search

philippgille / chromem-go

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.
Mozilla Public License 2.0
224 stars 17 forks source link
chroma chromadb cosine-similarity embedded embeddings go golang in-memory llm llms nearest-neighbor rag retrieval-augmented-generation vector-database vector-search

readme

chromem-go

Go Reference Build status Go Report Card GitHub Releases

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.

Because chromem-go is embeddable it enables you to add retrieval augmented generation (RAG) and similar embeddings-based features into your Go app without having to run a separate database. Like when using SQLite instead of PostgreSQL/MySQL/etc.

It's not a library to connect to Chroma and also not a reimplementation of it in Go. It's a database on its own.

The focus is not scale (millions of documents) or number of features, but simplicity and performance for the most common use cases. On a mid-range 2020 Intel laptop CPU you can query 1,000 documents in 0.3 ms and 100,000 documents in 40 ms, with very few and small memory allocations. See Benchmarks for details.

⚠️ The project is in beta, under heavy construction, and may introduce breaking changes in releases before v1.0.0. All changes are documented in the CHANGELOG.

Contents

  1. Use cases
  2. Interface
  3. Features + Roadmap
  4. Installation
  5. Usage
  6. Benchmarks
  7. Development
  8. Motivation
  9. Related projects

Use cases

With a vector database you can do various things:

Let's look at the RAG use case in more detail:

RAG

The knowledge of large language models (LLMs) - even the ones with 30 billion, 70 billion parameters and more - is limited. They don't know anything about what happened after their training ended, they don't know anything about data they were not trained with (like your company's intranet, Jira / bug tracker, wiki or other kinds of knowledge bases), and even the data they do know they often can't reproduce it exactly, but start to hallucinate instead.

Fine-tuning an LLM can help a bit, but it's more meant to improve the LLMs reasoning about specific topics, or reproduce the style of written text or code. Fine-tuning does not add knowledge 1:1 into the model. Details are lost or mixed up. And knowledge cutoff (about anything that happened after the fine-tuning) isn't solved either.

=> A vector database can act as the up-to-date, precise knowledge for LLMs:

  1. You store relevant documents that you want the LLM to know in the database.
  2. The database stores the embeddings alongside the documents, which you can either provide or can be created by specific "embedding models" like OpenAI's text-embedding-3-small.
    • chromem-go can do this for you and supports multiple embedding providers and models out-of-the-box.
  3. Later, when you want to talk to the LLM, you first send the question to the vector DB to find similar/related content. This is called "nearest neighbor search".
  4. In the question to the LLM, you provide this content alongside your question.
  5. The LLM can take this up-to-date precise content into account when answering.

Check out the example code to see it in action!

Interface

Our original inspiration was the Chroma interface, whose core API is the following (taken from their README):

Chroma core interface ```python import chromadb # setup Chroma in-memory, for easy prototyping. Can add persistence easily! client = chromadb.Client() # Create collection. get_collection, get_or_create_collection, delete_collection also available! collection = client.create_collection("all-my-documents") # Add docs to the collection. Can also update and delete. Row-based API coming soon! collection.add( documents=["This is document1", "This is document2"], # we handle tokenization, embedding, and indexing automatically. You can skip that and add your own embeddings as well metadatas=[{"source": "notion"}, {"source": "google-docs"}], # filter on these! ids=["doc1", "doc2"], # unique for each doc ) # Query/search 2 most similar results. You can also .get by id results = collection.query( query_texts=["This is a query document"], n_results=2, # where={"metadata_field": "is_equal_to_this"}, # optional filter # where_document={"$contains":"search_string"} # optional filter ) ```

Our Go library exposes the same interface:

chromem-go equivalent ```go package main import "github.com/philippgille/chromem-go" func main() { // Set up chromem-go in-memory, for easy prototyping. Can add persistence easily! // We call it DB instead of client because there's no client-server separation. The DB is embedded. db := chromem.NewDB() // Create collection. GetCollection, GetOrCreateCollection, DeleteCollection also available! collection, _ := db.CreateCollection("all-my-documents", nil, nil) // Add docs to the collection. Update and delete will be added in the future. // Can be multi-threaded with AddConcurrently()! // We're showing the Chroma-like method here, but more Go-idiomatic methods are also available! _ = collection.Add(ctx, []string{"doc1", "doc2"}, // unique ID for each doc nil, // We handle embedding automatically. You can skip that and add your own embeddings as well. []map[string]string{{"source": "notion"}, {"source": "google-docs"}}, // Filter on these! []string{"This is document1", "This is document2"}, ) // Query/search 2 most similar results. You can also get by ID. results, _ := collection.Query(ctx, "This is a query document", 2, map[string]string{"metadata_field": "is_equal_to_this"}, // optional filter map[string]string{"$contains": "search_string"}, // optional filter ) } ```

Initially chromem-go started with just the four core methods, but we added more over time. We intentionally don't want to cover 100% of Chroma's API surface though.
We're providing some alternative methods that are more Go-idiomatic instead.

For the full interface see the Godoc: https://pkg.go.dev/github.com/philippgille/chromem-go

Features

Roadmap

Installation

go get github.com/philippgille/chromem-go@latest

Usage

See the Godoc for a reference: https://pkg.go.dev/github.com/philippgille/chromem-go

For full, working examples, using the vector database for retrieval augmented generation (RAG) and semantic search and using either OpenAI or locally running the embeddings model and LLM (in Ollama), see the example code.

Quickstart

This is taken from the "minimal" example:

package main

import (
 "context"
 "fmt"
 "runtime"

 "github.com/philippgille/chromem-go"
)

func main() {
  ctx := context.Background()

  db := chromem.NewDB()

  c, err := db.CreateCollection("knowledge-base", nil, nil)
  if err != nil {
    panic(err)
  }

  err = c.AddDocuments(ctx, []chromem.Document{
    {
      ID:      "1",
      Content: "The sky is blue because of Rayleigh scattering.",
    },
    {
      ID:      "2",
      Content: "Leaves are green because chlorophyll absorbs red and blue light.",
    },
  }, runtime.NumCPU())
  if err != nil {
    panic(err)
  }

  res, err := c.Query(ctx, "Why is the sky blue?", 1, nil, nil)
  if err != nil {
    panic(err)
  }

  fmt.Printf("ID: %v\nSimilarity: %v\nContent: %v\n", res[0].ID, res[0].Similarity, res[0].Content)
}

Output:

ID: 1
Similarity: 0.6833369
Content: The sky is blue because of Rayleigh scattering.

Benchmarks

Benchmarked on 2024-03-17 with:

$ go test -benchmem -run=^$ -bench .
goos: linux
goarch: amd64
pkg: github.com/philippgille/chromem-go
cpu: 11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz
BenchmarkCollection_Query_NoContent_100-8          13164      90276 ns/op     5176 B/op       95 allocs/op
BenchmarkCollection_Query_NoContent_1000-8          2142     520261 ns/op    13558 B/op      141 allocs/op
BenchmarkCollection_Query_NoContent_5000-8           561    2150354 ns/op    47096 B/op      173 allocs/op
BenchmarkCollection_Query_NoContent_25000-8          120    9890177 ns/op   211783 B/op      208 allocs/op
BenchmarkCollection_Query_NoContent_100000-8          30   39574238 ns/op   810370 B/op      232 allocs/op
BenchmarkCollection_Query_100-8                    13225      91058 ns/op     5177 B/op       95 allocs/op
BenchmarkCollection_Query_1000-8                    2226     519693 ns/op    13552 B/op      140 allocs/op
BenchmarkCollection_Query_5000-8                     550    2128121 ns/op    47108 B/op      173 allocs/op
BenchmarkCollection_Query_25000-8                    100   10063260 ns/op   211705 B/op      205 allocs/op
BenchmarkCollection_Query_100000-8                    30   39404005 ns/op   810295 B/op      229 allocs/op
PASS
ok   github.com/philippgille/chromem-go 28.402s

Development

Motivation

In December 2023, when I wanted to play around with retrieval augmented generation (RAG) in a Go program, I looked for a vector database that could be embedded in the Go program, just like you would embed SQLite in order to not require any separate DB setup and maintenance. I was surprised when I didn't find any, given the abundance of embedded key-value stores in the Go ecosystem.

At the time most of the popular vector databases like Pinecone, Qdrant, Milvus, Chroma, Weaviate and others were not embeddable at all or only in Python or JavaScript/TypeScript.

Then I found @eliben's blog post and example code which showed that with very little Go code you could create a very basic PoC of a vector database.

That's when I decided to build my own vector database, embeddable in Go, inspired by the ChromaDB interface. ChromaDB stood out for being embeddable (in Python), and by showing its core API in 4 commands on their README and on the landing page of their website.

Related projects