@exulu/backend 1.48.2 → 1.49.0

package/mintlify-docs/core/exulu-context/configuration.mdx

@@ -1,648 +0,0 @@
----
-title: "Configuration"
-description: "Complete guide to configuring ExuluContext for semantic search"
----
-
-## Constructor parameters
-
-The ExuluContext constructor accepts a configuration object with the following parameters:
-
-```typescript
-const context = new ExuluContext({
-  id: string,
-  name: string,
-  description: string,
-  active: boolean,
-  fields: ExuluContextFieldDefinition[],
-  embedder?: ExuluEmbedder,
-  processor?: ExuluContextProcessor,
-  sources: ExuluContextSource[],
-  rateLimit?: RateLimiterRule,
-  queryRewriter?: (query: string) => Promise<string>,
-  resultReranker?: (results: any[]) => Promise<any[]>,
-  configuration?: { /* ... */ }
-});
-```
-
-## Required parameters
-
-### id
-
-<ParamField path="id" type="string" required>
-  Unique identifier for the context. Must be a valid PostgreSQL identifier: start with a letter or underscore, contain only letters, digits, or underscores, 5-80 characters long.
-</ParamField>
-
-```typescript
-id: "product_docs"
-```
-
-<Warning>
-  The ID is used for database table names and should not change after creation. Changing the ID requires database migration.
-</Warning>
-
-### name
-
-<ParamField path="name" type="string" required>
-  Human-readable name displayed in UI and logs
-</ParamField>
-
-```typescript
-name: "Product Documentation"
-```
-
-### description
-
-<ParamField path="description" type="string" required>
-  Description of what information this context contains. Used in the auto-generated tool description for agents.
-</ParamField>
-
-```typescript
-description: "Product documentation, help articles, and tutorials for end users"
-```
-
-### active
-
-<ParamField path="active" type="boolean" required>
-  Whether this context is active and available for use
-</ParamField>
-
-```typescript
-active: true
-```
-
-### fields
-
-<ParamField path="fields" type="ExuluContextFieldDefinition[]" required>
-  Array of field definitions that define the schema for items in this context
-</ParamField>
-
-```typescript
-fields: [
-  {
-    name: "title",
-    type: "text",
-    required: true,
-    editable: true
-  },
-  {
-    name: "content",
-    type: "text",
-    required: true
-  },
-  {
-    name: "category",
-    type: "text",
-    index: true,
-    enumValues: ["guide", "reference", "tutorial"]
-  }
-]
-```
-
-#### Field definition properties
-
-<ParamField path="fields[].name" type="string" required>
-  Field name (must be valid PostgreSQL column name)
-</ParamField>
-
-<ParamField path="fields[].type" type="ExuluFieldTypes" required>
-  Field type: `text`, `number`, `boolean`, `date`, `json`, `file`, `longtext`, `decimal`, `integer`, `timestamp`
-</ParamField>
-
-<ParamField path="fields[].required" type="boolean">
-  Whether this field is required when creating items
-</ParamField>
-
-<ParamField path="fields[].editable" type="boolean">
-  Whether this field can be edited after creation
-</ParamField>
-
-<ParamField path="fields[].unique" type="boolean">
-  Whether this field must have unique values
-</ParamField>
-
-<ParamField path="fields[].index" type="boolean">
-  Whether to create a database index on this field for faster queries
-</ParamField>
-
-<ParamField path="fields[].default" type="any">
-  Default value for this field
-</ParamField>
-
-<ParamField path="fields[].calculated" type="boolean">
-  Whether this field is calculated/computed rather than user-provided
-</ParamField>
-
-<ParamField path="fields[].enumValues" type="string[]">
-  For text fields, restrict values to this list of allowed values
-</ParamField>
-
-<ParamField path="fields[].allowedFileTypes" type="allFileTypes[]">
-  For file fields, restrict allowed file types (e.g., `["pdf", "docx", "txt"]`)
-</ParamField>
-
-### sources
-
-<ParamField path="sources" type="ExuluContextSource[]" required>
-  Array of data sources that populate this context
-</ParamField>
-
-```typescript
-sources: [
-  {
-    id: "github_issues",
-    name: "GitHub Issues",
-    description: "Syncs issues from GitHub repository",
-    config: {
-      schedule: "0 */6 * * *", // Every 6 hours
-      queue: await ExuluQueues.register("github_sync"),
-      retries: 3,
-      backoff: {
-        type: "exponential",
-        delay: 2000
-      }
-    },
-    execute: async ({ exuluConfig }) => {
-      const issues = await fetchGitHubIssues();
-      return issues.map(issue => ({
-        external_id: issue.id,
-        name: issue.title,
-        content: issue.body,
-        metadata: { labels: issue.labels }
-      }));
-    }
-  }
-]
-```
-
-#### Source configuration
-
-<ParamField path="sources[].id" type="string" required>
-  Unique identifier for the source
-</ParamField>
-
-<ParamField path="sources[].name" type="string" required>
-  Human-readable source name
-</ParamField>
-
-<ParamField path="sources[].description" type="string" required>
-  Description of what this source provides
-</ParamField>
-
-<ParamField path="sources[].config.schedule" type="string">
-  Cron expression for scheduled execution (e.g., `"0 * * * *"` for hourly)
-</ParamField>
-
-<ParamField path="sources[].config.queue" type="Promise<ExuluQueueConfig>">
-  Queue configuration for background processing
-</ParamField>
-
-<ParamField path="sources[].config.retries" type="number">
-  Number of retry attempts on failure (default: 3)
-</ParamField>
-
-<ParamField path="sources[].config.backoff" type="object">
-  Backoff strategy for retries: `{ type: "exponential" | "linear", delay: number }`
-</ParamField>
-
-<ParamField path="sources[].execute" type="function" required>
-  Async function that fetches and returns items from the source
-</ParamField>
-
-## Optional parameters
-
-### embedder
-
-<ParamField path="embedder" type="ExuluEmbedder">
-  Embedder instance that generates vector embeddings for items
-</ParamField>
-
-```typescript
-import { ExuluEmbedder } from "@exulu/backend";
-
-embedder: new ExuluEmbedder({
-  id: "openai_embedder",
-  name: "OpenAI Embeddings",
-  provider: "openai",
-  model: "text-embedding-3-small",
-  vectorDimensions: 1536,
-  template: "{{title}}\n\n{{content}}"
-})
-```
-
-<Note>
-  Without an embedder, semantic search is not available. You can still use the context for structured data storage and retrieval.
-</Note>
-
-### processor
-
-<ParamField path="processor" type="ExuluContextProcessor">
-  Processor that transforms items before storage or embeddings generation
-</ParamField>
-
-```typescript
-processor: {
-  name: "PDF Text Extractor",
-  config: {
-    trigger: "onInsert", // or "onUpdate", "always", "manual"
-    generateEmbeddings: true, // Auto-trigger embeddings after processing
-    queue: await ExuluQueues.register("processing"),
-    timeoutInSeconds: 300,
-    retries: 2,
-    backoff: {
-      type: "exponential",
-      delay: 2000
-    }
-  },
-  filter: async ({ item, user }) => {
-    // Optional: Filter which items to process
-    return item.document_s3key !== undefined;
-  },
-  execute: async ({ item, utils, exuluConfig }) => {
-    // Transform the item
-    const text = await utils.storage.extractText(item.document_s3key);
-    return {
-      ...item,
-      content: text,
-      textlength: text.length
-    };
-  }
-}
-```
-
-### rateLimit
-
-<ParamField path="rateLimit" type="RateLimiterRule">
-  Rate limiting rules for API access to this context
-</ParamField>
-
-```typescript
-rateLimit: {
-  points: 100,      // Number of requests
-  duration: 60,     // Time window in seconds
-  blockDuration: 60 // Block duration after exceeding limit
-}
-```
-
-### queryRewriter
-
-<ParamField path="queryRewriter" type="(query: string) => Promise<string>">
-  Function that rewrites queries before search to improve results
-</ParamField>
-
-```typescript
-queryRewriter: async (query: string) => {
-  // Use an LLM to expand or clarify the query
-  const response = await openai.chat.completions.create({
-    model: "gpt-4",
-    messages: [
-      {
-        role: "system",
-        content: "Expand this query to improve search results"
-      },
-      {
-        role: "user",
-        content: query
-      }
-    ]
-  });
-  return response.choices[0].message.content;
-}
-```
-
-### resultReranker
-
-<ParamField path="resultReranker" type="(results: any[]) => Promise<any[]>">
-  Function that reranks search results based on custom logic or a reranker model
-</ParamField>
-
-```typescript
-resultReranker: async (results) => {
-  // Use a reranker to improve result ordering
-  const reranked = await cohereReranker.rerank({
-    query: results[0].query,
-    documents: results.map(r => r.chunk_content)
-  });
-
-  return reranked.results.map(r => results[r.index]);
-}
-```
-
-## Configuration object
-
-<ParamField path="configuration" type="object">
-  Additional configuration options for search behavior
-</ParamField>
-
-### calculateVectors
-
-<ParamField path="configuration.calculateVectors" type="'manual' | 'onUpdate' | 'onInsert' | 'always'">
-  When to automatically generate embeddings for items (default: `"manual"`)
-</ParamField>
-
-```typescript
-configuration: {
-  calculateVectors: "onInsert" // Generate embeddings when items are created
-}
-```
-
-<Tabs>
-  <Tab title="manual">
-    Never auto-generate embeddings. You must call `embeddings.generate.one()` or `embeddings.generate.all()` manually.
-  </Tab>
-
-  <Tab title="onInsert">
-    Generate embeddings when new items are created
-  </Tab>
-
-  <Tab title="onUpdate">
-    Generate embeddings when items are updated
-  </Tab>
-
-  <Tab title="always">
-    Generate embeddings on both insert and update
-  </Tab>
-</Tabs>
-
-### maxRetrievalResults
-
-<ParamField path="configuration.maxRetrievalResults" type="number">
-  Maximum number of results to return from search queries (default: `10`)
-</ParamField>
-
-```typescript
-configuration: {
-  maxRetrievalResults: 20
-}
-```
-
-### defaultRightsMode
-
-<ParamField path="configuration.defaultRightsMode" type="'private' | 'public' | 'restricted'">
-  Default access control mode for new items (default: `"private"`)
-</ParamField>
-
-```typescript
-configuration: {
-  defaultRightsMode: "public"
-}
-```
-
-### enableAsTool
-
-<ParamField path="configuration.enableAsTool" type="boolean">
-  Whether to automatically expose this context as a tool for agents (default: `true`)
-</ParamField>
-
-```typescript
-configuration: {
-  enableAsTool: true // Agents can query this context
-}
-```
-
-<Info>
-  When enabled, agents receive a tool called `{context_name}_context_search` that they can use to query this context.
-</Info>
-
-### cutoffs
-
-<ParamField path="configuration.cutoffs" type="object">
-  Minimum relevance scores for different search methods
-</ParamField>
-
-```typescript
-configuration: {
-  cutoffs: {
-    cosineDistance: 0.7,  // Min similarity for semantic search (0-1)
-    tsvector: 0.5,        // Min score for keyword search
-    hybrid: 0.6           // Min score for hybrid search
-  }
-}
-```
-
-Results below these thresholds are filtered out.
-
-### expand
-
-<ParamField path="configuration.expand" type="object">
-  Number of surrounding chunks to include with each result
-</ParamField>
-
-```typescript
-configuration: {
-  expand: {
-    before: 1, // Include 1 chunk before the matched chunk
-    after: 2   // Include 2 chunks after the matched chunk
-  }
-}
-```
-
-This provides more context around matched chunks, improving the agent's understanding.
-
-### language
-
-<ParamField path="configuration.language" type="'english' | 'german'">
-  Language for full-text search indexing (default: `"english"`)
-</ParamField>
-
-```typescript
-configuration: {
-  language: "german" // Use German text search configuration
-}
-```
-
-This affects stemming and stop words in keyword search.
-
-## Complete example
-
-```typescript
-import {
-  ExuluContext,
-  ExuluEmbedder,
-  ExuluQueues
-} from "@exulu/backend";
-
-const embedder = new ExuluEmbedder({
-  id: "openai_ada",
-  name: "OpenAI Ada",
-  provider: "openai",
-  model: "text-embedding-3-small",
-  vectorDimensions: 1536,
-  template: "Title: {{title}}\nCategory: {{category}}\n\n{{content}}"
-});
-
-const docsContext = new ExuluContext({
-  id: "product_docs",
-  name: "Product Documentation",
-  description: "Comprehensive product docs including guides, API references, and tutorials",
-  active: true,
-
-  fields: [
-    {
-      name: "title",
-      type: "text",
-      required: true,
-      index: true
-    },
-    {
-      name: "content",
-      type: "longtext",
-      required: true
-    },
-    {
-      name: "category",
-      type: "text",
-      enumValues: ["guide", "api", "tutorial", "reference"],
-      index: true
-    },
-    {
-      name: "url",
-      type: "text",
-      unique: true
-    },
-    {
-      name: "last_updated",
-      type: "timestamp"
-    },
-    {
-      name: "metadata",
-      type: "json"
-    }
-  ],
-
-  embedder: embedder,
-
-  processor: {
-    name: "Markdown Processor",
-    config: {
-      trigger: "onInsert",
-      generateEmbeddings: true,
-      queue: await ExuluQueues.register("doc_processing")
-    },
-    execute: async ({ item }) => {
-      // Process markdown, extract headings, etc.
-      const processed = processMarkdown(item.content);
-      return {
-        ...item,
-        content: processed.text,
-        metadata: { headings: processed.headings }
-      };
-    }
-  },
-
-  sources: [
-    {
-      id: "github_docs",
-      name: "GitHub Documentation",
-      description: "Sync docs from GitHub repository",
-      config: {
-        schedule: "0 */4 * * *", // Every 4 hours
-        queue: await ExuluQueues.register("github_sync"),
-        retries: 3,
-        backoff: {
-          type: "exponential",
-          delay: 2000
-        }
-      },
-      execute: async ({ exuluConfig }) => {
-        const docs = await fetchGitHubDocs();
-        return docs.map(doc => ({
-          external_id: doc.path,
-          name: doc.title,
-          content: doc.content,
-          category: doc.category,
-          url: doc.url,
-          last_updated: doc.updatedAt
-        }));
-      }
-    }
-  ],
-
-  rateLimit: {
-    points: 100,
-    duration: 60,
-    blockDuration: 60
-  },
-
-  queryRewriter: async (query) => {
-    // Expand query with LLM
-    return expandQuery(query);
-  },
-
-  resultReranker: async (results) => {
-    // Rerank with Cohere
-    return rerankResults(results);
-  },
-
-  configuration: {
-    calculateVectors: "onInsert",
-    maxRetrievalResults: 15,
-    defaultRightsMode: "public",
-    enableAsTool: true,
-    cutoffs: {
-      cosineDistance: 0.65,
-      tsvector: 0.5,
-      hybrid: 0.6
-    },
-    expand: {
-      before: 1,
-      after: 2
-    },
-    language: "english"
-  }
-});
-```
-
-## Field type reference
-
-<AccordionGroup>
-  <Accordion title="text">
-    Short text field (VARCHAR). Use for titles, names, categories, etc.
-  </Accordion>
-
-  <Accordion title="longtext">
-    Long text field (TEXT). Use for descriptions, articles, documentation content.
-  </Accordion>
-
-  <Accordion title="number">
-    Floating point number (DOUBLE PRECISION)
-  </Accordion>
-
-  <Accordion title="integer">
-    Whole number (INTEGER)
-  </Accordion>
-
-  <Accordion title="decimal">
-    Precise decimal number (DECIMAL)
-  </Accordion>
-
-  <Accordion title="boolean">
-    True/false value (BOOLEAN)
-  </Accordion>
-
-  <Accordion title="date">
-    Date without time (DATE)
-  </Accordion>
-
-  <Accordion title="timestamp">
-    Date with time (TIMESTAMP)
-  </Accordion>
-
-  <Accordion title="json">
-    JSON object or array (JSONB)
-  </Accordion>
-
-  <Accordion title="file">
-    S3 file reference. Creates a `{field_name}_s3key` column that stores the S3 object key.
-  </Accordion>
-</AccordionGroup>
-
-## Next steps
-
-<CardGroup cols={2}>
-  <Card title="API reference" icon="code" href="/core/exulu-context/api-reference">
-    Explore all methods and properties
-  </Card>
-  <Card title="ExuluEmbedder" icon="brain" href="/core/exulu-embedder/introduction">
-    Learn about configuring embedders
-  </Card>
-</CardGroup>