georgeguimaraes

georgeguimaraes

I’m excited to share Arcana, a RAG (Retrieval Augmented Generation) library I’ve been building for Elixir/Phoenix applications.

What is it?

Arcana lets you add vector search, document retrieval, and AI-powered Q&A to any Phoenix app. It’s designed to be embeddable - it uses your existing Ecto Repo and PostgreSQL with pgvector, no separate vector database needed.

Key Features

Simple API for basic RAG:

  {:ok, doc} = Arcana.ingest("Your content", repo: MyApp.Repo)
  results = Arcana.search("query", repo: MyApp.Repo, mode: :hybrid)
  {:ok, answer} = Arcana.ask("What is Elixir?", repo: MyApp.Repo, llm: "openai:gpt-4o")

Agentic RAG Pipeline for complex questions:

  ctx =
    Agent.new("Compare Elixir and Erlang")
    |> Agent.select(collections: ["elixir-docs", "erlang-docs"])
    |> Agent.expand()
    |> Agent.decompose()
    |> Agent.search()
    |> Agent.rerank(threshold: 7)
    |> Agent.answer(self_correct: true)

The pipeline includes query rewriting, collection routing, query expansion, question decomposition, re-ranking, and self-correcting answers (reduces hallucinations by verifying answers are grounded in context).

Embeddings with Nx/Bumblebee:

  • Local embeddings with bge-small-en-v1.5 - no API keys needed
  • Or use OpenAI embeddings
  • Or bring your own via the Arcana.Embedder behaviour

Pluggable Everything:

Every pipeline step has a behaviour you can implement:

defmodule MyApp.CrossEncoderReranker do
    @behaviour Arcana.Agent.Reranker

    @impl true
    def rerank(question, chunks, opts) do
      # Your cross-encoder logic
      {:ok, scored_chunks}
    end
  end

Other highlights:

  • Hybrid search (vector + fulltext with Reciprocal Rank Fusion)
  • In-memory HNSWLib backend for testing or smaller apps
  • Built-in telemetry for all operations
  • Evaluation metrics (MRR, Recall@k, Precision@k)
  • Optional LiveView dashboard
  • File ingestion (text, markdown, PDF)

Links

GitHub: GitHub - georgeguimaraes/arcana: Embeddable RAG library for Elixir/Phoenix with agentic pipelines and dashboard · GitHub
Hex: arcana | Hex
Demo app with Doctor Who corpus: GitHub - georgeguimaraes/arcana-adept: Example Phoenix app demonstrating Arcana RAG toolkit · GitHub

Would love feedback from the community!

https://github.com/georgeguimaraes/arcana

Showing Posts 1 to 3

georgeguimaraes

georgeguimaraes OP

Dashboard example here:

SyntaxSorcerer

SyntaxSorcerer

I’m curious to how members of the community are using this. I have a small collection of PDFs I’d like to use in a RAG pipeline for some agentic workflows. Not sure what’s the best way to get started but Arcana looks like it could be useful.

georgeguimaraes

georgeguimaraes OP

Check GitHub - georgeguimaraes/arcana-adept: Example Phoenix app demonstrating Arcana RAG toolkit · GitHub

It’s not using PDF, but JSON files, but it’d give you a good overview of the whole workflow.

Also, Arcana has pdf “scraping” capabilities using https://poppler.freedesktop.org/. Not fancy, and not extremely exceptional. I want to experiment with GitHub - xberg-io/xberg: A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. Available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, TypeScript (Node/Bun/Wasm/Deno)- or use via CLI, REST API, or MCP server. · GitHub to know how we can do better.

But remember, you can define your own PDF Parser and give it to Arcana.

— All posts loaded —

Where Next? Top

Trending in Announcing Top

type1fool
WebAuthnLiveComponent WebAuthnComponents See this post about renaming the package. Passwordless authentication for Phoenix LiveView app...
New
GenericJam
Edit: 2026 May 15 - This post is archived. Mob is alive!! Main docs: mob v0.7.11 — Documentation A bit of explanation for the slightly c...
New
woylie
I released Doggo, a collection of unstyled Phoenix components. https://github.com/woylie/doggo Features Unstyled Phoenix components....
New
ahamez
Hi everyone, I’ve been working on this protobuf library for 3 years. We use it in the company I work for, EasyMile, to communicate with ...
New
garrison
Hobbes is a low-level distributed database for the Elixir programming language. Hobbes provides a simple, safe, and scalable storage lay...
New
kip
I’ll shortly be launching Text, a nascent text analysis library. Current functionality In this early version (not ready for prime time) ...
New
kip
Following on from my CLDR lbraries I started work on Unicode transforms. But like everything related to CLDR there is a lot of yak-shavin...
New

Other Trending Topics Top

mudasobwa
I am happy to introduce the very α version of the new programming language compiled to BEAM. Welcome Cure. It has literally three kille...
New
budgie
A little off-topic, but I feel like people here have a good head on their shoulders. I used to be quite good at making software. Was luc...
New
KristerV
Hey. Is there anyone here who creates agents in their apps? Not talking about using agents, but creating them. I’m finding it pretty diff...
New
webofbits
With AI doing more of the implementation work, I’ve been wondering how much coding I should deliberately keep doing myself. My main conc...
#ai
New
budgie
I love Elixir. It’s one of 2 programming languages I’ve ever fallen in love with. But I don’t use it anymore. Serverless was the promis...
New
type1fool
I just stumbled on a newly redesigned elixir-lang.org. :tada: It looks like @Software_Mansion did the work, and I think it is generally a...
New

We're in Beta

About us Mission Statement

Options

Thread Display Mode




Thread Preview

Skip Thread Previews