Packages

beam_weaver

0.1.13
0.1.13 0.1.12 0.1.11 0.1.10 0.1.9 0.1.8 0.1.7 0.1.6 0.1.5 0.1.4 0.1.3 0.1.2 0.1.1 0.1.0

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custom clients/adapters, minimal deps, and WeaveScope tracing.

Current section

Files

Jump to
Readme
14 Versions
7 Dependencies
Dependants
Files
Activity
beam_weaver examples retrieval_indexing_agent.exs
Raw

examples/retrieval_indexing_agent.exs 

alias BeamWeaver.Core.Document

alias BeamWeaver.Core.Message

alias BeamWeaver.DocumentIndex

alias BeamWeaver.DocumentLoader

alias BeamWeaver.DocumentTransformer

alias BeamWeaver.Models.FakeEmbeddingModel

alias BeamWeaver.Retriever

alias BeamWeaver.VectorStore

alias BeamWeaver.VectorStore.ETS, as: VectorETS



store = VectorETS.new(embedding: %FakeEmbeddingModel{})



index =

  DocumentIndex.new(

    loader: DocumentLoader.text("BeamWeaver uses explicit retrievers.", metadata: %{source: "guide"}),

    transformers: [DocumentTransformer.metadata_map(&Map.put(&1, :tenant, "demo"))],

    vector_store: store

  )



{:ok, %{added: 1}} = DocumentIndex.run(index)

retriever = VectorStore.as_retriever(store, k: 1)

{:ok, [%Document{} = doc]} = Retriever.retrieve(retriever, "retrievers")



IO.puts(Message.text(Message.assistant(doc.content)))