@pairsystems/goodmem-client

v1.0.237-alpha

Published

a day ago

JavaScript client for GoodMem API

0High
0Medium
0Low

zabdulre

amin991

weisifan

@pairsystems/goodmem-client

GoodMemClient - JavaScript client for @pairsystems/goodmem-client No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) This SDK is automatically generated by the OpenAPI Generator project:

API version:
Package version: 1.0.237-alpha
Generator version: 7.21.0-SNAPSHOT
Build package: org.openapitools.codegen.languages.JavascriptClientCodegen

Installation

For Node.js

npm

To publish the library as a npm, please follow the procedure in "Publishing npm packages".

Then install it via:

npm install @pairsystems/goodmem-client --save

Finally, you need to build the module:

npm run build

Local development

To use the library locally without publishing to a remote npm registry, first install the dependencies by changing into the directory containing package.json (and this README). Let's call this JAVASCRIPT_CLIENT_DIR. Then run:

npm install

Next, link it globally in npm with the following, also from JAVASCRIPT_CLIENT_DIR:

npm link

To use the link you just defined in your project, switch to the directory you want to use your @pairsystems/goodmem-client from, and run:

npm link /path/to/<JAVASCRIPT_CLIENT_DIR>

Finally, you need to build the module:

npm run build

git

If the library is hosted at a git repository, e.g.https://github.com/PAIR-Systems-Inc/goodmem/clients/js then install it via:

    npm install PAIR-Systems-Inc/goodmem/clients/js --save

For browser

The library also works in the browser environment via npm and browserify. After following the above steps with Node.js and installing browserify with npm install -g browserify, perform the following (assuming main.js is your entry file):

browserify main.js > bundle.js

Then include bundle.js in the HTML pages.

Webpack Configuration

Using Webpack you may encounter the following error: "Module not found: Error: Cannot resolve module", most certainly you should disable AMD loader. Add/merge the following section to your webpack config:

module: {
  rules: [
    {
      parser: {
        amd: false
      }
    }
  ]
}

Getting Started

Please follow the installation instruction and execute the following JS code:

var GoodMemClient = require('@pairsystems/goodmem-client');

// Configure the API client
var defaultClient = GoodMemClient.ApiClient.instance;
defaultClient.basePath = "http://localhost:8080";  // Use your server URL

// Configure API key authentication: X-API-Key header
defaultClient.defaultHeaders = {
    "X-API-Key": "your-api-key-here",
    "Content-Type": "application/json",
    "Accept": "application/json"
};


var api = new GoodMemClient.APIKeysApi()
var createApiKeyRequest = {"labels":{"environment":"development","service":"chat-ui"},"expiresAt":"1735689600000"}; // {CreateApiKeyRequest} API key configuration
api.createApiKey(createApiKeyRequest).then(function(data) {
  console.log('API called successfully. Returned data: ' + data);
}, function(error) {
  console.error(error);
});

Streaming Memory Retrieval

The GoodMem JavaScript client provides a StreamingClient class for real-time streaming memory retrieval. This is the recommended approach for memory retrieval operations.

Supported Formats

The StreamingClient supports two streaming formats:

NDJSON (application/x-ndjson) - Newline-delimited JSON (default, recommended)
SSE (text/event-stream) - Server-Sent Events

Basic Streaming with ChatPostProcessor

Use retrieveMemoryStreamChat() for streaming with automatic ChatPostProcessor configuration:

const GoodMemClient = require('@pairsystems/goodmem-client');
const { StreamingClient } = GoodMemClient;

// Configure client
const defaultClient = GoodMemClient.ApiClient.instance;
defaultClient.basePath = 'http://localhost:8080';
defaultClient.defaultHeaders = {
    'X-API-Key': 'your-api-key'
};

// Create streaming client
const streamingClient = new StreamingClient(defaultClient);

// Create abort controller
const controller = new AbortController();

// Stream with ChatPostProcessor (NDJSON format)
streamingClient.retrieveMemoryStreamChat(
    controller.signal,
    'your search query',
    ['space-uuid'],
    10,                    // requested size
    true,                  // fetch memory
    false,                 // fetch memory content
    'ndjson',              // format (ndjson or sse)
    'llm-uuid',            // LLM ID
    'reranker-uuid',       // reranker ID
    0.5,                   // relevance threshold
    0.3,                   // LLM temperature
    10,                    // max results
    true                   // chronological resort
).then(async (stream) => {
    for await (const event of stream) {
        if (event.abstractReply) {
            console.log('Abstract:', event.abstractReply.text);
        } else if (event.retrievedItem && event.retrievedItem.memory) {
            console.log('Memory:', event.retrievedItem.memory);
        }
    }
}).catch(error => {
    console.error('Streaming error:', error);
});

Advanced Streaming with Custom Post-Processor

Use retrieveMemoryStreamAdvanced() for custom post-processor configuration:

// Create advanced request
const request = {
    message: 'your search query',
    spaceIds: ['space-uuid'],
    requestedSize: 10,
    fetchMemory: true,
    fetchMemoryContent: false,
    format: 'ndjson',  // or 'sse'
    postProcessorName: 'com.goodmem.retrieval.postprocess.ChatPostProcessorFactory',
    postProcessorConfig: {
        llm_id: 'llm-uuid',
        reranker_id: 'reranker-uuid',
        relevance_threshold: 0.5,
        llm_temp: 0.3,
        max_results: 10,
        chronological_resort: true
    }
};

// Execute advanced streaming
streamingClient.retrieveMemoryStreamAdvanced(controller.signal, request)
    .then(async (stream) => {
        for await (const event of stream) {
            if (event.abstractReply) {
                console.log('Abstract:', event.abstractReply.text);
            } else if (event.retrievedItem) {
                console.log('Retrieved:', event.retrievedItem);
            }
        }
    }).catch(error => {
        console.error('Streaming error:', error);
    });

Choosing Between NDJSON and SSE

NDJSON (recommended): Simpler parsing, better for most use cases
SSE: Standard browser EventSource API compatible, useful for web applications

Authentication

Configure API key authentication by setting the X-API-Key header:

var GoodMemClient = require("@pairsystems/goodmem-client");

// Configure the API client
var defaultClient = GoodMemClient.ApiClient.instance;
defaultClient.basePath = "http://localhost:8080";  // Use your server URL

// Configure API key authentication
defaultClient.defaultHeaders = {
    "X-API-Key": "your-api-key-here",
    "Content-Type": "application/json",
    "Accept": "application/json"
};

// Create API instances
var apiKeysApi = new GoodMemClient.APIKeysApi();
var spacesApi = new GoodMemClient.SpacesApi();

Getting an API Key

You can create an API key using the APIKeysApi:

var createRequest = {
    labels: {
        "environment": "development",
        "service": "your-app-name"
    }
};

apiKeysApi.createApiKey(createRequest).then(function(response) {
    console.log("API Key created successfully:");
    console.log("Key ID:", response.apiKeyMetadata.apiKeyId);
    console.log("Raw API Key:", response.rawApiKey);
    console.log("Key Prefix:", response.apiKeyMetadata.keyPrefix);
}, function(error) {
    console.error("Error creating API key:", error);
});

Documentation for API Endpoints

All URIs are relative to http://localhost

Class | Method | HTTP request | Description ------------ | ------------- | ------------- | ------------- GoodMemClient.APIKeysApi | createApiKey | POST /v1/apikeys | Create a new API key GoodMemClient.APIKeysApi | deleteApiKey | DELETE /v1/apikeys/{id} | Delete an API key GoodMemClient.APIKeysApi | listApiKeys | GET /v1/apikeys | List API keys GoodMemClient.APIKeysApi | updateApiKey | PUT /v1/apikeys/{id} | Update an API key GoodMemClient.AdministrationApi | drainServer | POST /v1/admin:drain | Request the server to enter drain mode GoodMemClient.AdministrationApi | purgeBackgroundJobs | POST /v1/admin/background-jobs:purge | Purge completed background jobs GoodMemClient.AdministrationApi | reloadLicense | POST /v1/admin/license:reload | Reload the active license from disk GoodMemClient.EmbeddersApi | createEmbedder | POST /v1/embedders | Create a new embedder GoodMemClient.EmbeddersApi | deleteEmbedder | DELETE /v1/embedders/{id} | Delete an embedder GoodMemClient.EmbeddersApi | getEmbedder | GET /v1/embedders/{id} | Get an embedder by ID GoodMemClient.EmbeddersApi | listEmbedders | GET /v1/embedders | List embedders GoodMemClient.EmbeddersApi | updateEmbedder | PUT /v1/embedders/{id} | Update an embedder GoodMemClient.LLMsApi | createLLM | POST /v1/llms | Create a new LLM GoodMemClient.LLMsApi | deleteLLM | DELETE /v1/llms/{id} | Delete an LLM GoodMemClient.LLMsApi | getLLM | GET /v1/llms/{id} | Get an LLM by ID GoodMemClient.LLMsApi | listLLMs | GET /v1/llms | List LLMs GoodMemClient.LLMsApi | updateLLM | PUT /v1/llms/{id} | Update an LLM GoodMemClient.MemoriesApi | batchCreateMemory | POST /v1/memories:batchCreate | Create multiple memories in a batch GoodMemClient.MemoriesApi | batchDeleteMemory | POST /v1/memories:batchDelete | Delete memories in batch GoodMemClient.MemoriesApi | batchGetMemory | POST /v1/memories:batchGet | Get multiple memories by ID GoodMemClient.MemoriesApi | createMemory | POST /v1/memories | Create a new memory GoodMemClient.MemoriesApi | deleteMemory | DELETE /v1/memories/{id} | Delete a memory GoodMemClient.MemoriesApi | getMemory | GET /v1/memories/{id} | Get a memory by ID GoodMemClient.MemoriesApi | getMemoryContent | GET /v1/memories/{id}/content | Download memory content GoodMemClient.MemoriesApi | listMemories | GET /v1/spaces/{spaceId}/memories | List memories in a space GoodMemClient.MemoriesApi | retrieveMemory | GET /v1/memories:retrieve | Stream semantic memory retrieval GoodMemClient.MemoriesApi | retrieveMemoryAdvanced | POST /v1/memories:retrieve | Advanced semantic memory retrieval with JSON GoodMemClient.OCRApi | ocrDocument | POST /v1/ocr:document | Run OCR on a document or image GoodMemClient.PingApi | pingOnce | POST /v1/ping:once | Run a single ping probe GoodMemClient.PingApi | pingStream | POST /v1/ping:stream | Stream ping probe results GoodMemClient.RerankersApi | createReranker | POST /v1/rerankers | Create a new reranker GoodMemClient.RerankersApi | deleteReranker | DELETE /v1/rerankers/{id} | Delete a reranker GoodMemClient.RerankersApi | getReranker | GET /v1/rerankers/{id} | Get a reranker by ID GoodMemClient.RerankersApi | listRerankers | GET /v1/rerankers | List rerankers GoodMemClient.RerankersApi | updateReranker | PUT /v1/rerankers/{id} | Update a reranker GoodMemClient.SpacesApi | createSpace | POST /v1/spaces | Create a new Space GoodMemClient.SpacesApi | deleteSpace | DELETE /v1/spaces/{id} | Delete a space GoodMemClient.SpacesApi | getSpace | GET /v1/spaces/{id} | Get a space by ID GoodMemClient.SpacesApi | listSpaces | GET /v1/spaces | List spaces GoodMemClient.SpacesApi | updateSpace | PUT /v1/spaces/{id} | Update a space GoodMemClient.SystemApi | getSystemInfo | GET /v1/system/info | Retrieve server build metadata GoodMemClient.SystemApi | initializeSystem | POST /v1/system/init | Initialize the system GoodMemClient.UsersApi | getCurrentUser | GET /v1/users/me | Get current user profile GoodMemClient.UsersApi | getUser | GET /v1/users/{id} | Get a user by ID GoodMemClient.UsersApi | getUserByEmail | GET /v1/users/email/{email} | Get user by email address

Documentation for Models

Documentation for Authorization

Authentication required - see configuration below.

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

@pairsystems/goodmem-client

Installation

For Node.js

npm

Local development

git

For browser

Webpack Configuration

Getting Started

Streaming Memory Retrieval

Supported Formats

Basic Streaming with ChatPostProcessor

Advanced Streaming with Custom Post-Processor

Choosing Between NDJSON and SSE

Authentication

Getting an API Key

Documentation for API Endpoints

Documentation for Models

Documentation for Authorization