Update README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ datasets:
|
|
14 |
This is a [txtai](https://github.com/neuml/txtai) embeddings index (5GB embeddings + 25GB documents) for the [english edition of Wikipedia](https://en.wikipedia.org/).
|
15 |
|
16 |
Embeddings is the engine that delivers semantic search. Data is transformed into embeddings vectors where similar concepts will produce similar vectors.
|
17 |
-
An embeddings index generated by txtai is a fully encapsulated index format. It
|
18 |
|
19 |
This index is built from the [Wikipedia october 2024 dataset](https://huggingface.co/datasets/burgerbee/wikipedia-en-20241020).
|
20 |
The Wikipedia index works well as a fact-based context source for retrieval augmented generation (RAG). It also uses [Wikipedia Page Views](https://dumps.wikimedia.org/other/pageviews/readme.html) data to add a `percentile` field. The `percentile` field can be used
|
|
|
14 |
This is a [txtai](https://github.com/neuml/txtai) embeddings index (5GB embeddings + 25GB documents) for the [english edition of Wikipedia](https://en.wikipedia.org/).
|
15 |
|
16 |
Embeddings is the engine that delivers semantic search. Data is transformed into embeddings vectors where similar concepts will produce similar vectors.
|
17 |
+
An embeddings index generated by txtai is a fully encapsulated index format. It doesn't require a database server.
|
18 |
|
19 |
This index is built from the [Wikipedia october 2024 dataset](https://huggingface.co/datasets/burgerbee/wikipedia-en-20241020).
|
20 |
The Wikipedia index works well as a fact-based context source for retrieval augmented generation (RAG). It also uses [Wikipedia Page Views](https://dumps.wikimedia.org/other/pageviews/readme.html) data to add a `percentile` field. The `percentile` field can be used
|