apache / apache/geaflow

[geaflow/ai-memory] Implement schema-first property graph extraction prompt builder

Open
#838 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Java
Stars
808
Forks
188
Avg merge
3d 22h
Merged PRs (30d)
2

Description

Priority: P1
Difficulty: Intermediate

Context: Later LLM extraction needs consistent prompts, but prompt construction should be isolated from model clients. This issue provides prompt generation, not model execution.

Scope:

- Add `ExtractionPromptBuilder`.
- Generate prompt sections for schema, allowed entity types, allowed relation types, examples, and output JSON format.
- Add golden prompt tests.

Constraints:

- No remote model call.
- Prompt must include strict JSON output requirement and source span requirement.
- Prompt must not include unrelated schemas.

Acceptance Criteria:

- Prompt output is deterministic for the same schema and examples.
- Golden tests cover English, Chinese, and mixed text.
- Prompt builder rejects schema with no vertex or edge definitions.

Suggested paths:

- `geaflow-ai/src/main/java/org/apache/geaflow/ai/extract/prompt`

Contributor guide

Open the contributing guide

Research direction

Start in geaflow-ai/src/main/java/org/apache/geaflow/ai/extract/prompt and identify the prompt-builder entry point and nearby schema types. Add golden prompt tests covering English, Chinese, and mixed text, then verify deterministic output, strict JSON and source-span requirements, rejection of schemas without vertex or edge definitions, and exclusion of unrelated schemas.

Written by the indexing model from the issue text.

Assessment

Tech stack
java
Domain
ai
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Clearly specified
Newbie friendliness
78/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.