> ## 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. # Get RAG Analytics > This route allows you to view the RAG analytics for a dataset. ## OpenAPI ````yaml post /api/analytics/rag 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/analytics/rag: post: tags: - Analytics summary: Get RAG Analytics description: This route allows you to view the RAG analytics for a dataset. operationId: get_rag_analytics parameters: - name: TR-Dataset in: header description: >- The dataset id or tracking_id to use for the request. We assume you intend to use an id if the value is a valid uuid. required: true schema: type: string format: uuid requestBody: description: JSON request payload to filter the graph content: application/json: schema: $ref: '#/components/schemas/RAGAnalytics' required: true responses: '200': description: The RAG analytics for the dataset content: application/json: schema: $ref: '#/components/schemas/RAGAnalyticsResponse' '400': description: Service error relating to getting RAG analytics content: application/json: schema: $ref: '#/components/schemas/ErrorResponseBody' security: - ApiKey: - admin components: schemas: RAGAnalytics: oneOf: - type: object title: RAGQueries required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true has_clicks: type: boolean nullable: true page: type: integer format: int32 nullable: true minimum: 0 sort_by: allOf: - $ref: '#/components/schemas/RAGSortBy' nullable: true sort_order: allOf: - $ref: '#/components/schemas/SortOrder' nullable: true type: type: string enum: - rag_queries - type: object title: RAGUsage required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true type: type: string enum: - rag_usage - type: object title: RAGUsageGraph required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - rag_usage_graph - type: object title: QueryDetails required: - request_id - type properties: request_id: type: string format: uuid type: type: string enum: - rag_query_details - type: object title: RAGQueryRatings required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true type: type: string enum: - rag_query_ratings - type: object title: FollowupQueries required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true page: type: integer format: int32 nullable: true minimum: 0 type: type: string enum: - followup_queries - type: object title: TopicAnalytics required: - type properties: filter: allOf: - $ref: '#/components/schemas/TopicAnalyticsFilter' nullable: true page: type: integer format: int32 nullable: true minimum: 0 sort_by: allOf: - $ref: '#/components/schemas/RAGSortBy' nullable: true sort_order: allOf: - $ref: '#/components/schemas/SortOrder' nullable: true topic_events_filter: allOf: - $ref: '#/components/schemas/TopicEventFilter' nullable: true type: type: string enum: - topic_queries - type: object title: TopicDetails required: - topic_id - type properties: topic_id: type: string format: uuid type: type: string enum: - topic_details - type: object title: TopicsOverTime required: - type properties: filter: allOf: - $ref: '#/components/schemas/TopicAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - topics_over_time - type: object required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - ctr_metrics_over_time - type: object required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - messages_per_user - type: object required: - type properties: filter: allOf: - $ref: '#/components/schemas/RAGAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - chat_average_rating - type: object title: ChatConversionRate required: - type properties: filter: allOf: - $ref: '#/components/schemas/TopicAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - chat_conversion_rate - type: object title: EventFunnel required: - type properties: filter: allOf: - $ref: '#/components/schemas/TopicAnalyticsFilter' nullable: true type: type: string enum: - event_funnel - type: object title: EventsForTopic required: - topic_id - type properties: topic_id: type: string format: uuid type: type: string enum: - events_for_topic - type: object title: ChatRevenue required: - type properties: direct: type: boolean nullable: true filter: allOf: - $ref: '#/components/schemas/EventAnalyticsFilter' nullable: true granularity: allOf: - $ref: '#/components/schemas/Granularity' nullable: true type: type: string enum: - chat_revenue - type: object title: PopularChats required: - type properties: filter: allOf: - $ref: '#/components/schemas/TopicAnalyticsFilter' nullable: true page: type: integer format: int32 nullable: true minimum: 0 type: type: string enum: - popular_chats discriminator: propertyName: type RAGAnalyticsResponse: oneOf: - $ref: '#/components/schemas/RagQueryResponse' - $ref: '#/components/schemas/RAGUsageResponse' - $ref: '#/components/schemas/RAGUsageGraphResponse' - $ref: '#/components/schemas/RagQueryEvent' - $ref: '#/components/schemas/RagQueryRatingsResponse' - $ref: '#/components/schemas/FollowupQueriesResponse' - $ref: '#/components/schemas/TopicQueriesResponse' - $ref: '#/components/schemas/TopicDetailsResponse' - $ref: '#/components/schemas/TopicsOverTimeResponse' - $ref: '#/components/schemas/CTRMetricsOverTimeResponse' - $ref: '#/components/schemas/MessagesPerUserResponse' - $ref: '#/components/schemas/ChatAverageRatingResponse' - $ref: '#/components/schemas/ChatConversionRateResponse' - $ref: '#/components/schemas/EventNameAndCountsResponse' - $ref: '#/components/schemas/EventsForTopicResponse' - $ref: '#/components/schemas/ChatRevenueResponse' - $ref: '#/components/schemas/PopularChatsResponse' ErrorResponseBody: type: object required: - message properties: message: type: string example: message: Bad Request RAGAnalyticsFilter: type: object properties: component_name: type: string nullable: true date_range: allOf: - $ref: '#/components/schemas/DateRange' nullable: true query: type: string nullable: true query_rating: allOf: - $ref: '#/components/schemas/QueryRatingRange' nullable: true rag_type: allOf: - $ref: '#/components/schemas/RagTypes' nullable: true RAGSortBy: type: string enum: - hallucination_score - top_score - created_at SortOrder: type: string enum: - desc - asc Granularity: type: string enum: - minute - second - hour - day - month TopicAnalyticsFilter: type: object properties: component_name: type: string nullable: true date_range: allOf: - $ref: '#/components/schemas/DateRange' nullable: true hallucination_score: allOf: - $ref: '#/components/schemas/FloatRange' nullable: true query: type: string nullable: true query_rating: allOf: - $ref: '#/components/schemas/QueryRatingRange' nullable: true rag_type: allOf: - $ref: '#/components/schemas/RagTypes' nullable: true top_score: allOf: - $ref: '#/components/schemas/FloatRange' nullable: true TopicEventFilter: type: object required: - event_names - inverted properties: event_names: type: array items: $ref: '#/components/schemas/EventNamesFilter' description: Filter by event type inverted: type: boolean EventAnalyticsFilter: type: object description: Filter to apply to the events when querying for them properties: date_range: allOf: - $ref: '#/components/schemas/DateRange' nullable: true event_type: allOf: - $ref: '#/components/schemas/EventTypesFilter' nullable: true is_conversion: type: boolean description: Filter by conversions nullable: true metadata_filter: type: string description: Filter by metadata path i.e. path.attribute = \"value\" nullable: true user_id: type: string description: Filter by user ID nullable: true example: date_range: gt: '2021-08-10T00:00:00Z' lt: '2021-08-11T00:00:00Z' event_type: view is_conversion: true metadata_filter: path = "value" user_id: user1 RagQueryResponse: type: object title: RagQueryResponse required: - queries properties: queries: type: array items: $ref: '#/components/schemas/RagQueryEvent' RAGUsageResponse: type: object title: RAGUsageResponse required: - total_queries properties: total_queries: type: integer format: int32 minimum: 0 RAGUsageGraphResponse: type: object title: RAGUsageGraphResponse required: - points properties: points: type: array items: $ref: '#/components/schemas/IntegerTimePoint' RagQueryEvent: type: object title: RagQueryEvent required: - id - rag_type - user_message - search_id - topic_id - results - dataset_id - llm_response - top_score - hallucination_score - detected_hallucinations - created_at - user_id properties: created_at: type: string dataset_id: type: string format: uuid detected_hallucinations: type: array items: type: string hallucination_score: type: number format: double id: type: string format: uuid llm_response: type: string metadata: nullable: true query_rating: allOf: - $ref: '#/components/schemas/SearchQueryRating' nullable: true rag_type: $ref: '#/components/schemas/ClickhouseRagTypes' results: type: array items: {} search_id: type: string format: uuid top_score: type: number format: float topic_id: type: string format: uuid user_id: type: string user_message: type: string RagQueryRatingsResponse: type: object title: RagQueryRatingsResponse required: - total_positive_ratings - total_negative_ratings properties: total_negative_ratings: type: integer format: int64 description: Total number of negative RAG ratings total_positive_ratings: type: integer format: int64 description: Total number of positive RAG ratings FollowupQueriesResponse: type: object required: - top_queries properties: top_queries: type: array items: $ref: '#/components/schemas/FollowupQuery' TopicQueriesResponse: type: object required: - topics properties: topics: type: array items: $ref: '#/components/schemas/ClickhouseTopicAnalyticsSummary' TopicDetailsResponse: type: object required: - topic - messages properties: messages: type: array items: $ref: '#/components/schemas/RagQueryEvent' topic: $ref: '#/components/schemas/TopicQuery' TopicsOverTimeResponse: type: object required: - total_topics - points properties: points: type: array items: $ref: '#/components/schemas/IntegerTimePoint' total_topics: type: integer format: int64 CTRMetricsOverTimeResponse: type: object required: - total_ctr - points properties: points: type: array items: $ref: '#/components/schemas/FloatTimePoint' total_ctr: type: number format: double MessagesPerUserResponse: type: object required: - avg_messages_per_user - points properties: avg_messages_per_user: type: number format: double points: type: array items: $ref: '#/components/schemas/FloatTimePoint' ChatAverageRatingResponse: type: object required: - avg_chat_rating - points properties: avg_chat_rating: type: number format: double points: type: array items: $ref: '#/components/schemas/FloatTimePoint' ChatConversionRateResponse: type: object required: - conversion_rate - points properties: conversion_rate: type: number format: double points: type: array items: $ref: '#/components/schemas/FloatTimePoint' EventNameAndCountsResponse: type: object required: - event_names properties: event_names: type: array items: $ref: '#/components/schemas/EventNameAndCounts' EventsForTopicResponse: type: object required: - events properties: events: type: array items: $ref: '#/components/schemas/EventData' ChatRevenueResponse: type: object required: - revenue - points properties: points: type: array items: $ref: '#/components/schemas/FloatTimePoint' revenue: type: number format: double PopularChatsResponse: type: object required: - chats properties: chats: type: array items: $ref: '#/components/schemas/PopularChat' 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' QueryRatingRange: type: object properties: gt: type: integer format: int32 nullable: true minimum: 0 gte: type: integer format: int32 nullable: true minimum: 0 lt: type: integer format: int32 nullable: true minimum: 0 lte: type: integer format: int32 nullable: true minimum: 0 example: gt: 1 gte: 1 lt: 1 lte: 1 RagTypes: type: string enum: - chosen_chunks - all_chunks FloatRange: type: object properties: gt: type: number format: double nullable: true gte: type: number format: double nullable: true lt: type: number format: double nullable: true lte: type: number format: double nullable: true EventNamesFilter: type: string enum: - component_close - component_open - View - site-followup_query - Click - site-add_to_cart - site-checkout_end EventTypesFilter: type: string enum: - view - filter_clicked - click - add_to_cart - purchase IntegerTimePoint: type: object required: - time_stamp - point properties: point: type: integer format: int64 time_stamp: type: string SearchQueryRating: type: object required: - rating properties: metadata: nullable: true note: type: string nullable: true rating: type: integer format: int32 ClickhouseRagTypes: type: string enum: - chosen_chunks - all_chunks FollowupQuery: type: object required: - query - count properties: count: type: integer format: int64 query: type: string ClickhouseTopicAnalyticsSummary: type: object required: - id - name - topic_id - owner_id - created_at - updated_at - message_count - avg_top_score - avg_hallucination_score - event_names properties: avg_hallucination_score: type: number format: double avg_query_rating: type: number format: double nullable: true avg_top_score: type: number format: double created_at: type: string event_names: type: array items: type: string description: >- All event_names that are associated with the topic, may contain duplicate names id: type: string format: uuid message_count: type: integer format: int64 minimum: 0 name: type: string owner_id: type: string topic_id: type: string format: uuid updated_at: type: string TopicQuery: type: object required: - id - name - topic_id - dataset_id - owner_id - created_at - updated_at properties: created_at: type: string dataset_id: type: string format: uuid id: type: string format: uuid metadata: nullable: true name: type: string owner_id: type: string topic_id: type: string format: uuid updated_at: type: string FloatTimePoint: type: object required: - time_stamp - point properties: point: type: number format: double time_stamp: type: string EventNameAndCounts: type: object required: - event_name - event_count properties: event_count: type: integer format: int64 event_name: type: string EventData: type: object title: EventData description: EventData represents a single analytics event required: - id - event_type - event_name - items - dataset_id - created_at - updated_at properties: created_at: type: string description: The time the event was created. dataset_id: type: string format: uuid description: The unique identifier for the dataset the event is associated with. event_name: type: string description: >- The name of the event, e.g. "Added to Cart", "Purchased", "Viewed Home Page", "Clicked", "Filter Clicked", "Followup Query". event_type: type: string description: >- The type of event, "add_to_cart", "purchase", "view", "click", "filter_clicked", "followup_query" id: type: string format: uuid description: The unique identifier for the event is_conversion: type: boolean description: Whether the event is a conversion event. nullable: true items: type: array items: type: string description: >- The items associated with the event. This could be a list of stringified json chunks for search events, or a list of items for add_to_cart, purchase, view, and click events. metadata: description: >- Additional metadata associated with the event. This can be custom data that is specific to the event. nullable: true request_id: type: string description: The unique identifier for the request the event is associated with. nullable: true request_type: type: string description: The type of request the event is associated with. nullable: true updated_at: type: string description: The time the event was last updated. user_id: type: string description: The user identifier associated with the event. nullable: true example: created_at: '2021-08-10T00:00:00Z' dataset_id: 00000000-0000-0000-0000-000000000000 event_name: Viewed Home Page event_type: view is_conversion: true items: - item1 - item2 metadata: metadata request_id: 00000000-0000-0000-0000-000000000000 updated_at: '2021-08-10T00:00:00Z' user_id: user1 PopularChat: type: object required: - name - count properties: count: type: integer format: int64 name: type: string securitySchemes: ApiKey: type: apiKey in: header name: Authorization ````