|
1 | | -# GoRag: Go Interface for LLM / RAG development via Multiple Vector Database types 📜 |
| 1 | +# GoRag: A Go Library for Retrieval-Augmented Generation (RAG) Development with Multi-Vector Database Support 📜 |
2 | 2 |
|
3 | 3 | [](https://goreportcard.com/report/github.com/stackloklabs/gorag) |
4 | 4 | [](LICENSE) |
5 | 5 |
|
6 | | -GoRag is a Go library that provides an easy interface to interact with Large |
7 | | -Language Model backends including [Ollama](https://ollama.com) and [OpenAI](https://openai.com), along with an embeddings interface for RAG (currently with Postgres pgvector). |
| 6 | +GoRag provides an intuitive Go interface for developing Retrieval-Augmented Generation (RAG) applications. It supports multiple vector database types, enabling efficient data retrieval for enhanced generation augmentation. |
| 7 | + |
| 8 | +Language Model backends including [Ollama](https://ollama.com) and [OpenAI](https://openai.com), along with an embeddings interface for RAG using a local embeddings model (mxbai-embed-large) or a hosted such type (such as text-embedding-ada-002 from OpenAI) |
8 | 9 |
|
9 | 10 |
|
10 | 11 | ## 🌟 Features |
@@ -85,7 +86,7 @@ prompt := backend.NewPrompt(). |
85 | 86 | }) |
86 | 87 | ``` |
87 | 88 |
|
88 | | -Generate a response |
| 89 | +Call the Generations API |
89 | 90 |
|
90 | 91 | ```go |
91 | 92 | response, err := generationBackend.Generate(ctx, prompt) |
@@ -117,7 +118,7 @@ prompt := backend.NewPrompt(). |
117 | 118 | }) |
118 | 119 | ``` |
119 | 120 |
|
120 | | -Generate a response |
| 121 | +Call the Generations API and get a response |
121 | 122 |
|
122 | 123 | ```go |
123 | 124 | response, err := generationBackend.Generate(ctx, prompt) |
@@ -179,7 +180,7 @@ Example output: |
179 | 180 | 2024/10/28 15:08:26 Vector Document generated |
180 | 181 | 2024/10/28 15:08:26 Vector embeddings generated |
181 | 182 | 2024/10/28 15:08:26 Retrieved Document: {doc-5630d3f2-bf61-4e13-8ec9-9e863bc1a962 map[content:Mickey mouse is a real human being]} |
182 | | -2024/10/28 15:08:34 Retrieval-Augmented Generation influenced output from LLM model: In that case, since Mickey Mouse is a real human being (as per your context), I would say... **YES**, Mickey Mouse is indeed a human! |
| 183 | +2024/10/28 15:08:34 Retrieval-Augmented Generation influenced output from LLM model: Mickey Mouse is indeed a human! |
183 | 184 | ``` |
184 | 185 |
|
185 | 186 | # 📝 Contributing |
|
0 commit comments