judotens commited on
Commit
e1eb9ff
·
verified ·
1 Parent(s): 72e6bec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -12
README.md CHANGED
@@ -18,9 +18,9 @@ Open-source infrastructure for building search systems, AI applications, and lan
18
 
19
  Flatseek is an open-source ecosystem for modern AI infrastructure.
20
 
21
- Instead of treating search, retrieval, model training, inference, and storage as separate problems, the ecosystem provides modular projects that work independently or together as a complete pipeline.
22
 
23
- Index your knowledge once, then reuse it across semantic search, Retrieval-Augmented Generation (RAG), model training, inference, analytics, and deployment.
24
 
25
  ```text
26
  Knowledge
@@ -71,19 +71,18 @@ Index your knowledge once, then reuse it across semantic search, Retrieval-Augme
71
  ```
72
 
73
  ---
74
-
75
- # Projects
76
 
77
  | Project | Description |
78
  |---------|-------------|
79
- | **Flatseek** | Disk-first full-text search engine for portable datasets and production-scale search. An alternative to Elasticsearch, OpenSearch, and Meilisearch. |
80
- | **Flatvec** | Disk-first vector search engine for semantic retrieval and RAG. An alternative to FAISS, Milvus, Pinecone, Qdrant, and Chroma. |
81
- | **Flatask** | Retrieval-Augmented Generation (RAG) runtime that connects Flatseek, Flatvec, and language models with minimal configuration. |
82
- | **Flattune** | Dataset generation and fine-tuning pipeline for creating instruction datasets and preparing training corpora from existing knowledge. |
83
- | **Flatbuild** | End-to-end language model training framework for building tokenizers, training transformer models from scratch, exporting checkpoints, and creating conversational AI. |
84
- | **Flatweight** | Storage-native model format and tooling for organizing, converting, and managing model weights for efficient deployment. |
85
- | **Flatrun** | Streaming inference runtime capable of executing GGUF, SafeTensors, and MLX models directly from storage without loading entire checkpoints into memory. |
86
- | **Flatlens** | Analytics and visualization interface for exploring search indexes, datasets, AI pipelines, and retrieval systems. |
87
 
88
  ---
89
 
 
18
 
19
  Flatseek is an open-source ecosystem for modern AI infrastructure.
20
 
21
+ Instead of treating search, retrieval, model training, inference, and model storage as isolated problems, the ecosystem provides modular projects that work independently or together as a complete AI pipeline.
22
 
23
+ Index your knowledge once, then reuse it across search, semantic retrieval, Retrieval-Augmented Generation (RAG), model training, inference, analytics, and deployment.
24
 
25
  ```text
26
  Knowledge
 
71
  ```
72
 
73
  ---
74
+ ## Projects
 
75
 
76
  | Project | Description |
77
  |---------|-------------|
78
+ | **[Flatseek](https://github.com/flatseek/flatseek)** | Disk-first full-text search engine for portable datasets and production-scale search. An alternative to Elasticsearch, OpenSearch, and Meilisearch. |
79
+ | **[Flatvec](https://github.com/flatseek/flatvec)** | Disk-first vector search engine for semantic retrieval and RAG. An alternative to FAISS, Milvus, Pinecone, Qdrant, and Chroma. |
80
+ | **[Flatask](https://github.com/flatseek/flatask)** | Retrieval-Augmented Generation (RAG) runtime that connects keyword search, semantic search, and language models into a unified retrieval pipeline. |
81
+ | **[Flattune](https://github.com/flatseek/flattune)** | Dataset generation and fine-tuning pipeline for creating high-quality training corpora from existing knowledge. |
82
+ | **[Flatbuild](https://github.com/flatseek/flatbuild)** | Framework for training transformer language models from scratch, including tokenizer training, chat templates, checkpoint export, and GGUF conversion. |
83
+ | **[Flatweight](https://github.com/flatseek/flatweight)** | Storage-native model format and tooling for organizing, converting, and managing model weights for efficient deployment and streaming inference. |
84
+ | **[Flatrun](https://github.com/flatseek/flatrun)** | Streaming inference runtime that executes GGUF, SafeTensors, and MLX models directly from storage with minimal memory usage. |
85
+ | **[Flatlens](https://github.com/flatseek/flatlens)** | Analytics and visualization interface for exploring search indexes, datasets, retrieval pipelines, and AI workflows. |
86
 
87
  ---
88