> ## Documentation Index > Fetch the complete documentation index at: https://docs.trieve.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Dataset > Dataset will be created in the org specified via the TR-Organization header. Auth'ed user must be an owner of the organization to create a dataset. ## OpenAPI ````yaml post /api/dataset openapi: 3.0.3 info: title: Trieve API description: >- Trieve OpenAPI Specification. This document describes all of the operations available through the Trieve API. contact: name: Trieve Team url: https://trieve.ai email: developers@trieve.ai license: name: BSL url: https://github.com/devflowinc/trieve/blob/main/LICENSE.txt version: 0.13.0 servers: - url: https://api.trieve.ai description: Production server - url: http://localhost:8090 description: Local development server security: [] tags: - name: Invitation description: Invitation endpoint. Exists to invite users to an organization. - name: Auth description: Authentication endpoint. Serves to register and authenticate users. - name: User description: User endpoint. Enables you to modify user roles and information. - name: Organization description: >- Organization endpoint. Enables you to modify organization roles and information. - name: Dataset description: >- Dataset endpoint. Datasets belong to organizations and hold configuration information for both client and server. Datasets contain chunks and chunk groups. - name: Chunk description: >- Chunk endpoint. Think of chunks as individual searchable units of information. The majority of your integration will likely be with the Chunk endpoint. - name: Chunk Group description: >- Chunk groups endpoint. Think of a chunk_group as a bookmark folder within the dataset. - name: Crawl description: Crawl endpoint. Used to create and manage crawls for datasets. - name: File description: >- File endpoint. When files are uploaded, they are stored in S3 and broken up into chunks with text extraction from Apache Tika. You can upload files of pretty much any type up to 1GB in size. See chunking algorithm details at `docs.trieve.ai` for more information on how chunking works. Improved default chunking is on our roadmap. - name: Events description: >- Notifications endpoint. Files are uploaded asynchronously and events are sent to the user when the upload is complete. - name: Topic description: >- Topic chat endpoint. Think of topics as the storage system for gen-ai chat memory. Gen AI messages belong to topics. - name: Message description: >- Message chat endpoint. Messages are units belonging to a topic in the context of a chat with a LLM. There are system, user, and assistant messages. - name: Stripe description: >- Stripe endpoint. Used for the managed SaaS version of this app. Eventually this will become a micro-service. Reach out to the team using contact info found at `docs.trieve.ai` for more information. - name: Health description: Health check endpoint. Used to check if the server is up and running. - name: Metrics description: Metrics endpoint. Used to get information for monitoring - name: Analytics description: Analytics endpoint. Used to get information for search and RAG analytics - name: Experiment description: Experiment endpoint. Used to create and manage experiments paths: /api/dataset: post: tags: - Dataset summary: Create Dataset description: >- Dataset will be created in the org specified via the TR-Organization header. Auth'ed user must be an owner of the organization to create a dataset. operationId: create_dataset parameters: - name: TR-Organization in: header description: The organization id to use for the request required: true schema: type: string format: uuid requestBody: description: JSON request payload to create a new dataset content: application/json: schema: $ref: '#/components/schemas/CreateDatasetReqPayload' required: true responses: '200': description: Dataset created successfully content: application/json: schema: $ref: '#/components/schemas/Dataset' '400': description: Service error relating to creating the dataset content: application/json: schema: $ref: '#/components/schemas/ErrorResponseBody' security: - ApiKey: - owner components: schemas: CreateDatasetReqPayload: type: object required: - dataset_name properties: dataset_name: type: string description: Name of the dataset. server_configuration: allOf: - $ref: '#/components/schemas/DatasetConfigurationDTO' nullable: true tracking_id: type: string description: >- Optional tracking ID for the dataset. Can be used to track the dataset in external systems. Must be unique within the organization. Strongly recommended to not use a valid uuid value as that will not work with the TR-Dataset header. nullable: true example: dataset_name: My Dataset organization_id: 00000000-0000-0000-0000-000000000000 server_configuration: AIMON_RERANKER_TASK_DEFINITION: >- Your task is to grade the relevance of context document(s) against the specified user query. BM25_AVG_LEN: 256 BM25_B: 0.75 BM25_ENABLED: true BM25_K: 0.75 DISTANCE_METRIC: cosine EMBEDDING_BASE_URL: https://api.openai.com/v1 EMBEDDING_MODEL_NAME: text-embedding-3-small EMBEDDING_QUERY_PREFIX: '' EMBEDDING_SIZE: 1536 FREQUENCY_PENALTY: 0 FULLTEXT_ENABLED: true INDEXED_ONLY: false LLM_BASE_URL: https://api.openai.com/v1 LLM_DEFAULT_MODEL: gpt-3.5-turbo-1106 LOCKED: false MAX_LIMIT: 10000 MESSAGE_TO_QUERY_PROMPT: >+ Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: N_RETRIEVALS_TO_INCLUDE: 8 PRESENCE_PENALTY: 0 QDRANT_ONLY: false RAG_PROMPT: >- Use the following retrieved documents to respond briefly and accurately: SEMANTIC_ENABLED: true STOP_TOKENS: - |+ - |+ SYSTEM_PROMPT: You are a helpful assistant TEMPERATURE: 0.5 USE_MESSAGE_TO_QUERY_PROMPT: false Dataset: type: object required: - id - name - created_at - updated_at - organization_id - server_configuration - deleted properties: created_at: type: string format: date-time description: Timestamp of the creation of the dataset deleted: type: integer format: int32 description: >- Flag to indicate if the dataset has been deleted. Deletes are handled async after the flag is set so as to avoid expensive search index compaction. id: type: string format: uuid description: >- Unique identifier of the dataset, auto-generated uuid created by Trieve name: type: string description: Name of the dataset organization_id: type: string format: uuid description: Unique identifier of the organization that owns the dataset server_configuration: description: Configuration of the dataset for RAG, embeddings, BM25, etc. tracking_id: type: string description: >- Tracking ID of the dataset, can be any string, determined by the user. Tracking ID's are unique identifiers for datasets within an organization. They are designed to match the unique identifier of the dataset in the user's system. nullable: true updated_at: type: string format: date-time description: Timestamp of the last update of the dataset example: created_at: '2021-01-01 00:00:00.000' id: e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3 name: Trieve organization_id: e3e3e3e3-e3e3-e3e3-e3e3-e3e3e3e3e3e3 server_configuration: AIMON_RERANKER_TASK_DEFINITION: >- Your task is to grade the relevance of context document(s) against the specified user query. BM25_AVG_LEN: 256 BM25_B: 0.75 BM25_ENABLED: true BM25_K: 0.75 DISTANCE_METRIC: cosine EMBEDDING_BASE_URL: https://embedding.trieve.ai EMBEDDING_MODEL_NAME: jina-base-en EMBEDDING_QUERY_PREFIX: '' EMBEDDING_SIZE: 768 FREQUENCY_PENALTY: 0 FULLTEXT_ENABLED: true INDEXED_ONLY: false LLM_BASE_URL: https://api.openai.com/v1 LLM_DEFAULT_MODEL: gpt-4o LOCKED: false MAX_LIMIT: 10000 MESSAGE_TO_QUERY_PROMPT: >+ Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: N_RETRIEVALS_TO_INCLUDE: 8 PRESENCE_PENALTY: 0 QDRANT_ONLY: false RAG_PROMPT: >- Use the following retrieved documents to respond briefly and accurately: SEMANTIC_ENABLED: true STOP_TOKENS: - |+ - |+ SYSTEM_PROMPT: You are a helpful assistant TEMPERATURE: 0.5 USE_MESSAGE_TO_QUERY_PROMPT: false tracking_id: foobar-dataset updated_at: '2021-01-01 00:00:00.000' ErrorResponseBody: type: object required: - message properties: message: type: string example: message: Bad Request DatasetConfigurationDTO: type: object description: Lets you specify the configuration for a dataset properties: AIMON_RERANKER_TASK_DEFINITION: type: string nullable: true BM25_AVG_LEN: type: number format: float description: The average length of the chunks in the index for BM25 nullable: true BM25_B: type: number format: float description: The BM25 B parameter nullable: true BM25_ENABLED: type: boolean description: Whether to use BM25 nullable: true BM25_K: type: number format: float description: The BM25 K parameter nullable: true DISABLE_ANALYTICS: type: boolean description: Whether to disable analytics nullable: true DISTANCE_METRIC: allOf: - $ref: '#/components/schemas/DistanceMetric' nullable: true EMBEDDING_BASE_URL: type: string description: The base URL for the embedding API nullable: true EMBEDDING_MODEL_NAME: type: string description: The name of the embedding model to use nullable: true EMBEDDING_QUERY_PREFIX: type: string description: The prefix to use for the embedding query nullable: true EMBEDDING_SIZE: type: integer description: The size of the embeddings nullable: true minimum: 0 FREQUENCY_PENALTY: type: number format: double description: The frequency penalty to use nullable: true FULLTEXT_ENABLED: type: boolean description: Whether to use fulltext search nullable: true INDEXED_ONLY: type: boolean description: Whether to only use indexed chunks nullable: true LLM_API_VERSION: type: string description: The API version for the LLM API nullable: true LLM_BASE_URL: type: string description: The base URL for the LLM API nullable: true LLM_DEFAULT_MODEL: type: string description: The default model to use for the LLM nullable: true LOCKED: type: boolean description: Whether the dataset is locked to prevent changes or deletion nullable: true MAX_LIMIT: type: integer format: int64 description: The maximum limit for the number of chunks for counting nullable: true minimum: 0 MAX_TOKENS: type: integer format: int64 description: The maximum number of tokens to use in LLM Response nullable: true minimum: 0 MESSAGE_TO_QUERY_PROMPT: type: string description: The prompt to use for converting a message to a query nullable: true N_RETRIEVALS_TO_INCLUDE: type: integer description: The number of retrievals to include with the RAG model nullable: true minimum: 0 PAGEFIND_ENABLED: type: boolean description: Whether to enable pagefind indexing nullable: true PRESENCE_PENALTY: type: number format: double description: The presence penalty to use nullable: true PUBLIC_DATASET: allOf: - $ref: '#/components/schemas/PublicDatasetOptions' nullable: true QDRANT_ONLY: type: boolean description: Whether or not to insert chunks into Postgres nullable: true RAG_PROMPT: type: string description: The prompt to use for the RAG model nullable: true RERANKER_BASE_URL: type: string description: The base URL for the reranker API nullable: true RERANKER_MODEL_NAME: type: string description: The model name for the Reranker API nullable: true SEMANTIC_ENABLED: type: boolean description: Whether to use semantic search nullable: true STOP_TOKENS: type: array items: type: string description: The stop tokens to use nullable: true SYSTEM_PROMPT: type: string description: The system prompt to use for the LLM nullable: true TEMPERATURE: type: number format: double description: The temperature to use nullable: true TOOL_CONFIGURATION: allOf: - $ref: '#/components/schemas/ToolConfiguration' nullable: true USE_MESSAGE_TO_QUERY_PROMPT: type: boolean description: Whether to use the message to query prompt nullable: true example: AIMON_RERANKER_TASK_DEFINITION: >- Your task is to grade the relevance of context document(s) against the specified user query. BM25_AVG_LEN: 256 BM25_B: 0.75 BM25_ENABLED: true BM25_K: 0.75 DISTANCE_METRIC: cosine EMBEDDING_BASE_URL: https://embedding.trieve.ai EMBEDDING_MODEL_NAME: jina-base-en EMBEDDING_QUERY_PREFIX: '' EMBEDDING_SIZE: 768 FREQUENCY_PENALTY: 0 FULLTEXT_ENABLED: true INDEXED_ONLY: false LLM_BASE_URL: https://api.openai.com/v1 LLM_DEFAULT_MODEL: gpt-4o LOCKED: false MAX_LIMIT: 10000 MESSAGE_TO_QUERY_PROMPT: >+ Write a 1-2 sentence semantic search query along the lines of a hypothetical response to: N_RETRIEVALS_TO_INCLUDE: 8 PRESENCE_PENALTY: 0 QDRANT_ONLY: false RAG_PROMPT: >- Use the following retrieved documents to respond briefly and accurately: SEMANTIC_ENABLED: true STOP_TOKENS: - |+ - |+ SYSTEM_PROMPT: You are a helpful assistant TEMPERATURE: 0.5 USE_MESSAGE_TO_QUERY_PROMPT: false DistanceMetric: type: string enum: - euclidean - cosine - manhattan - dot PublicDatasetOptions: type: object required: - enabled properties: enabled: type: boolean extra_params: allOf: - $ref: '#/components/schemas/PublicPageParameters' nullable: true ToolConfiguration: type: object properties: query_tool_options: allOf: - $ref: '#/components/schemas/QueryToolOptions' nullable: true PublicPageParameters: type: object properties: allowSwitchingModes: type: boolean nullable: true analytics: type: boolean nullable: true apiKey: type: string nullable: true baseUrl: type: string nullable: true brandColor: type: string nullable: true brandFontFamily: type: string nullable: true brandLogoImgSrcUrl: type: string nullable: true brandName: type: string nullable: true buttonTriggers: type: array items: $ref: '#/components/schemas/ButtonTrigger' nullable: true chat: type: boolean nullable: true creatorLinkedInUrl: type: string nullable: true creatorName: type: string nullable: true currencyPosition: type: string nullable: true datasetId: type: string format: uuid nullable: true debounceMs: type: integer format: int32 nullable: true defaultAiQuestions: type: array items: $ref: '#/components/schemas/DefaultSearchQueryType' nullable: true defaultCurrency: type: string nullable: true defaultImageQuestion: type: string nullable: true defaultSearchMode: type: string nullable: true defaultSearchQueries: type: array items: $ref: '#/components/schemas/DefaultSearchQueryType' nullable: true defaultSearchQuery: type: string nullable: true floatingButtonPosition: type: string nullable: true floatingButtonVersion: type: string nullable: true floatingSearchIconPosition: type: string nullable: true followupQuestions: type: boolean nullable: true forBrandName: type: string nullable: true headingPrefix: type: string nullable: true heroPattern: allOf: - $ref: '#/components/schemas/HeroPattern' nullable: true hideDrawnText: type: boolean nullable: true imageStarterText: type: string nullable: true inline: type: boolean nullable: true inlineHeader: type: string nullable: true isTestMode: type: boolean nullable: true navLogoImgSrcUrl: type: string nullable: true notFilterToolCallOptions: allOf: - $ref: '#/components/schemas/NotFilterToolCallOptions' nullable: true numberOfSuggestions: type: integer nullable: true minimum: 0 openGraphMetadata: allOf: - $ref: '#/components/schemas/OpenGraphMetadata' nullable: true openLinksInNewTab: type: boolean nullable: true placeholder: type: string nullable: true priceToolCallOptions: allOf: - $ref: '#/components/schemas/PriceToolCallOptions' nullable: true problemLink: type: string nullable: true relevanceToolCallOptions: allOf: - $ref: '#/components/schemas/RelevanceToolCallOptions' nullable: true responsive: type: boolean nullable: true searchBar: type: boolean nullable: true searchOptions: allOf: - $ref: '#/components/schemas/PublicPageSearchOptions' nullable: true searchPageProps: allOf: - $ref: '#/components/schemas/SearchPageProps' nullable: true searchToolCallOptions: allOf: - $ref: '#/components/schemas/SearchToolCallOptions' nullable: true showFloatingButton: type: boolean nullable: true showFloatingInput: type: boolean nullable: true showFloatingSearchIcon: type: boolean nullable: true showResultHighlights: type: boolean nullable: true singleProductOptions: allOf: - $ref: '#/components/schemas/SingleProductOptions' nullable: true suggestedQueries: type: boolean nullable: true tabMessages: type: array items: $ref: '#/components/schemas/PublicPageTabMessage' nullable: true tags: type: array items: $ref: '#/components/schemas/PublicPageTag' nullable: true theme: allOf: - $ref: '#/components/schemas/PublicPageTheme' nullable: true type: type: string nullable: true useGroupSearch: type: boolean nullable: true useLocal: type: boolean nullable: true usePagefind: type: boolean nullable: true videoLink: type: string nullable: true videoPosition: type: string nullable: true zIndex: type: integer format: int32 nullable: true QueryToolOptions: type: object properties: max_price_option_description: type: string nullable: true min_price_option_description: type: string nullable: true price_filter_description: type: string nullable: true query_parameter_description: type: string nullable: true tool_description: type: string nullable: true ButtonTrigger: type: object required: - selector - mode properties: mode: type: string removeTriggers: type: boolean nullable: true selector: type: string DefaultSearchQueryType: oneOf: - type: string - $ref: '#/components/schemas/DefaultSearchQuery' HeroPattern: type: object properties: backgroundColor: type: string nullable: true foregroundColor: type: string nullable: true foregroundOpacity: type: number format: float nullable: true heroPatternName: type: string nullable: true heroPatternSvg: type: string nullable: true NotFilterToolCallOptions: type: object properties: toolDescription: type: string nullable: true userMessageTextPrefix: type: string nullable: true OpenGraphMetadata: type: object properties: description: type: string nullable: true image: type: string nullable: true title: type: string nullable: true PriceToolCallOptions: type: object required: - toolDescription properties: maxPriceDescription: type: string nullable: true minPriceDescription: type: string nullable: true toolDescription: type: string RelevanceToolCallOptions: type: object required: - toolDescription properties: highDescription: type: string nullable: true includeImages: type: boolean nullable: true lowDescription: type: string nullable: true mediumDescription: type: string nullable: true toolDescription: type: string userMessageTextPrefix: type: string nullable: true PublicPageSearchOptions: type: object properties: content_only: type: boolean description: >- Set content_only to true to only returning the chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typically 10-50ms). Default is false. nullable: true filters: allOf: - $ref: '#/components/schemas/ChunkFilter' nullable: true get_total_pages: type: boolean description: >- Get total page count for the query accounting for the applied filters. Defaults to false, but can be set to true when the latency penalty is acceptable (typically 50-200ms). nullable: true page: type: integer format: int64 description: Page of chunks to fetch. Page is 1-indexed. nullable: true minimum: 0 page_size: type: integer format: int64 description: >- Page size is the number of chunks to fetch. This can be used to fetch more than 10 chunks at a time. nullable: true minimum: 0 remove_stop_words: type: boolean description: >- If true, stop words (specified in server/src/stop-words.txt in the git repo) will be removed. Queries that are entirely stop words will be preserved. nullable: true score_threshold: type: number format: float description: >- Set score_threshold to a float to filter out chunks with a score below the threshold for cosine distance metric. For Manhattan Distance, Euclidean Distance, and Dot Product, it will filter out scores above the threshold distance. This threshold applies before weight and bias modifications. If not specified, this defaults to no threshold. A threshold of 0 will default to no threshold. nullable: true scoring_options: allOf: - $ref: '#/components/schemas/ScoringOptions' nullable: true search_type: allOf: - $ref: '#/components/schemas/SearchMethod' nullable: true slim_chunks: type: boolean description: >- Set slim_chunks to true to avoid returning the content and chunk_html of the chunks. This is useful for when you want to reduce amount of data over the wire for latency improvement (typically 10-50ms). Default is false. nullable: true sort_options: allOf: - $ref: '#/components/schemas/SortOptions' nullable: true typo_options: allOf: - $ref: '#/components/schemas/TypoOptions' nullable: true use_autocomplete: type: boolean description: Enables autocomplete on the search modal. nullable: true use_quote_negated_terms: type: boolean description: >- If true, quoted and - prefixed words will be parsed from the queries and used as required and negated words respectively. Default is false. nullable: true user_id: type: string description: >- User ID is the id of the user who is making the request. This is used to track user interactions with the search results. nullable: true example: filters: must: - field: num_value range: gt: 0 gte: 0 lt: 1 lte: 1 must_not: - field: metadata.key3 match: - value5 - value6 should: - field: metadata.key1 match: - value1 - value2 score_threshold: 0.5 search_type: semantic SearchPageProps: type: object properties: display: type: boolean nullable: true filterSidebarProps: allOf: - $ref: '#/components/schemas/SidebarFilters' nullable: true SearchToolCallOptions: type: object properties: noSearchRagContext: type: string nullable: true toolDescription: type: string nullable: true userMessageTextPrefix: type: string nullable: true SingleProductOptions: type: object properties: enabled: type: boolean nullable: true groupTrackingId: type: string nullable: true pdpPrompt: type: string nullable: true productDescriptionHtml: type: string nullable: true productName: type: string nullable: true productPrimaryImageUrl: type: string nullable: true productQuestions: type: array items: $ref: '#/components/schemas/DefaultSearchQuery' nullable: true productTrackingId: type: string nullable: true recSearchQuery: type: string nullable: true PublicPageTabMessage: type: object required: - title - tabInnerHtml - showComponentCode properties: showComponentCode: type: boolean tabInnerHtml: type: string title: type: string PublicPageTag: type: object required: - tag properties: description: type: string nullable: true iconClassName: type: string nullable: true label: type: string nullable: true selected: type: boolean nullable: true tag: type: string PublicPageTheme: type: string enum: - light - dark DefaultSearchQuery: type: object properties: imageUrl: type: string nullable: true query: type: string nullable: true ChunkFilter: type: object description: >- ChunkFilter is a JSON object which can be used to filter chunks. This is useful for when you want to filter chunks by arbitrary metadata. Unlike with tag filtering, there is a performance hit for filtering on metadata. properties: must: type: array items: $ref: '#/components/schemas/ConditionType' description: >- All of these field conditions have to match for the chunk to be included in the result set. nullable: true must_not: type: array items: $ref: '#/components/schemas/ConditionType' description: >- None of these field conditions can match for the chunk to be included in the result set. nullable: true should: type: array items: $ref: '#/components/schemas/ConditionType' description: >- Only one of these field conditions has to match for the chunk to be included in the result set. nullable: true example: must: - field: tag_set match_all: - A - B - field: num_value range: gte: 10 lte: 25 ScoringOptions: type: object description: >- Scoring options provides ways to modify the sparse or dense vector created for the query in order to change how potential matches are scored. If not specified, this defaults to no modifications. properties: fulltext_boost: allOf: - $ref: '#/components/schemas/FullTextBoost' nullable: true semantic_boost: allOf: - $ref: '#/components/schemas/SemanticBoost' nullable: true SearchMethod: type: string enum: - fulltext - semantic - hybrid - bm25 SortOptions: type: object description: >- Sort Options lets you specify different methods to rerank the chunks in the result set. If not specified, this defaults to the score of the chunks. properties: location_bias: allOf: - $ref: '#/components/schemas/GeoInfoWithBias' nullable: true mmr: allOf: - $ref: '#/components/schemas/MmrOptions' nullable: true recency_bias: type: number format: float description: >- Recency Bias lets you determine how much of an effect the recency of chunks will have on the search results. If not specified, this defaults to 0.0. We recommend setting this to 1.0 for a gentle reranking of the results, >3.0 for a strong reranking of the results. nullable: true sort_by: allOf: - $ref: '#/components/schemas/QdrantSortBy' nullable: true tag_weights: type: object description: >- Tag weights is a JSON object which can be used to boost the ranking of chunks with certain tags. This is useful for when you want to be able to bias towards chunks with a certain tag on the fly. The keys are the tag names and the values are the weights. additionalProperties: type: number format: float nullable: true use_weights: type: boolean description: >- Set use_weights to true to use the weights of the chunks in the result set in order to sort them. If not specified, this defaults to true. nullable: true TypoOptions: type: object description: >- Typo Options lets you specify different methods to correct typos in the query. If not specified, typos will not be corrected. properties: correct_typos: type: boolean description: >- Set correct_typos to true to correct typos in the query. If not specified, this defaults to false. nullable: true disable_on_word: type: array items: type: string description: >- Words that should not be corrected. If not specified, this defaults to an empty list. nullable: true one_typo_word_range: allOf: - $ref: '#/components/schemas/TypoRange' nullable: true prioritize_domain_specifc_words: type: boolean description: >- Auto-require non-english words present in the dataset to exist in each results chunk_html text. If not specified, this defaults to true. nullable: true two_typo_word_range: allOf: - $ref: '#/components/schemas/TypoRange' nullable: true SidebarFilters: type: object properties: sections: type: array items: $ref: '#/components/schemas/FilterSidebarSection' nullable: true ConditionType: oneOf: - $ref: '#/components/schemas/FieldCondition' - $ref: '#/components/schemas/HasChunkIDCondition' description: >- Filters can be constructed using either fields on the chunk objects, ids or tracking ids of chunks, and finally ids or tracking ids of groups. FullTextBoost: type: object description: >- Boost the presence of certain tokens for fulltext (SPLADE) and keyword (BM25) search. I.e. boosting title phrases to priortize title matches or making sure that the listing for AirBNB itself ranks higher than companies who make software for AirBNB hosts by boosting the in-document-frequency of the AirBNB token (AKA word) for its official listing. Conceptually it multiples the in-document-importance second value in the tuples of the SPLADE or BM25 sparse vector of the chunk_html innerText for all tokens present in the boost phrase by the boost factor like so: (token, in-document-importance) -> (token, in-document-importance*boost_factor). required: - phrase - boost_factor properties: boost_factor: type: number format: double description: >- Amount to multiplicatevly increase the frequency of the tokens in the phrase by phrase: type: string description: The phrase to boost in the fulltext document frequency index SemanticBoost: type: object description: >- Semantic boosting moves the dense vector of the chunk in the direction of the distance phrase for semantic search. I.e. you can force a cluster by moving every chunk for a PDF closer to its title or push a chunk with a chunk_html of "iphone" 25% closer to the term "flagship" by using the distance phrase "flagship" and a distance factor of 0.25. Conceptually it's drawing a line (euclidean/L2 distance) between the vector for the innerText of the chunk_html and distance_phrase then moving the vector of the chunk_html distance_factor*L2Distance closer to or away from the distance_phrase point along the line between the two points. required: - phrase - distance_factor properties: distance_factor: type: number format: float description: >- Arbitrary float (positive or negative) specifying the multiplicate factor to apply before summing the phrase vector with the chunk_html embedding vector phrase: type: string description: >- Terms to embed in order to create the vector which is weighted summed with the chunk_html embedding vector GeoInfoWithBias: type: object description: >- Location bias lets you rank your results by distance from a location. If not specified, this has no effect. Bias allows you to determine how much of an effect the location of chunks will have on the search results. If not specified, this defaults to 0.0. We recommend setting this to 1.0 for a gentle reranking of the results, >3.0 for a strong reranking of the results. required: - location - bias properties: bias: type: number format: double description: >- Bias lets you specify how much of an effect the location of chunks will have on the search results. If not specified, this defaults to 0.0. We recommend setting this to 1.0 for a gentle reranking of the results, >3.0 for a strong reranking of the results. location: $ref: '#/components/schemas/GeoInfo' MmrOptions: type: object description: >- MMR Options lets you specify different methods to rerank the chunks in the result set using Maximal Marginal Relevance. If not specified, this defaults to the score of the chunks. required: - use_mmr properties: mmr_lambda: type: number format: float description: >- Set mmr_lambda to a value between 0.0 and 1.0 to control the tradeoff between relevance and diversity. Closer to 1.0 will give more diverse results, closer to 0.0 will give more relevant results. If not specified, this defaults to 0.5. nullable: true use_mmr: type: boolean description: >- Set use_mmr to true to use the Maximal Marginal Relevance algorithm to rerank the results. QdrantSortBy: oneOf: - $ref: '#/components/schemas/SortByField' - $ref: '#/components/schemas/SortBySearchType' description: >- Sort by lets you specify a method to sort the results by. If not specified, this defaults to the score of the chunks. If specified, this can be any key in the chunk metadata. This key must be a numeric value within the payload. TypoRange: type: object description: >- The TypoRange struct is used to specify the range of which the query will be corrected if it has a typo. required: - min properties: max: type: integer format: int32 description: >- The maximum number of characters that the query will be corrected if it has a typo. If not specified, this defaults to 8. nullable: true minimum: 0 min: type: integer format: int32 description: >- The minimum number of characters that the query will be corrected if it has a typo. If not specified, this defaults to 5. minimum: 0 FilterSidebarSection: type: object required: - key - filterKey - title - selectionType - filterType - options properties: filterKey: type: string filterType: type: string key: type: string options: type: array items: $ref: '#/components/schemas/TagProp' selectionType: type: string title: type: string FieldCondition: type: object description: >- FieldCondition is a JSON object which can be used to filter chunks by a field. This is useful for when you want to filter chunks by arbitrary metadata. To access fields inside of the metadata that you provide with the card, prefix the field name with `metadata.`. required: - field properties: boolean: type: boolean description: >- Boolean is a true false value for a field. This only works for boolean fields. You can specify this if you want values to be true or false. nullable: true date_range: allOf: - $ref: '#/components/schemas/DateRange' nullable: true field: type: string description: >- Field is the name of the field to filter on. Commonly used fields are `timestamp`, `link`, `tag_set`, `location`, `num_value`, `group_ids`, and `group_tracking_ids`. The field value will be used to check for an exact substring match on the metadata values for each existing chunk. This is useful for when you want to filter chunks by arbitrary metadata. To access fields inside of the metadata that you provide with the card, prefix the field name with `metadata.`. geo_bounding_box: allOf: - $ref: '#/components/schemas/LocationBoundingBox' nullable: true geo_polygon: allOf: - $ref: '#/components/schemas/LocationPolygon' nullable: true geo_radius: allOf: - $ref: '#/components/schemas/LocationRadius' nullable: true match_all: type: array items: $ref: '#/components/schemas/MatchCondition' description: >- Match all lets you pass in an array of values that will return results if all of the items match. The match value will be used to check for an exact substring match on the metadata values for each existing chunk. If both match_all and match_any are provided, the match_any condition will be used. nullable: true match_any: type: array items: $ref: '#/components/schemas/MatchCondition' description: >- Match any lets you pass in an array of values that will return results if any of the items match. The match value will be used to check for an exact substring match on the metadata values for each existing chunk. If both match_all and match_any are provided, the match_any condition will be used. nullable: true range: allOf: - $ref: '#/components/schemas/Range' nullable: true example: field: metadata.key1 match: - value1 - value2 range: gt: 0 gte: 0 lt: 1 lte: 1 HasChunkIDCondition: type: object description: >- HasChunkIDCondition is a JSON object which can be used to filter chunks by their ids or tracking ids. This is useful for when you want to filter chunks by their ids or tracking ids. properties: ids: type: array items: type: string format: uuid description: >- Ids of the chunks to apply a match_any condition with. Only chunks with one of these ids will be returned. nullable: true tracking_ids: type: array items: type: string description: >- Tracking ids of the chunks to apply a match_any condition with. Only chunks with one of these tracking ids will be returned. nullable: true GeoInfo: type: object description: Location that you want to use as the center of the search. required: - lat - lon properties: lat: $ref: '#/components/schemas/GeoTypes' lon: $ref: '#/components/schemas/GeoTypes' SortByField: type: object required: - field properties: direction: allOf: - $ref: '#/components/schemas/SortOrder' nullable: true field: type: string description: >- Field to sort by. This has to be a numeric field with a Qdrant `Range` index on it. i.e. num_value and timestamp prefetch_amount: type: integer format: int64 description: How many results to pull in before the sort nullable: true minimum: 0 SortBySearchType: type: object required: - rerank_type properties: prefetch_amount: type: integer format: int64 description: How many results to pull in before the rerabj nullable: true minimum: 0 rerank_query: type: string description: Query to use for prefetching defaults to the search query nullable: true rerank_type: $ref: '#/components/schemas/ReRankOptions' TagProp: type: object properties: description: type: string nullable: true label: type: string nullable: true range: allOf: - $ref: '#/components/schemas/RangeSliderConfig' nullable: true tag: type: string nullable: true DateRange: type: object description: >- DateRange is a JSON object which can be used to filter chunks by a range of dates. This leverages the time_stamp field on chunks in your dataset. You can specify this if you want values in a certain range. You must provide ISO 8601 combined date and time without timezone. properties: gt: type: string nullable: true gte: type: string nullable: true lt: type: string nullable: true lte: type: string nullable: true example: gt: '2021-01-01 00:00:00.000' gte: '2021-01-01 00:00:00.000' lt: '2021-01-01 00:00:00.000' lte: '2021-01-01 00:00:00.000' LocationBoundingBox: type: object required: - top_left - bottom_right properties: bottom_right: $ref: '#/components/schemas/GeoInfo' top_left: $ref: '#/components/schemas/GeoInfo' LocationPolygon: type: object required: - exterior properties: exterior: type: array items: $ref: '#/components/schemas/GeoInfo' interior: type: array items: type: array items: $ref: '#/components/schemas/GeoInfo' nullable: true LocationRadius: type: object required: - center - radius properties: center: $ref: '#/components/schemas/GeoInfo' radius: type: number format: double MatchCondition: oneOf: - type: string - type: integer format: int64 - type: number format: double Range: type: object properties: gt: allOf: - $ref: '#/components/schemas/RangeCondition' nullable: true gte: allOf: - $ref: '#/components/schemas/RangeCondition' nullable: true lt: allOf: - $ref: '#/components/schemas/RangeCondition' nullable: true lte: allOf: - $ref: '#/components/schemas/RangeCondition' nullable: true example: gt: 0 gte: 0 lt: 1 lte: 1 GeoTypes: oneOf: - type: integer format: int64 - type: number format: double SortOrder: type: string enum: - desc - asc ReRankOptions: type: string enum: - semantic - fulltext - bm25 - cross_encoder RangeSliderConfig: type: object properties: max: type: number format: double nullable: true min: type: number format: double nullable: true RangeCondition: oneOf: - type: number format: double - type: integer format: int64 securitySchemes: ApiKey: type: apiKey in: header name: Authorization ````