Skip to content

Commit 4b8c584

Browse files
author
Zhe Yu
committed
docs(database): update database configuration documentation
1 parent dfecc3e commit 4b8c584

1 file changed

Lines changed: 5 additions & 23 deletions

File tree

docs/cli.md

Lines changed: 5 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -261,7 +261,11 @@ be accepted. This allows you to leave trailing comma in the config file, as well
261261
as writing comments (`//`). This can be very useful if you're experimenting with
262262
the configs.
263263

264-
The JSON configuration file may hold the following values:
264+
The JSON configuration file may hold the following values:
265+
- `db_type`: string, default: `"ChromaDB0Connector"`, the database backend to use;
266+
- `db_params`: dictionary. See
267+
[the corresponding database source code](../src/vectorcode/database/) for the
268+
default values;
265269
- `embedding_function`: string, one of the embedding functions supported by [Chromadb](https://www.trychroma.com/)
266270
(find more [here](https://docs.trychroma.com/docs/embeddings/embedding-functions) and
267271
[here](https://docs.trychroma.com/integrations/chroma-integrations)). For
@@ -282,14 +286,6 @@ The JSON configuration file may hold the following values:
282286
to. _Make sure your model supports Matryoshka Representation Learning (MRL)
283287
before using this._ Learn more about MRL [here](https://sbert.net/examples/sentence_transformer/training/matryoshka/README.html#matryoshka-embeddings).
284288
When set to `null` (or unset), the embeddings won't be truncated;
285-
- `db_url`: string, the url that points to the Chromadb server. VectorCode will start an
286-
HTTP server for Chromadb at a randomly picked free port on `localhost` if your
287-
configured `http://host:port` is not accessible. Default: `http://127.0.0.1:8000`;
288-
- `db_path`: string, Path to local persistent database. If you didn't set up a standalone
289-
Chromadb server, this is where the files for your database will be stored.
290-
Default: `~/.local/share/vectorcode/chromadb/`;
291-
- `db_log_path`: string, path to the _directory_ where the built-in chromadb
292-
server will write the log to. Default: `~/.local/share/vectorcode/`;
293289
- `chunk_size`: integer, the maximum number of characters per chunk. A larger
294290
value reduces the number of items in the database, and hence accelerates the
295291
search, but at the cost of potentially truncated data and lost information.
@@ -330,20 +326,6 @@ The JSON configuration file may hold the following values:
330326
}
331327
}
332328
```
333-
- `db_settings`: dictionary, works in a similar way to `embedding_params`, but
334-
for Chromadb client settings so that you can configure
335-
[authentication for remote Chromadb](https://docs.trychroma.com/production/administration/auth);
336-
- `hnsw`: a dictionary of
337-
[hnsw settings](https://cookbook.chromadb.dev/core/configuration/#hnsw-configuration)
338-
that may improve the query performances or avoid runtime errors during
339-
queries. **It's recommended to re-vectorise the collection after modifying these
340-
options, because some of the options can only be set during collection
341-
creation.** Example (and default):
342-
```json5
343-
"hnsw": {
344-
"hnsw:M": 64,
345-
}
346-
```
347329
- `filetype_map`: `dict[str, list[str]]`, a dictionary where keys are
348330
[language name](https://github.com/Goldziher/tree-sitter-language-pack?tab=readme-ov-file#available-languages)
349331
and values are lists of [Python regex patterns](https://docs.python.org/3/library/re.html)

0 commit comments

Comments
 (0)