> ## Documentation Index > Fetch the complete documentation index at: https://algolia.com/llms.txt > Use this file to discover all available pages before exploring further. # Get Data By User Token > Retrieves all memories, conversations and their messages for the given user token. This is a **beta feature** according to [Algolia's Terms of Service ("Beta Services")](https://www.algolia.com/policies/terms/). **Required ACL:** `logs` ## OpenAPI ````yaml specs/agent-studio.yml get /1/user-data/{userToken} openapi: 3.1.0 info: title: Agent Studio API description: > The Agent Studio API lets you build and operate generative AI agents that use Algolia data, tools, and your chosen LLM provider. Use it to create, configure, publish, and update agents, then generate chat completions grounded in live data from your Algolia indices. You can manage LLM providers, Agent Studio tools, conversations, feedback, secret keys, user data, caching, and application settings for your AI experiences. ## Client libraries Use Algolia's API clients and libraries to reliably integrate Algolia's APIs with your apps. For more information, see [Algolia's ecosystem](https://www.algolia.com/doc/libraries). ## Base URL Base URL for the Agent Studio API: - `https://{APPLICATION_ID}.algolia.net/agent-studio` **All requests must use HTTPS.** ## Authentication Add these headers to authenticate requests: - `x-algolia-application-id`. Your Algolia application ID. - `x-algolia-api-key`. An API key with the necessary permissions to make the request. The required access control list (ACL) to make a request is listed in each endpoint's reference. You can find your application ID and API key in the [Algolia dashboard](https://dashboard.algolia.com/account/api-keys). ## Request format Request bodies must be JSON objects. ## Response status and errors The Agent Studio API returns JSON responses. Since JSON doesn't guarantee any specific ordering, don't rely on the order of attributes in the API response. Successful responses return `2xx` statuses. Client errors return `4xx` statuses. Server errors return `5xx` statuses. Error responses have a `message` property with more information. ## Version The current version of the Agent Studio API is version 1, indicated by the `/1/` in each endpoint's URL. version: 0.1.0 servers: - url: https://{APPLICATION_ID}.algolia.net/agent-studio description: Agent Studio API. variables: APPLICATION_ID: default: EXAMPLE description: Your Algolia application ID. security: - appId: [] apiKey: [] tags: - name: Agents description: Manage your agents. - name: Allowed Domains description: Restrict where an agent's API key may be used. - name: Completions description: Generate completions. - name: Configurations description: Manage Agent Studio related application configurations. - name: Conversations description: View, export, and delete conversation history. - name: Feedback description: Capture user feedback on agent responses. - name: Internal description: Endpoints that are needed for internal or integration logic. - name: Providers description: Manage your LLM providers. - name: Secret Keys description: Manage secret keys used to authenticate requests. - name: User Data description: Manage end-user data associated with conversations. paths: /1/user-data/{userToken}: get: tags: - User Data summary: Get Data By User Token description: >- Retrieves all memories, conversations and their messages for the given user token. operationId: getUserData parameters: - name: userToken in: path required: true schema: type: string title: userToken description: The userToken. responses: '200': description: Successful Response. content: application/json: schema: $ref: '#/components/schemas/UserDataResponse' '422': description: Validation Error. content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-codeSamples: - lang: csharp label: C# source: |- // Initialize the client var client = new AgentStudioClient( new AgentStudioConfig("ALGOLIA_APPLICATION_ID", "ALGOLIA_API_KEY") ); // Call the API var response = await client.GetUserDataAsync("test-user-token"); // print the response Console.WriteLine(response); - lang: dart label: Dart source: |- // Initialize the client final client = AgentStudioClient( appId: 'ALGOLIA_APPLICATION_ID', apiKey: 'ALGOLIA_API_KEY'); // Call the API final response = await client.getUserData( userToken: "test-user-token", ); // print the response print(response); - lang: go label: Go source: >- // Initialize the client client, err := agentStudio.NewClient("ALGOLIA_APPLICATION_ID", "ALGOLIA_API_KEY") if err != nil { // The client can fail to initialize if you pass an invalid parameter. panic(err) } // Call the API response, err := client.GetUserData(client.NewApiGetUserDataRequest( "test-user-token")) if err != nil { // handle the eventual error panic(err) } // print the response print(response) - lang: java label: Java source: >- // Initialize the client AgentStudioClient client = new AgentStudioClient("ALGOLIA_APPLICATION_ID", "ALGOLIA_API_KEY"); // Call the API UserDataResponse response = client.getUserData("test-user-token"); // print the response System.out.println(response); - lang: javascript label: JavaScript source: >- // Initialize the client const client = agentStudioClient('ALGOLIA_APPLICATION_ID', 'ALGOLIA_API_KEY'); // Call the API const response = await client.getUserData({ userToken: 'test-user-token' }); // print the response console.log(response); - lang: kotlin label: Kotlin source: >- // Initialize the client val client = AgentStudioClient(appId = "ALGOLIA_APPLICATION_ID", apiKey = "ALGOLIA_API_KEY") // Call the API var response = client.getUserData(userToken = "test-user-token") // print the response println(response) - lang: php label: PHP source: >- // Initialize the client $client = AgentStudioClient::create('ALGOLIA_APPLICATION_ID', 'ALGOLIA_API_KEY'); // Call the API $response = $client->getUserData( 'test-user-token', ); // print the response var_dump($response); - lang: python label: Python source: >- # Initialize the client # In an asynchronous context, you can use AgentStudioClient instead, which exposes the exact same methods. client = AgentStudioClientSync("ALGOLIA_APPLICATION_ID", "ALGOLIA_API_KEY") # Call the API response = client.get_user_data( user_token="test-user-token", ) # print the response print(response) - lang: ruby label: Ruby source: >- # Initialize the client client = Algolia::AgentStudioClient.create("ALGOLIA_APPLICATION_ID", "ALGOLIA_API_KEY") # Call the API response = client.get_user_data("test-user-token") # print the response puts(response) - lang: scala label: Scala source: >- // Initialize the client val client = AgentStudioClient(appId = "ALGOLIA_APPLICATION_ID", apiKey = "ALGOLIA_API_KEY") // Call the API val response = Await.result( client.getUserData( userToken = "test-user-token" ), Duration(100, "sec") ) // print the response println(response) - lang: swift label: Swift source: >- // Initialize the client let client = try AgentStudioClient(appID: "ALGOLIA_APPLICATION_ID", apiKey: "ALGOLIA_API_KEY") // Call the API let response = try await client.getUserData(userToken: "test-user-token") // print the response print(response) - lang: cURL label: curl source: |- curl --request GET \ --url https://example.algolia.net/agent-studio/1/user-data/lorem \ --header 'accept: application/json' \ --header 'x-algolia-api-key: ALGOLIA_API_KEY' \ --header 'x-algolia-application-id: ALGOLIA_APPLICATION_ID' components: schemas: UserDataResponse: properties: conversations: items: $ref: '#/components/schemas/ConversationFullResponse' type: array title: conversations memories: items: $ref: '#/components/schemas/MemoryRecord' type: array title: memories type: object required: - conversations - memories title: userDataResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: detail type: object title: hTTPValidationError ConversationFullResponse: properties: agentId: type: string title: agentid createdAt: type: string title: createdat id: type: string title: id messages: items: $ref: '#/components/schemas/MessageResponse' type: array title: messages updatedAt: type: string title: updatedat conversationMetadata: oneOf: - $ref: '#/components/schemas/ConversationMetadata' - type: 'null' feedback: $ref: '#/components/schemas/FeedbackUnion' isFromDashboard: type: boolean title: isfromdashboard default: false lastActivityAt: oneOf: - type: string - type: 'null' title: lastactivityat messageCount: type: integer title: messagecount default: 0 title: oneOf: - type: string - type: 'null' title: title totalInputTokens: type: integer title: totalinputtokens default: 0 totalOutputTokens: type: integer title: totaloutputtokens default: 0 totalTokens: type: integer title: totaltokens default: 0 userToken: oneOf: - type: string - type: 'null' title: usertoken type: object required: - id - agentId - createdAt - updatedAt - messages title: conversationFullResponse description: Response model for a conversation with all its messages. MemoryRecord: properties: rawExtract: type: string maxLength: 5000 minLength: 1 title: rawextract description: Verbatim conversation extract, not paraphrased. text: type: string maxLength: 2000 minLength: 1 title: text description: Self-contained, first-person memory for long-term recall. _tags: items: type: string type: array title: tags description: >- Arbitrary labels/themes for flexible categorization (e.g., 'Q1-goals', 'paris-trip', 'vip-customer'). agentIDs: items: type: string type: array title: agentids description: >- Agent IDs with access: ['agent1'], ['*'] for all, ['*', '-agent1'] to exclude. appId: type: string title: appid description: Application ID. default: '' createdAt: type: integer title: createdat description: Epoch seconds. default: 0 episode: oneOf: - $ref: '#/components/schemas/Episode' - type: 'null' keywords: items: type: string type: array title: keywords description: >- 5-20 free-form keywords: entities, context, search terms (any words). memoryType: $ref: '#/components/schemas/MemoryType' objectID: oneOf: - type: string - type: 'null' title: objectid description: ObjectID of existing memory to update. Leave empty for new memory. recallTriggers: items: type: string type: array title: recalltriggers description: 3-5 natural phrases that should trigger this memory. topics: items: type: string type: array title: topics description: >- 2-4 topics ONLY from this list: [complaints, entertainment, family, feedback, finance, food, goals, health, history, hobbies, learning, praise, preferences, schedule, shopping, technical, travel, work]. updatedAt: type: integer title: updatedat description: Epoch seconds. default: 0 userID: type: string title: userid description: User ID. default: '' type: object required: - text - rawExtract title: memoryRecord description: >- Universal storage model for all memory types (semantic, episodic). This is the ONLY model that touches storage (Algolia). Domain models (SemanticMemory, EpisodicMemory) are used for LLM extraction and converted to MemoryRecord before saving. See https://langchain-ai.github.io/langmem/concepts/conceptual_guide/#memory-types for memory type definitions. ValidationError: properties: loc: items: $ref: '#/components/schemas/LocationItemUnion' type: array title: location msg: type: string title: message type: type: string title: errorType ctx: type: object title: context input: title: input type: object required: - loc - msg - type title: validationError MessageResponse: properties: conversationId: type: string title: conversationid createdAt: type: string title: createdat id: type: string title: id parts: items: $ref: '#/components/schemas/MessagePart' type: array title: parts role: $ref: '#/components/schemas/MessageRole' updatedAt: type: string title: updatedat inputTokens: oneOf: - type: integer - type: 'null' title: inputtokens model: oneOf: - type: string - type: 'null' title: model outputTokens: oneOf: - type: integer - type: 'null' title: outputtokens turnContext: oneOf: - additionalProperties: type: string type: object - type: 'null' title: turncontext type: object required: - id - conversationId - role - parts - createdAt - updatedAt title: messageResponse description: Response model for a message. ConversationMetadata: properties: cachedAt: oneOf: - type: string - type: 'null' title: cachedat type: object title: conversationMetadata description: Public metadata exposed on conversation responses. FeedbackUnion: oneOf: - items: $ref: '#/components/schemas/FeedbackResponse' type: array - type: 'null' Episode: properties: action: type: string maxLength: 5000 minLength: 1 title: action description: >- What was done with PRECISE details (1-3 sentences). WITH tool calls: use arrow notation `tool(param:value) → feedback → tool(refined_param:new_value)`. WITHOUT tool calls: capture communication/workflow pattern. observation: type: string maxLength: 5000 minLength: 1 title: observation description: >- What user wanted + key context (1-2 sentences). Include prior failed attempts if they informed the approach. result: type: string maxLength: 5000 minLength: 1 title: result description: >- Learned pattern + effectiveness (1-3 sentences). What worked and WHY it's replicable. Note efficiency: multi-turn refinements, which results were relevant, what made final attempt succeed. Use strict `param:value` syntax for learnings. Format: 'For [context], use [param:value] because [reason]'. thoughts: type: string maxLength: 5000 minLength: 1 title: thoughts description: >- WHY this approach was chosen, which constraints/preferences drove decisions (1-3 sentences). Capture reasoning that applies to similar future scenarios. type: object required: - observation - thoughts - action - result title: episode description: >- Episodic memory schema following LangMem's OTAR pattern: Observation → Thoughts → Action → Result Captures complete interaction experiences for agent learning. See https://langchain-ai.github.io/langmem/concepts/conceptual_guide/#episodic-memory-past-experiences. MemoryType: type: string enum: - semantic - episodic title: memoryType description: >- Memory types implemented so far. Follows LangMem's ontology: https://langchain-ai.github.io/langmem/concepts/conceptual_guide/#memory-types. LocationItemUnion: oneOf: - type: string - type: integer MessagePart: oneOf: - $ref: '#/components/schemas/TextPart' - $ref: '#/components/schemas/ToolCallPart' - $ref: '#/components/schemas/ToolResultPart' - $ref: '#/components/schemas/StartPart' - $ref: '#/components/schemas/StartStepPart' - $ref: '#/components/schemas/ReasoningPart' - $ref: '#/components/schemas/ToolApprovalRequestPart' discriminator: propertyName: type mapping: reasoning: $ref: '#/components/schemas/ReasoningPart' start: $ref: '#/components/schemas/StartPart' start-step: $ref: '#/components/schemas/StartStepPart' text: $ref: '#/components/schemas/TextPart' tool-approval-request: $ref: '#/components/schemas/ToolApprovalRequestPart' tool-call: $ref: '#/components/schemas/ToolCallPart' tool-result: $ref: '#/components/schemas/ToolResultPart' MessageRole: type: string enum: - user - assistant title: messageRole description: Role of a message in the conversation. FeedbackResponse: properties: agentId: type: string title: agentid createdAt: type: string title: createdat id: type: string title: id messageId: type: string title: messageid tags: items: type: string type: array title: tags updatedAt: type: string title: updatedat vote: type: integer title: vote model: oneOf: - type: string - type: 'null' title: model notes: oneOf: - type: string - type: 'null' title: notes type: object required: - id - agentId - messageId - vote - tags - createdAt - updatedAt title: feedbackResponse TextPart: properties: text: type: string title: text type: type: string const: text title: type default: text type: object required: - type - text title: textPart ToolCallPart: properties: args: title: args toolCallId: type: string title: toolcallid toolName: type: string title: toolname type: type: string const: tool-call title: type default: tool-call providerOptions: oneOf: - type: object additionalProperties: true - type: 'null' title: provideroptions requiresApproval: oneOf: - type: boolean - type: 'null' title: requiresapproval type: object required: - type - toolCallId - toolName - args title: toolCallPart ToolResultPart: properties: output: $ref: '#/components/schemas/ToolResultOutput' toolCallId: type: string title: toolcallid toolName: type: string title: toolname type: type: string const: tool-result title: type default: tool-result providerOptions: oneOf: - type: object additionalProperties: true - type: 'null' title: provideroptions type: object required: - type - toolCallId - toolName - output title: toolResultPart StartPart: properties: type: type: string const: start title: type default: start type: object title: startPart required: - type StartStepPart: properties: type: type: string const: start-step title: type default: start-step type: object title: startStepPart required: - type ReasoningPart: properties: text: type: string title: text type: type: string const: reasoning title: type default: reasoning type: object required: - type - text title: reasoningPart ToolApprovalRequestPart: properties: args: title: args toolCallId: type: string title: toolcallid toolName: type: string title: toolname type: type: string const: tool-approval-request title: type default: tool-approval-request appId: oneOf: - type: string - type: 'null' title: appid argsHash: oneOf: - type: string - type: 'null' title: argshash description: oneOf: - type: string - type: 'null' title: description providerOptions: oneOf: - type: object additionalProperties: true - type: 'null' title: provideroptions type: object required: - type - toolCallId - toolName - args title: toolApprovalRequestPart ToolResultOutput: properties: type: $ref: '#/components/schemas/ToolResultOutputType' value: title: value type: object required: - type - value title: toolResultOutput ToolResultOutputType: type: string enum: - text - json - error-text - error-json - content title: toolResultOutputType description: The valid 'type' of tool results. securitySchemes: appId: type: apiKey in: header name: x-algolia-application-id description: Your Algolia application ID. apiKey: type: apiKey in: header name: x-algolia-api-key description: > Your Algolia API key with the necessary permissions to make the request. Permissions are controlled through access control lists (ACL) and access restrictions. The required ACL to make a request is listed in each endpoint's reference. ````