embeddings
diapason.connectors.embeddings
¶
Dense embedding clients for the IngestionPipeline.
A thin HTTP wrapper around a local Ollama <https://ollama.com>_ daemon
running an embedding model (default nomic-embed-text, 768-dim). Embeddings
are serialised as float32 bytes for storage in the embedding BLOB
column of knowledge_chunks.
The client degrades gracefully when the daemon is unreachable: embed
returns None and is_available() reports False instead of raising,
so ingestion never fails because a sidecar service is down.
OllamaEmbedder
¶
Embed text via a local Ollama daemon.
Parameters¶
model:
Ollama model tag (e.g. nomic-embed-text, mxbai-embed-large).
host:
Base URL for the Ollama HTTP API. Defaults to http://localhost:11434.
timeout:
Per-request timeout in seconds.
dim
property
¶
Embedding dimensionality, learned after the first successful call.
model_version
property
¶
Stable identifier persisted alongside each embedding row.
embed(text)
¶
Embed a single string. Returns float32 bytes or None on failure.
embed_batch(texts)
¶
Embed a list of strings sequentially.
Ollama's HTTP API serves one prompt per call; on the same host the round-trip overhead is negligible relative to model inference.
is_available()
¶
Return True iff the daemon answers and the model is installed.
decode_embedding(blob, *, dtype=None)
¶
Reconstruct a 1-D vector from a BLOB written by OllamaEmbedder.embed.
Returns None when the input is missing or zero-length so callers can
treat absent embeddings uniformly. dtype defaults to np.float32
(resolved lazily; passing np.float32 as a default arg would import
numpy at module load).