View Source API Reference fnord v0.5.5

AI is a behavior module that defines the interface for interacting with OpenAI's API. It provides a common interface for the various OpenAI-powered operations used by the application.

When file or other input to too large for the model's context window, this module may be used to process the file in chunks. It automatically modifies the supplied agent prompt to include instructions for accumulating a response across multiple chunks based on the max_tokens parameter supplied to the get_response function.

This module provides an agent that summarizes files' contents in order to generate embeddings for the database and summaries for the user.

This module sends a request to the model and handles the response. It is able to handle tool calls and responses.

This module provides functions to interact with the OpenAI API, including getting embeddings and completions.

This module is used to split a string into chunks by the number of tokens, while accounting for other data that might be going with it to the API endpoint with the limited token count.

Oh yeah? I'm gonna make my own tokenizer, with blackjack and hookers!

Implements the default tokenizer behaviour for AI.Tokenizer.

This module implements the cl100k-base tokenizer model used by OpenAI's text-embedding-3-large model.

This module implements the o200k-base tokenizer model used by OpenAI's gpt-4o models.

This module defines the behaviour for tool calls. Defining a new tool requires implementing the spec/0 and call/2 functions.

Fnord is a code search tool that uses OpenAI's embeddings API to index and search code files.

Module for interacting with git.

This behaviour wraps the AI-powered operations used by Cmd.Index to allow overrides for testing. See impl/0.

A module that implements a process pool using a GenServer.

Conversations are stored per project in the project's store dir, under converations/. Each conversation is given a UUID identifier and stored as a JSON file with the keys

The ask subcommand saves useful prompts to the store. Saved prompts are accompanied by a title and a list of example questions for which the prompt is appropriate.