Perform pure semantic search using vector similarity. Args: ctx: Agent runtime context with dependencies query: Search q

Set a user preference for the session.

Perform hybrid search combining semantic and keyword matching. Args: ctx: Agent runtime context with dependencies query:

Generate embedding for text using OpenAI.

Initialize external connections.

Add a query to the search history.

Load settings with proper error handling.

Acquire a connection from the pool.

* Sanitizes HTML content to prevent XSS attacks * @param unsafe - The unsafe string that might contain HTML * @returns A safe string with HTML speci

Clean up external connections.

* Set a new stored value

Acquire a connection from the pool.

Simple text splitting as fallback. Args: text: Text to split Returns: List of chunk

Simple text splitting as fallback. Args: text: Text to split Returns: List of chunk

Chunk document using simple rules. Args: content: Document content title: Document title

Chunk document using simple rules. Args: content: Document content title: Document title

Create appropriate chunker based on configuration. Args: config: Chunking configuration Returns: Chunker instan

Create appropriate chunker based on configuration. Args: config: Chunking configuration Returns: Chunker instan

Display welcome message.

Create a DocumentChunk object.

Create a DocumentChunk object.

Create DocumentChunk objects from text chunks. Args: chunks: List of chunk texts original_content: O

Create DocumentChunk objects from text chunks. Args: chunks: List of chunk texts original_content: O

Generate hash for text.

Generate hash for text.

Process texts individually as fallback. Args: texts: List of texts to embed Returns:

Process texts individually as fallback. Args: texts: List of texts to embed Returns:

Analyze data and return structured report. Args: data_input: Raw data or description to analyze dependencies: Optional a

Analyze data and return structured report. Args: data_input: Raw data or description to analyze dependencies: Optional a

Ask the tool-enabled agent a question. Args: question: Question or request for the agent dependencies: Optional tool dep

Ask the tool-enabled agent a question. Args: question: Question or request for the agent dependencies: Optional tool dep

Create embedding generator with optional caching. Args: model: Embedding model to use use_cache: Whether to use caching

Create embedding generator with optional caching. Args: model: Embedding model to use use_cache: Whether to use caching

Generate embeddings for document chunks. Args: chunks: List of document chunks progress_callback: Op

Generate embeddings for document chunks. Args: chunks: List of document chunks progress_callback: Op

Generate embedding for a single text. Args: text: Text to embed Returns: Embedding

Generate embedding for a single text. Args: text: Text to embed Returns: Embedding

* Parses the signed cookie and verifies its integrity. * @param cookieHeader - The value of the Cookie header from the request. * @param secret - Th

Get OpenAI client for embeddings. Returns: Configured OpenAI client for embeddings

Get OpenAI client for embeddings. Returns: Configured OpenAI client for embeddings

Get embedding model name. Returns: Embedding model name

Get embedding model name. Returns: Embedding model name

Get LLM model configuration based on environment variables. Args: model_choice: Optional override for model choice Retu

Get LLM model configuration based on environment variables. Args: model_choice: Optional override for model choice Retu

Get LLM model configuration based on environment variables. Supports any OpenAI-compatible API provider. Args: model_choice:

Get LLM model configuration for OpenAI. Returns: Configured OpenAI model

* Imports a secret key string for HMAC-SHA256 signing. * @param secret - The raw secret key string. * @returns A promise resolving to the CryptoKey

Create connection pool.

Create connection pool.

Check if a path should be ignored based on gitignore patterns. Args: path: Path to check template_root: Root directory o

Clean existing data from databases.

Clean existing data from databases.

Extract metadata from document content.

Extract metadata from document content.

Extract title from document content or filename.

Extract title from document content or filename.

Find all markdown files in the documents folder.

Find all markdown files in the documents folder.

Ingest a single document. Args: file_path: Path to the document file Returns: Inges

Ingest a single document. Args: file_path: Path to the document file Returns: Inges

Read document content from file.

Read document content from file.

Save document and chunks to PostgreSQL.

Save document and chunks to PostgreSQL.

Perform semantic chunking using LLM. Args: content: Content to chunk Returns: List

Perform semantic chunking using LLM. Args: content: Content to chunk Returns: List

Simple rule-based chunking. Args: content: Content to chunk base_metadata: Base metadata for chunks

Simple rule-based chunking. Args: content: Content to chunk base_metadata: Base metadata for chunks

Split a long section using LLM for semantic boundaries. Args: section: Section to split Returns

Split a long section using LLM for semantic boundaries. Args: section: Section to split Returns

Split content on structural boundaries. Args: content: Content to split Returns: Li

Split content on structural boundaries. Args: content: Content to split Returns: Li

Main function to chat with the agent. Args: message: User's message to the agent context: Optional conversation context

Main function to chat with the agent. Args: message: User's message to the agent context: Optional conversation context