5.6 KiB
Entity Extraction
Location: packages/memory-service/src/entities/extraction.js
Triggered by: Episode creation (POST /episodes)
Model: qwen2.5:3b via Ollama (configurable via EXTRACTION_MODEL env var)
Purpose
After each episode is saved to SQLite, the extraction pipeline runs asynchronously in the background to identify named entities and the relationships between them. Results are written back to SQLite and embedded into Qdrant — the episode response is never delayed.
Trigger
createEpisode() in episodic/index.js calls extractAndStoreEntities()
immediately after the SQLite insert, without awaiting it:
extractAndStoreEntities(userMessage, aiResponse, episode.id, projectId)
.catch(err => logger.error(`Failed to extract entities for episode ${episode.id}:`, err.message));
If extraction throws, the episode is unaffected — the error is logged and swallowed.
Model Settings
| Setting | Value | Notes |
|---|---|---|
| Model | qwen2.5:3b |
Ollama, configurable via EXTRACTION_MODEL |
| Temperature | 0.1 | Low for consistent, deterministic output |
num_predict |
1500 | Higher ceiling to accommodate entity + relationship JSON |
format |
'json' |
Ollama constrained decoding — enforces valid JSON output |
| Prompt format | ChatML | <|im_start|> / <|im_end|> tokens |
Prompt Structure
The prompt is built by buildExtractionPrompt(). It includes:
- System message — declares the model's role as an entity and relationship extractor
- Instructions — entity types, field rules, relationship label format, required JSON schema
- Known entities block — last 20 entities from SQLite, by
rowid DESC, used to encourage consistent name/type pairs across conversations - Conversation — the raw user message and AI response, delimited clearly
<|im_start|>system
You are a named entity and relationship extractor. You output only valid JSON.
<|im_end|>
<|im_start|>user
Read the conversation below and extract all named entities and the relationships between them.
Entity types: person, place, project, technology, concept, organization
...
Return this exact JSON structure:
{ "entities": [...], "relationships": [...] }
Already known entities (use these exact name and type values if the same entity appears):
- "NexusAI" (project)
- "Alice" (person)
--- CONVERSATION ---
User: ...
Assistant: ...
--- END CONVERSATION ---
<|im_end|>
<|im_start|>assistant
Expected JSON Output
{
"entities": [
{ "name": "Alice", "type": "person", "notes": "Software engineer working on NexusAI." },
{ "name": "NexusAI", "type": "project", "notes": "A modular AI assistant with persistent memory." }
],
"relationships": [
{
"from": "Alice", "fromType": "person",
"to": "NexusAI", "toType": "project",
"label": "works_on",
"notes": "Alice is the primary developer."
}
]
}
Relationship labels use snake_case verbs (e.g. works_on, manages, uses,
knows, located_in, part_of, created_by).
JSON Parsing
The raw model response is matched with /\{[\s\S]*\}/ before parsing — this
tolerates any preamble or trailing prose the model emits alongside the JSON.
If the match fails or JSON.parse throws, the function logs a warning and
returns without writing anything.
Entity Processing
For each entity in parsed.entities:
- Validate
name,type(must be inENTITY_TYPES), and not inIGNORED_NAMES - Call
upsertEntity(name, type, notes):- Insert: creates new row with
mention_count = 1,source = 'extraction' - Conflict on
(name, type): incrementsmention_count, updateslast_seen_at, preserves existingnotesif new extraction returns null
- Insert: creates new row with
- Add to
entityMapkeyed by"${name}::${type}"— used for relationship resolution below - Call
linkEntityToEpisode(entity.id, episodeId)— writes toentity_episodesjoin table - Fire-and-forget: embed as
"${name} (${type}): ${notes}"→ store to Qdrantentitiescollection with{ name, type, notes, projectId }in payload
Valid entity types: person, place, project, technology, concept, organization
Stoplist (ignored names): good morning, good night, hello, goodbye, thanks, thank you
Relationship Processing
After all entities are saved, relationships are processed:
- For each entry in
parsed.relationships, look up both endpoints inentityMapusing"${from}::${fromType}"and"${to}::${toType}"as keys - If either endpoint is missing (filtered out, invalid type, or not in this extraction), the relationship is silently skipped
- Call
upsertRelationship(fromId, toId, label, notes):- Insert: creates new row with
mention_count = 1 - Conflict on
(from_id, to_id, label): incrementsmention_count, preserves existingnotesif new is null
- Insert: creates new row with
Relationships are unidirectional in storage. Bidirectionality is handled at query time by the graph traversal layer.
Project Scoping
projectId is threaded through from the episode creation call. It is stored
in the Qdrant entity payload, which enables project-scoped entity search in
orchestration. SQLite entities and relationships are global — scoping only
applies at the Qdrant retrieval layer.
Error Behaviour
All steps after the initial model call are wrapped in a single outer try/catch.
If Ollama is unreachable, returns a non-200 status, or the JSON cannot be
parsed, the function logs at warn level and returns. There is no retry logic.
Individual entity embedding failures are caught per-entity and logged at warn
level without affecting other entities in the same batch.