Your stack retrieves by recency or similarity. EDM artifacts give it a third signal — significance encoded in the episodic record at the moment it occurred, before retrieval ever happens. Bring your stack. EDM enriches it.
Retrieval comparison
In a controlled comparison on 18 significance-typed queries, the live /v1/activate endpoint returned the correct artifact in 83.3% (15/18). Raw vector similarity returned 33.3%(6/18). Queries EDM answered exclusively had zero lexical or semantic overlap between question and answer — they required affective structure to find.
Bring your retrieval stack. EDM artifacts enrich it — whichever paradigm you use.
Other systems score relevance at retrieval time. EDM encodes significance at capture time — so every retrieval paradigm gets a richer signal to work with.
Embedding-based retrieval
Retrieve by resonance — not recency or keyword match
Temporal knowledge graph
Traverse entity relationships and temporal edges as a network of meaning
Agentic reasoning
Reason over who this person is — not just what they said
Episodic memory
Significance that strengthens, decays, or re-emerges — encoded in the episodic record, not computed at query time
The same physie reflection — processed at Essential, Extended, and Full profile. Each level unlocks additional fields your retrieval stack can act on.
Raw input
“Just got these photos and what an absolute ball I had competing in my physie comps! About 8 years ago I was diagnosed with psoriatic arthritis which affects my joints and I'm on medication I will need to take forever to keep them mobile. However, it's continuing to move that really keeps it at bay. Not only does physie do this for me, it's also so good for my mental health…”
Core · Constellation
Narrative anchors and primary emotional topology. Enough for session coherence and basic salience-weighted retrieval.
Core · Constellation · Milky_Way · Gravity
Adds full emotional topology, relational context, and salience geometry. The right entry point for longitudinal memory and companion AI.
All 10 domains
Adds complete salience geometry and motivational orientation. Required for Certified conformance and regulated contexts.
transformation · pride · enduring · continuity · approach — none of these appeared in the source text. Significance encoded at capture time.
Pass any text. Receive a structured EDM artifact — profile-matched to your use case, ready for re-ingestion into your memory stack.
curl -X POST https://api.deepadata.com/v1/extract \
-H "Authorization: Bearer dda_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"content": "Just got these photos and what an absolute ball I had competing in my physie comps...",
"profile": "essential",
"subject_id": "user-12345"
}'Returns 24 fields. Upgrade to Extended or Full by changing the profile parameter.
EDM artifacts are governed episodic memory records. They slot into your existing retrieval infrastructure — embedding-based, graph-based, or hybrid — without architectural changes.
Add emotional significance as a retrieval dimension alongside Mem0's memory graph.
Request accessEDM artifacts as LangChain memory objects — structured emotional context in any chain.
Request accessOpen source · MIT licensed · Extract, self-seal, and verify locally with ddna-tools
First 1,000 extractions free. No credit card required. Enterprise volume pricing available.