Setup
Run a Chroma server (it listens on port 8000 by default) and store the collection in the shape the mount reads: one path tree document plus chunk documents that name their file.1. Add the path tree document
1. Add the path tree document
Store one document with the ID
__path_tree__. Its content is a JSON
object, plain or gzip-compressed and base64-encoded, whose keys are file
paths below the mount:- Forward slashes make folders.
- No empty path, and no
.,..or empty segment. - Every path stays unique after leading and trailing slashes are trimmed.
- A path is never both a file and a folder prefix:
guidesandguides/quickstart.mdcannot both be files. size,created_atandupdated_atare optional and used when present.
2. Tag every chunk
2. Tag every chunk
Each chunk document names its file and its place in that file:The keys default to
page_slug and chunk_index. A collection with other
names sets slug_field and chunk_index_field in the config.3. Check the collection
3. Check the collection
Confirm the tree document and at least one chunk for a path:
Connect
- YAML
- Python
- TypeScript
workspace.yaml
Layout
- Paths come from the
__path_tree__document;ssl: truereaches the server over HTTPS. - A file is its chunks sorted by chunk index and joined by line breaks, so no
grepmatch spans two chunks. - The
searchCLI ranks chunks by meaning with Chroma’s vector query.
Sample runs
grep -r reads only the files Chroma finds the text
in; Chroma matches case, so grep -ri reads every file.
SDK guides
Python
Every config field, the VFS.md and write support.
TypeScript
Every config field, the VFS.md and write support.