Documentation Index
Fetch the complete documentation index at: https://docs.memwal.ai/llms.txt
Use this file to discover all available pages before exploring further.
Unlike the TypeScript SDK there is no separate
MemWalManual class in Python. The Python SDK is relayer-backed: the relayer always handles embedding, SEAL encryption, and Walrus storage. The “manual” methods are lower-level entry points on the same MemWal / MemWalSync client for callers that already have a vector or a pre-uploaded blob.remember / recall.
embed
Compute the embedding vector for text without storing anything.
remember_manual
Register a pre-uploaded Walrus blob with a pre-computed vector. The relayer stores the {blob_id, vector, owner, namespace} mapping; it does not upload for you here.
recall_manual
Search with a pre-computed query vector. Returns {blob_id, distance} hits only — no decrypted text (you fetch/decrypt the blobs yourself).
When to use which
| You have… | Use |
|---|---|
| Plain text, want it stored | remember / remember_and_wait |
| Plain text, want only the vector | embed |
| A vector + an already-uploaded blob | remember_manual |
| A query vector, want raw hits | recall_manual |
| Plain query text, want decrypted matches | recall |
MemWal (async) and MemWalSync (sync) with identical signatures.