MossClient
Semantic search client for vector similarity operations. All mutations and reads go through the Rust ManageClient. Querying uses the local IndexManager when the index is loaded, otherwise falls back to the cloud query API.Methods
create_index(name, docs, model_id)
Create a new index and populate it with documents.
When model_id is omitted, the SDK picks "moss-minilm" when no documents
carry pre-computed embeddings and "custom" when every document provides an
embedding. Mixed documents are rejected.
Parameters
- name (
str) - docs (List[
DocumentInfo]) - model_id (
Optional[str]=None)
Returns
MutationResult
add_docs(name, docs, options)
Add or update documents in an index.
Parameters
- name (
str) - docs (List[
DocumentInfo]) - options (Optional[
MutationOptions] =None)
Returns
MutationResult
delete_docs(name, doc_ids)
Delete documents from an index by their IDs.
Parameters
- name (
str) - doc_ids (
List[str])
Returns
MutationResult
get_job_status(job_id)
Get the status of a bulk operation job.
Parameters
- job_id (
str)
Returns
JobStatusResponse
get_index(name)
Get information about a specific index.
Parameters
- name (
str)
Returns
IndexInfo
list_indexes()
List all indexes with their information.
Returns
List[IndexInfo]
delete_index(name)
Delete an index and all its data.
Parameters
- name (
str)
Returns
bool
get_docs(name, options)
Retrieve documents from an index.
Parameters
- name (
str) - options (Optional[
GetDocumentsOptions] =None)
Returns
List[DocumentInfo]
load_index(name, auto_refresh, polling_interval_in_seconds)
Downloads an index from the cloud into memory for fast local querying.
Without load_index(), query() falls back to the cloud API (~100-500ms).
With load_index(), queries run entirely in-memory (~1-10ms).
Parameters
- name (
str) - auto_refresh (
bool=False) - polling_interval_in_seconds (
int=600)
Returns
str
unload_index(name)
Unload an index from memory.
Parameters
- name (
str)
query(name, query, options)
Perform a semantic similarity search.
If the index is loaded locally (via load_index), queries run in-memory.
Otherwise, falls back to the cloud query API.
Parameters
-
name (
str) -
query (
str) -
options (Optional[
QueryOptions] =None): Query options (top_k, alpha, embedding, filter). Example filter:
Returns
SearchResult