> ## Documentation Index > Fetch the complete documentation index at: https://docs.memobase.io/llms.txt > Use this file to discover all available pages before exploring further. # Get User Personalized Context Return a string of the user's personalized context you can directly insert it into your prompt. Format: ``` # Memory Unless the user has relevant queries, do not actively mention those memories in the conversation. ## User Background: {profile} ## Latest Events: {event} ``` ## OpenAPI ````yaml get /api/v1/users/context/{user_id} openapi: 3.1.0 info: title: Memobase API summary: APIs for Memobase, a user memory system for LLM Apps version: 0.0.40 servers: - url: https://api.memobase.dev - url: https://api.memobase.cn security: - BearerAuth: [] paths: /api/v1/users/context/{user_id}: get: tags: - context summary: Get User Context operationId: get_user_context_api_v1_users_context__user_id__get parameters: - name: user_id in: path required: true schema: anyOf: - type: string format: uuid4 - type: string format: uuid5 description: The ID of the user title: User Id description: The ID of the user - name: max_token_size in: query required: false schema: type: integer description: Max token size of returned Context default: 1000 title: Max Token Size description: Max token size of returned Context - name: prefer_topics in: query required: false schema: type: array items: type: string description: >- Rank prefer topics at first to try to keep them in filtering, default order is by updated time title: Prefer Topics description: >- Rank prefer topics at first to try to keep them in filtering, default order is by updated time - name: only_topics in: query required: false schema: type: array items: type: string description: Only return profiles with these topics, default is all title: Only Topics description: Only return profiles with these topics, default is all - name: max_subtopic_size in: query required: false schema: type: integer description: Max subtopic size of the same topic in returned Context title: Max Subtopic Size description: Max subtopic size of the same topic in returned Context - name: topic_limits_json in: query required: false schema: type: string description: >- Set specific subtopic limits for topics in JSON, for example {"topic1": 3, "topic2": 5}. The limits in this param will override `max_subtopic_size`. title: Topic Limits Json description: >- Set specific subtopic limits for topics in JSON, for example {"topic1": 3, "topic2": 5}. The limits in this param will override `max_subtopic_size`. - name: profile_event_ratio in: query required: false schema: type: number description: Profile event ratio of returned Context default: 0.6 title: Profile Event Ratio description: Profile event ratio of returned Context - name: require_event_summary in: query required: false schema: type: boolean description: Whether to require event summary in returned Context default: false title: Require Event Summary description: Whether to require event summary in returned Context - name: chats_str in: query required: false schema: type: string description: > Pass the recent chats to enable context search. Memobase will use those chats to search for relevant events. It's a list of chats in OpenAI Message format, for example: [{"role": "user", "content": "Hello"}, {"role": "assistant", "content": "Hi"}]. **NOTICE** - It will increase your latency by 0.1-1 seconds, because Memobase will use Embedding to search for relevant profiles and events. - It will cost your Memobase tokens, roughly 100~200 tokens per chat based on the profile size. - The profiles in the context will not be searched by the `chats_str`. - If you want also search profiles, see `full_profile_and_only_search_event` query parameter. title: Chats Str description: > Pass the recent chats to enable context search. Memobase will use those chats to search for relevant events. It's a list of chats in OpenAI Message format, for example: [{"role": "user", "content": "Hello"}, {"role": "assistant", "content": "Hi"}]. **NOTICE** - It will increase your latency by 0.1-1 seconds, because Memobase will use Embedding to search for relevant profiles and events. - It will cost your Memobase tokens, roughly 100~200 tokens per chat based on the profile size. - The profiles in the context will not be searched by the `chats_str`. - If you want also search profiles, see `full_profile_and_only_search_event` query parameter. - name: event_similarity_threshold in: query required: false schema: type: number description: Event similarity threshold of returned Context default: 0.2 title: Event Similarity Threshold description: Event similarity threshold of returned Context - name: time_range_in_days in: query required: false schema: type: integer description: Only allow events within the past few days, default is 180 default: 180 title: Time Range In Days description: Only allow events within the past few days, default is 180 - name: customize_context_prompt in: query required: false schema: type: string description: > Customize context prompt template. - use `{profile_section}` to refer to the profile section - use `{event_section}` to refer to the event section For example: ``` # Memory Unless the user has relevant queries, do not actively mention those memories in the conversation. ## User Background: {profile_section} ## Latest Events: {event_section} ``` title: Customize Context Prompt description: > Customize context prompt template. - use `{profile_section}` to refer to the profile section - use `{event_section}` to refer to the event section For example: ``` # Memory Unless the user has relevant queries, do not actively mention those memories in the conversation. ## User Background: {profile_section} ## Latest Events: {event_section} ``` - name: full_profile_and_only_search_event in: query required: false schema: type: boolean description: > If you pass `chats_str` and set this to `False`, Memobase will search for relevant profiles and events at the same time. **NOTICE** - It will increase your latency by 2-5(based on the profile size) seconds, because Memobase will use LLM and Embedding to search for relevant profiles and events. - It will cost your Memobase tokens, roughly 100~1000 tokens per chat based on the profile size. default: true title: Full Profile And Only Search Event description: > If you pass `chats_str` and set this to `False`, Memobase will search for relevant profiles and events at the same time. **NOTICE** - It will increase your latency by 2-5(based on the profile size) seconds, because Memobase will use LLM and Embedding to search for relevant profiles and events. - It will cost your Memobase tokens, roughly 100~1000 tokens per chat based on the profile size. - name: fill_window_with_events in: query required: false schema: type: boolean description: >- If set to `True`, Memobase will fill the token window with the rest events. default: false title: Fill Window With Events description: >- If set to `True`, Memobase will fill the token window with the rest events. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/UserContextDataResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' x-code-samples: - lang: python source: >+ # To use the Python SDK, install the package: # pip install memobase from memobase import MemoBaseClient client = MemoBaseClient(project_url='PROJECT_URL', api_key='PROJECT_TOKEN') context = u.context() label: Python - lang: javascript source: >+ // To use the JavaScript SDK, install the package: // npm install @memobase/memobase import { MemoBaseClient } from '@memobase/memobase'; const client = new MemoBaseClient(process.env.MEMOBASE_PROJECT_URL, process.env.MEMOBASE_API_KEY); const user = await client.getUser(userId); const context = await user.context(); label: JavaScript - lang: go source: >+ // To use the Go SDK, install the package: // go get github.com/memodb-io/memobase/src/client/memobase-go@latest import ( "fmt" "log" "github.com/memodb-io/memobase/src/client/memobase-go/core" ) func main() { projectURL := "YOUR_PROJECT_URL" apiKey := "YOUR_API_KEY" // Initialize the client client, err := core.NewMemoBaseClient( projectURL, apiKey, ) if err != nil { log.Fatalf("Failed to create client: %v", err) } // Get user context userID := "EXISTING_USER_ID" // Replace with an actual user ID user, err := client.GetUser(userID, false) if err != nil { log.Fatalf("Failed to get user: %v", err) } context, err := user.Context(nil) if err != nil { log.Fatalf("Failed to get context: %v", err) } fmt.Printf("User context: %s ", context) } label: Go components: schemas: UserContextDataResponse: properties: data: anyOf: - $ref: '#/components/schemas/ContextData' - type: 'null' description: Response containing user context errno: $ref: '#/components/schemas/CODE' description: Error code, 0 means success default: 0 errmsg: type: string title: Errmsg description: Error message, empty when success default: '' type: object title: UserContextDataResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ContextData: properties: context: type: string title: Context description: Context string type: object required: - context title: ContextData CODE: type: integer enum: - 0 - 400 - 401 - 403 - 404 - 405 - 409 - 422 - 500 - 501 - 502 - 503 - 504 - 520 title: CODE ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: BearerAuth: type: http scheme: bearer ````