 2024 г.

HTTP request
Query parameters
Response
SearchIndex
ExpirationConfig
TextSearchIndex
ChunkingStrategy
StaticChunkingStrategy
VectorSearchIndex
HybridSearchIndex
CombinationStrategy
MeanCombinationStrategy
ReciprocalRankFusionCombinationStrategy

List search indexes in a specific folder.

HTTP request

GET https://rest-assistant.api.cloud.yandex.net/assistants/v1/searchIndex

Query parameters

Request message for listing search indexes in a specific folder.

Field	Description
folderId	string Required field. Folder ID from which to list search indexes.
pageSize	string (int64) Maximum number of threads to return per page.
pageToken	string Token to retrieve the next page of results.

Response

HTTP Code: 200 - OK

{
  "indices": [
    {
      "id": "string",
      "folderId": "string",
      "name": "string",
      "description": "string",
      "createdBy": "string",
      "createdAt": "string",
      "updatedBy": "string",
      "updatedAt": "string",
      "expirationConfig": {
        "expirationPolicy": "string",
        "ttlDays": "string"
      },
      "expiresAt": "string",
      "labels": "object",
      // Includes only one of the fields `textSearchIndex`, `vectorSearchIndex`, `hybridSearchIndex`
      "textSearchIndex": {
        "chunkingStrategy": {
          // Includes only one of the fields `staticStrategy`
          "staticStrategy": {
            "maxChunkSizeTokens": "string",
            "chunkOverlapTokens": "string"
          }
          // end of the list of possible fields
        }
      },
      "vectorSearchIndex": {
        "docEmbedderUri": "string",
        "queryEmbedderUri": "string",
        "chunkingStrategy": {
          // Includes only one of the fields `staticStrategy`
          "staticStrategy": {
            "maxChunkSizeTokens": "string",
            "chunkOverlapTokens": "string"
          }
          // end of the list of possible fields
        }
      },
      "hybridSearchIndex": {
        "textSearchIndex": {
          "chunkingStrategy": {
            // Includes only one of the fields `staticStrategy`
            "staticStrategy": {
              "maxChunkSizeTokens": "string",
              "chunkOverlapTokens": "string"
            }
            // end of the list of possible fields
          }
        },
        "vectorSearchIndex": {
          "docEmbedderUri": "string",
          "queryEmbedderUri": "string",
          "chunkingStrategy": {
            // Includes only one of the fields `staticStrategy`
            "staticStrategy": {
              "maxChunkSizeTokens": "string",
              "chunkOverlapTokens": "string"
            }
            // end of the list of possible fields
          }
        },
        "chunkingStrategy": {
          // Includes only one of the fields `staticStrategy`
          "staticStrategy": {
            "maxChunkSizeTokens": "string",
            "chunkOverlapTokens": "string"
          }
          // end of the list of possible fields
        },
        "normalizationStrategy": "string",
        "combinationStrategy": {
          // Includes only one of the fields `meanCombination`, `rrfCombination`
          "meanCombination": {
            "meanEvaluationTechnique": "string",
            "weights": [
              "string"
            ]
          },
          "rrfCombination": {
            "k": "string"
          }
          // end of the list of possible fields
        }
      }
      // end of the list of possible fields
    }
  ],
  "nextPageToken": "string"
}

Response message for the list operation.

Field

Description

indices[]

SearchIndex

List of search indexes in the specified folder.

nextPageToken

string

Token to retrieve the next page of results.

SearchIndex

Represents a search index used to store and query data, either using traditional keyword-based text search or vector-based search mechanisms.

Field	Description
id	string Unique identifier of the search index.
folderId	string ID of the folder that the search index belongs to.
name	string Name of the search index.
description	string Description of the search index.
createdBy	string Identifier of the subject who created this search index.
createdAt	string (date-time) Timestamp representing when the search index was created. String in RFC3339 text format. The range of possible values is from `0001-01-01T00:00:00Z` to `9999-12-31T23:59:59.999999999Z`, i.e. from 0 to 9 digits for fractions of a second. To work with values in this field, use the APIs described in the Protocol Buffers reference. In some languages, built-in datetime utilities do not support nanosecond precision (9 digits).
updatedBy	string Identifier of the subject who last updated this search index.
updatedAt	string (date-time) Timestamp representing the last time this search index was updated. String in RFC3339 text format. The range of possible values is from `0001-01-01T00:00:00Z` to `9999-12-31T23:59:59.999999999Z`, i.e. from 0 to 9 digits for fractions of a second. To work with values in this field, use the APIs described in the Protocol Buffers reference. In some languages, built-in datetime utilities do not support nanosecond precision (9 digits).
expirationConfig	ExpirationConfig Configuration for the expiration of the search index, defining when and how the search index will expire.
expiresAt	string (date-time) Timestamp representing when the search index will expire. String in RFC3339 text format. The range of possible values is from `0001-01-01T00:00:00Z` to `9999-12-31T23:59:59.999999999Z`, i.e. from 0 to 9 digits for fractions of a second. To work with values in this field, use the APIs described in the Protocol Buffers reference. In some languages, built-in datetime utilities do not support nanosecond precision (9 digits).
labels	object (map<string, string>) Set of key-value pairs that can be used to organize and categorize the search index.
textSearchIndex	TextSearchIndex Keyword-based text search index configuration. This type of index is used for traditional text search, where documents are indexed based on their keywords. Includes only one of the fields `textSearchIndex`, `vectorSearchIndex`, `hybridSearchIndex`. Type of the search index. It can be either a traditional keyword-based text search or a vector-based search.
vectorSearchIndex	VectorSearchIndex Vector-based search index configuration. This type is used for vector search, where documents are indexed using vector embeddings. Includes only one of the fields `textSearchIndex`, `vectorSearchIndex`, `hybridSearchIndex`. Type of the search index. It can be either a traditional keyword-based text search or a vector-based search.
hybridSearchIndex	HybridSearchIndex Hybrid (vector-based + keyword-based) search index configuration This type is used for hybrid search, where documents are indexed using both keyword-based and vector-based search mechanisms. Includes only one of the fields `textSearchIndex`, `vectorSearchIndex`, `hybridSearchIndex`. Type of the search index. It can be either a traditional keyword-based text search or a vector-based search.

ExpirationConfig

Field

Description

expirationPolicy

enum (ExpirationPolicy)

EXPIRATION_POLICY_UNSPECIFIED
STATIC
SINCE_LAST_ACTIVE

ttlDays

string (int64)

TextSearchIndex

Defines the configuration for a traditional keyword-based text search index.

Field

Description

chunkingStrategy

ChunkingStrategy

Chunking strategy used to split text into smaller chunks before indexing.
In the case of text search, tokens are individual text characters.

ChunkingStrategy

Defines a general strategy for chunking text into smaller segments.
Currently, only StaticChunkingStrategy is supported.

Field

Description

staticStrategy

StaticChunkingStrategy

Includes only one of the fields staticStrategy.

StaticChunkingStrategy

Defines a chunking strategy where chunks are created with a fixed maximum chunk size and an overlap between consecutive chunks.

Field

Description

maxChunkSizeTokens

string (int64)

The maximum number of tokens allowed in a single chunk.
Constraints: must be within the range [100, 2048].
Default value: 800

chunkOverlapTokens

string (int64)

The number of tokens that should overlap between consecutive chunks.
This allows for some context from the previous chunk to be included in the next chunk.
Constraints: must be less than or equal to half of max_chunk_size_tokens.
Default value: 400

VectorSearchIndex

Defines the configuration for a vector-based search index. This type uses embeddings to represent documents and queries.

Field	Description
docEmbedderUri	string The ID of the model to be used for obtaining document text embeddings.
queryEmbedderUri	string The ID of the model to be used for obtaining query text embeddings.
chunkingStrategy	ChunkingStrategy Chunking strategy used to split text into smaller chunks before indexing. In the case of vector search, tokens are produced by the tokenizer from the embedding model.

HybridSearchIndex

Defines the configuration for a hybrid (vector-based + keyword-based) search index. This type uses both embeddings and keyword-based search to represent documents and queries.

Field	Description
textSearchIndex	TextSearchIndex Configuration for a traditional keyword-based text search index.
vectorSearchIndex	VectorSearchIndex Configuration for a vector-based search index.
chunkingStrategy	ChunkingStrategy Common chunking strategy that applies to both text and vector search indexes. If provided, it overrides the individual chunking strategies in both `text_search_index` and `vector_search_index`. In this case, both text and vector search will use token-based chunking, where tokens are produced by the tokenizer of the embedding model.
normalizationStrategy	enum (NormalizationStrategy) Normalization strategy for relevance scores from different indices. Default is MIN_MAX_STRATEGY `NORMALIZATION_STRATEGY_UNSPECIFIED` `MIN_MAX`: https://en.wikipedia.org/wiki/Feature_scaling#Rescaling_(min-max_normalization) `L2`: https://en.wikipedia.org/wiki/Cosine_similarity#L2-normalized_Euclidean_distance
combinationStrategy	CombinationStrategy Combination strategy for merging rankings from different indices. Default is arithmetic mean

CombinationStrategy

Combination strategy for merging rankings from different indices

Field

Description

meanCombination

MeanCombinationStrategy

Includes only one of the fields meanCombination, rrfCombination.

rrfCombination

ReciprocalRankFusionCombinationStrategy

Includes only one of the fields meanCombination, rrfCombination.

MeanCombinationStrategy

Field

Description

meanEvaluationTechnique

enum (MeanEvaluationTechnique)

Technique for averaging relevance scores from different indices. Default is ARITHMETIC

MEAN_EVALUATION_TECHNIQUE_UNSPECIFIED
ARITHMETIC: https://en.wikipedia.org/wiki/Arithmetic_mean
GEOMETRIC: https://en.wikipedia.org/wiki/Geometric_mean
HARMONIC: https://en.wikipedia.org/wiki/Harmonic_mean

weights[]

string

Weights used for evaluating the weighted mean of relevance scores. The sum of the values must equal 1.0
If not provided, all scores are given equal weight

ReciprocalRankFusionCombinationStrategy

https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf

Field

Description

string (int64)

The parameter k for RRFscore. Default is 60

Search Index, REST: SearchIndex.List

HTTP requestHTTP request

Query parametersQuery parameters

ResponseResponse

SearchIndexSearchIndex

ExpirationConfigExpirationConfig

TextSearchIndexTextSearchIndex

ChunkingStrategyChunkingStrategy

StaticChunkingStrategyStaticChunkingStrategy

VectorSearchIndexVectorSearchIndex

HybridSearchIndexHybridSearchIndex

CombinationStrategyCombinationStrategy

MeanCombinationStrategyMeanCombinationStrategy

ReciprocalRankFusionCombinationStrategyReciprocalRankFusionCombinationStrategy

Была ли статья полезна?

HTTP request

Query parameters

Response

SearchIndex

ExpirationConfig

TextSearchIndex

ChunkingStrategy

StaticChunkingStrategy

VectorSearchIndex

HybridSearchIndex

CombinationStrategy

MeanCombinationStrategy

ReciprocalRankFusionCombinationStrategy