# lucasyzc/graphragx architecture

> Architecture diagram of the GitHub repository lucasyzc/graphragx, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-04-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/lucasyzc/graphragx
- Repository: https://github.com/lucasyzc/graphragx

## Overview

1. **Overall shape**
   - GraphRAGX is a FastAPI-based backend with a thin server-rendered web console on top.
   - The architecture is centered on three durable stores: PostgreSQL for system state, Neo4j for symbol graph relationships, and Qdrant for vector retrieval.
   - Repository ingestion, knowledge ingestion, query answering, and impact analysis are separate flows that converge in the service layer.

2. **Presentation boundary**
   - The UI lives under `app/web` as Jinja templates plus static JavaScript/CSS.
   - Pages like Chat Home, Search, Project Management, Sync Management, Knowledge Management, and Impact Scenario call the API rather than owning business logic.
   - This keeps the browser layer as a control surface for project creation, sync triggering, search, and answer review.

3. **API layer**
   - `app/api/routes` splits the API by concern: projects, sync/jobs, query/chat, knowledge, symbols, analysis, web, and health.
   - `app/api/router.py` and `app/api/deps.py` act as the composition point and dependency boundary.
   - The API also carries a simple actor context through headers such as `X-User` and `X-Role`, which is the current RBAC scaffold.

4. **Domain and persistence model**
   - PostgreSQL is the system of record for projects, sync jobs, chat sessions/messages, knowledge sources, memories, and related metadata.
   - SQLAlchemy models live in `app/db/models.py`, with sessions and base wiring in `app/db/session.py` and `app/db/base.py`.
   - Alembic migrations define the schema evolution; the current revisions show the initial baseline and later additions for project instructions and memories.

5. **Sync and indexing pipeline**
   - The repository sync flow is the main ingestion path for codebases.
   - `app/services/scm_service.py` handles local or Git-backed source access, including checkout into a workspace for remote repositories.
   - `app/services/sync_service.py` orchestrates full and incremental sync, with incremental mode driven by `base_sha`, `head_sha`, and `since_sha`, falling back to full indexing when those are unavailable.
   - Sync execution is tracked as jobs, and duplicate queued/running syncs are rejected.

6. **Canonical intermediate representation**
   - Parsed code is normalized into a language-neutral IR under `app/ir`.
   - Extractors exist for Python, Java, and C# under `app/ir/extractors`, with Python using AST-based extraction and Java/C# using lighter structural matching.
   - This IR is the bridge between raw source files and downstream graph/vector persistence.

7. **Graph layer**
   - Neo4j stores symbol nodes and relations such as `CONTAINS`, `CALLS`, `IMPORTS`, and `REFERENCES`.
   - `app/graph/repository.py` is the graph persistence boundary, used primarily by sync and analysis services.
   - The graph is not just a mirror of code; it powers traversal-based features like impact analysis and symbol-centric lookup.

8. **Vector layer**
   - Qdrant stores embedded chunks for semantic retrieval.
   - `app/vector/repository.py` and `app/vector/types.py` define the vector-store boundary.
   - Symbol snippets and knowledge document chunks are embedded and upserted here, making vector search a shared retrieval substrate for both code and docs.

9. **Embedding and chat gateways**
   - `app/services/embedding_service.py` supports `local_hash` for deterministic/local behavior and `openai_compatible` for external embedding APIs.
   - `app/services/chat_service.py` similarly abstracts grounded answer generation with `none` and `openai_compatible` modes.
   - This design isolates model/provider choice from the rest of the system, so retrieval and orchestration stay stable even when the LLM backend changes.

10. **Query, retrieval, and chat flow**
   - `app/services/retrieval_service.py` and `app/services/chunking_service.py` unify search across vector chunks and metadata-backed sources.
   - `POST /query` is the primary retrieval endpoint and can return contextual snippets plus retrieval metadata.
   - Chat sessions are persisted separately from queries, so the system supports conversational state while still grounding each answer in retrieved evidence.

11. **Knowledge ingestion as a second content source**
   - Knowledge sources are treated as first-class inputs, separate from source-code repositories.
   - They support local directory and HTTP ingestion, then split supported documents into `document_chunks` with ACL scoping.
   - This makes the architecture a two-lane RAG system: code repositories on one side, external/internal documentation on the other, both feeding the same retrieval stack.

12. **Impact analysis**
   - `app/services/impact_service.py` uses the symbol graph to expand from a starting symbol or scope through graph hops.
   - The dedicated `/analysis/impact` route and scenario page use Neo4j relations to answer “what breaks if this changes?” style questions.
   - This is one of the clearest examples of why the graph store exists separately from the vector store.

13. **Operational control plane**
   - `app/services/job_service.py` tracks async work and stale-job recovery.
   - `app/services/runtime_check.py` enforces startup requirements: PostgreSQL, Neo4j, and Qdrant must be reachable when required, and SQLite is blocked outside test usage.
   - `app/services/audit_service.py` and `app/services/project_service.py` suggest a central governance layer around project-level actions.

14. **Execution environment and test posture**
   - Docker Compose packages the API with PostgreSQL, Neo4j, and Qdrant for local deployment.
   - Tests cover sync, indexing, retrieval, chat, knowledge, web routes, SCM behavior, and incremental behavior, indicating that the main architectural seams are already enforced by automated tests.
   - The repo is therefore structured as an integration-heavy application where the service layer is the real center of gravity.

Main entry points: [`app/api/router.py`](https://github.com/lucasyzc/graphragx/blob/main/app/api/router.py) (API router), [`app/services/indexing_service.py`](https://github.com/lucasyzc/graphragx/blob/main/app/services/indexing_service.py) (Indexing service), [`app/db/models.py`](https://github.com/lucasyzc/graphragx/blob/main/app/db/models.py) (DB models), [`app/services/retrieval_service.py`](https://github.com/lucasyzc/graphragx/blob/main/app/services/retrieval_service.py) (Retrieval service)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_presentation["Presentation"]
end

subgraph group_api["API Layer"]
  node_app_main["App entry<br/>FastAPI bootstrap<br/>[main.py]"]
  node_api_router["API router<br/>route composition<br/>[router.py]"]
  node_api_deps["API deps<br/>request context<br/>[deps.py]"]
  node_web_routes["Web routes<br/>page routes<br/>[web.py]"]
  node_project_routes["Projects API<br/>project endpoints<br/>[projects.py]"]
  node_sync_jobs_routes["Sync API<br/>job endpoints<br/>[jobs.py]"]
  node_query_routes["Query API<br/>retrieval endpoints<br/>[query.py]"]
  node_chat_routes["Chat API<br/>conversation endpoints<br/>[chat.py]"]
  node_knowledge_routes["Knowledge API<br/>doc endpoints<br/>[knowledge.py]"]
  node_symbol_routes["Symbols API<br/>symbol endpoints<br/>[symbols.py]"]
  node_analysis_routes["Analysis API<br/>impact endpoints<br/>[analysis.py]"]
end

subgraph group_services["Services"]
  node_project_service["Project service<br/>project orchestration<br/>[project_service.py]"]
  node_sync_service["Sync service<br/>ingestion orchestrator<br/>[sync_service.py]"]
  node_scm_service["SCM service<br/>source access<br/>[scm_service.py]"]
  node_indexing_service["Indexing service<br/>pipeline stage"]
  node_retrieval_service["Retrieval service<br/>search orchestration"]
  node_chat_service["Chat service<br/>answer generation<br/>[chat_service.py]"]
  node_knowledge_service["Knowledge service<br/>doc ingestion"]
  node_impact_service["Impact service<br/>graph analysis<br/>[impact_service.py]"]
  node_job_service["Job service<br/>async control<br/>[job_service.py]"]
  node_embedding_service["Embedding service<br/>vector adapter"]
  node_runtime_check["Runtime check<br/>startup guard<br/>[runtime_check.py]"]
end

subgraph group_persistence["Persistence"]
  node_db_models[("DB models<br/>sqlalchemy models<br/>[models.py]")]
  node_db_session["DB session<br/>session wiring<br/>[session.py]"]
  node_graph_repo["Graph repo<br/>neo4j boundary<br/>[repository.py]"]
  node_vector_repo["Vector repo<br/>qdrant boundary<br/>[repository.py]"]
end

subgraph group_domain["Domain Model"]
  node_ir_models["IR models<br/>normalized ir<br/>[models.py]"]
  node_python_extractor["Python extractor<br/>ast extractor"]
  node_java_extractor["Java extractor<br/>structural extractor<br/>[java_extractor.py]"]
  node_csharp_extractor["C# extractor<br/>structural extractor"]
  node_schemas["Schemas<br/>api contracts"]
end

node_app_main -->|"mounts"| node_api_router
node_app_main -->|"checks"| node_runtime_check
node_api_router -->|"uses"| node_api_deps
node_api_router -->|"includes"| node_project_routes
node_api_router -->|"includes"| node_sync_jobs_routes
node_api_router -->|"includes"| node_query_routes
node_api_router -->|"includes"| node_chat_routes
node_api_router -->|"includes"| node_knowledge_routes
node_api_router -->|"includes"| node_symbol_routes
node_api_router -->|"includes"| node_analysis_routes
node_api_router -->|"includes"| node_web_routes
node_api_router -->|"contracts"| node_schemas
node_web_routes -->|"calls"| node_project_service
node_web_routes -->|"calls"| node_sync_service
node_web_routes -->|"calls"| node_retrieval_service
node_project_routes -->|"calls"| node_project_service
node_sync_jobs_routes -->|"calls"| node_sync_service
node_sync_jobs_routes -->|"calls"| node_job_service
node_query_routes -->|"calls"| node_retrieval_service
node_chat_routes -->|"calls"| node_chat_service
node_chat_routes -->|"calls"| node_retrieval_service
node_knowledge_routes -->|"calls"| node_knowledge_service
node_symbol_routes -->|"calls"| node_graph_repo
node_analysis_routes -->|"calls"| node_impact_service
node_project_service -->|"persists"| node_db_models
node_job_service -->|"persists"| node_db_models
node_chat_service -->|"persists"| node_db_models
node_knowledge_service -->|"persists"| node_db_models
node_retrieval_service -->|"queries"| node_vector_repo
node_retrieval_service -->|"reads"| node_db_models
node_chat_service -->|"uses"| node_embedding_service
node_knowledge_service -->|"uses"| node_embedding_service
node_sync_service -->|"uses"| node_scm_service
node_sync_service -->|"orchestrates"| node_indexing_service
node_indexing_service -->|"produces"| node_ir_models
node_indexing_service -->|"uses"| node_python_extractor
node_indexing_service -->|"uses"| node_java_extractor
node_indexing_service -->|"uses"| node_csharp_extractor
node_indexing_service -->|"writes"| node_graph_repo
node_indexing_service -->|"writes"| node_vector_repo
node_indexing_service -->|"uses"| node_embedding_service
node_impact_service -->|"traverses"| node_graph_repo
node_knowledge_service -->|"writes"| node_vector_repo
node_runtime_check -->|"verifies"| node_db_session
node_db_session -->|"supports"| node_db_models

click node_app_main "https://github.com/lucasyzc/graphragx/blob/main/app/main.py"
click node_api_router "https://github.com/lucasyzc/graphragx/blob/main/app/api/router.py"
click node_api_deps "https://github.com/lucasyzc/graphragx/blob/main/app/api/deps.py"
click node_web_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/web.py"
click node_project_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/projects.py"
click node_sync_jobs_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/jobs.py"
click node_query_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/query.py"
click node_chat_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/chat.py"
click node_knowledge_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/knowledge.py"
click node_symbol_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/symbols.py"
click node_analysis_routes "https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/analysis.py"
click node_project_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/project_service.py"
click node_sync_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/sync_service.py"
click node_scm_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/scm_service.py"
click node_indexing_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/indexing_service.py"
click node_retrieval_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/retrieval_service.py"
click node_chat_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/chat_service.py"
click node_knowledge_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/knowledge_service.py"
click node_impact_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/impact_service.py"
click node_job_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/job_service.py"
click node_embedding_service "https://github.com/lucasyzc/graphragx/blob/main/app/services/embedding_service.py"
click node_runtime_check "https://github.com/lucasyzc/graphragx/blob/main/app/services/runtime_check.py"
click node_db_models "https://github.com/lucasyzc/graphragx/blob/main/app/db/models.py"
click node_db_session "https://github.com/lucasyzc/graphragx/blob/main/app/db/session.py"
click node_graph_repo "https://github.com/lucasyzc/graphragx/blob/main/app/graph/repository.py"
click node_vector_repo "https://github.com/lucasyzc/graphragx/blob/main/app/vector/repository.py"
click node_ir_models "https://github.com/lucasyzc/graphragx/blob/main/app/ir/models.py"
click node_python_extractor "https://github.com/lucasyzc/graphragx/blob/main/app/ir/extractors/python_extractor.py"
click node_java_extractor "https://github.com/lucasyzc/graphragx/blob/main/app/ir/extractors/java_extractor.py"
click node_csharp_extractor "https://github.com/lucasyzc/graphragx/blob/main/app/ir/extractors/csharp_extractor.py"
click node_schemas "https://github.com/lucasyzc/graphragx/tree/main/app/schemas"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_app_main,node_api_router,node_api_deps,node_web_routes,node_project_routes,node_sync_jobs_routes,node_query_routes,node_chat_routes,node_knowledge_routes,node_symbol_routes,node_analysis_routes toneAmber
class node_project_service,node_sync_service,node_scm_service,node_indexing_service,node_retrieval_service,node_chat_service,node_knowledge_service,node_impact_service,node_job_service,node_embedding_service,node_runtime_check toneMint
class node_db_models,node_db_session,node_graph_repo,node_vector_repo toneRose
class node_ir_models,node_python_extractor,node_java_extractor,node_csharp_extractor,node_schemas toneIndigo
```

## Components

### API Layer

FastAPI routing, dependency wiring, and request boundaries.

- [App entry](https://github.com/lucasyzc/graphragx/blob/main/app/main.py): FastAPI bootstrap · Application startup and server wiring. · `app/main.py`
- [API router](https://github.com/lucasyzc/graphragx/blob/main/app/api/router.py): route composition · Central API assembly and dependency boundary. · `app/api/router.py`
- [API deps](https://github.com/lucasyzc/graphragx/blob/main/app/api/deps.py): request context · Shared dependencies and actor context plumbing. · `app/api/deps.py`
- [Web routes](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/web.py): page routes · Thin server-rendered pages for console actions. · `app/api/routes/web.py`
- [Projects API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/projects.py): project endpoints · Project lifecycle and governance endpoints. · `app/api/routes/projects.py`
- [Sync API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/jobs.py): job endpoints · Sync triggering, job control, and related operations. · `app/api/routes/jobs.py`
- [Query API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/query.py): retrieval endpoints · Primary retrieval and answer request endpoints. · `app/api/routes/query.py`
- [Chat API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/chat.py): conversation endpoints · Chat session and answer interaction endpoints. · `app/api/routes/chat.py`
- [Knowledge API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/knowledge.py): doc endpoints · Knowledge source ingestion and management endpoints. · `app/api/routes/knowledge.py`
- [Symbols API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/symbols.py): symbol endpoints · Symbol lookup and graph-oriented access endpoints. · `app/api/routes/symbols.py`
- [Analysis API](https://github.com/lucasyzc/graphragx/blob/main/app/api/routes/analysis.py): impact endpoints · Impact analysis and graph expansion endpoints. · `app/api/routes/analysis.py`

### Services

Orchestration, ingestion, retrieval, and analysis workflows.

- [Project service](https://github.com/lucasyzc/graphragx/blob/main/app/services/project_service.py): project orchestration · Project state, setup, and governance logic. · `app/services/project_service.py`
- [Sync service](https://github.com/lucasyzc/graphragx/blob/main/app/services/sync_service.py): ingestion orchestrator · Full and incremental repository sync coordination. · `app/services/sync_service.py`
- [SCM service](https://github.com/lucasyzc/graphragx/blob/main/app/services/scm_service.py): source access · Local or Git-backed source checkout and file access. · `app/services/scm_service.py`
- [Indexing service](https://github.com/lucasyzc/graphragx/blob/main/app/services/indexing_service.py): pipeline stage · Transforms source into graph and vector-ready artifacts. · `app/services/indexing_service.py`
- [Retrieval service](https://github.com/lucasyzc/graphragx/blob/main/app/services/retrieval_service.py): search orchestration · Unifies vector and metadata-backed retrieval. · `app/services/retrieval_service.py`
- [Chat service](https://github.com/lucasyzc/graphragx/blob/main/app/services/chat_service.py): answer generation · Grounded answer generation with provider abstraction. · `app/services/chat_service.py`
- [Knowledge service](https://github.com/lucasyzc/graphragx/blob/main/app/services/knowledge_service.py): doc ingestion · Knowledge source ingestion and chunk preparation. · `app/services/knowledge_service.py`
- [Impact service](https://github.com/lucasyzc/graphragx/blob/main/app/services/impact_service.py): graph analysis · Graph traversal for change impact analysis. · `app/services/impact_service.py`
- [Job service](https://github.com/lucasyzc/graphragx/blob/main/app/services/job_service.py): async control · Job tracking, duplicate suppression, and recovery. · `app/services/job_service.py`
- [Embedding service](https://github.com/lucasyzc/graphragx/blob/main/app/services/embedding_service.py): vector adapter · Embedding provider abstraction for local and external modes. · `app/services/embedding_service.py`
- [Runtime check](https://github.com/lucasyzc/graphragx/blob/main/app/services/runtime_check.py): startup guard · Enforces required backing-store availability. · `app/services/runtime_check.py`

### Persistence

Database and external store boundaries.

- [DB models](https://github.com/lucasyzc/graphragx/blob/main/app/db/models.py): sqlalchemy models · System-of-record schema for projects, jobs, chat, and knowledge. · `app/db/models.py`
- [DB session](https://github.com/lucasyzc/graphragx/blob/main/app/db/session.py): session wiring · Database session and engine configuration. · `app/db/session.py`
- [Graph repo](https://github.com/lucasyzc/graphragx/blob/main/app/graph/repository.py): neo4j boundary · Persistence boundary for symbol nodes and relations. · `app/graph/repository.py`
- [Vector repo](https://github.com/lucasyzc/graphragx/blob/main/app/vector/repository.py): qdrant boundary · Persistence boundary for embedded chunks and semantic search. · `app/vector/repository.py`

### Domain Model

Schemas and normalized intermediate representation.

- [IR models](https://github.com/lucasyzc/graphragx/blob/main/app/ir/models.py): normalized ir · Language-neutral intermediate representation for code. · `app/ir/models.py`
- [Python extractor](https://github.com/lucasyzc/graphragx/blob/main/app/ir/extractors/python_extractor.py): ast extractor · Python source extraction into the shared IR. · `app/ir/extractors/python_extractor.py`
- [Java extractor](https://github.com/lucasyzc/graphragx/blob/main/app/ir/extractors/java_extractor.py): structural extractor · Java source extraction into the shared IR. · `app/ir/extractors/java_extractor.py`
- [C# extractor](https://github.com/lucasyzc/graphragx/blob/main/app/ir/extractors/csharp_extractor.py): structural extractor · C# source extraction into the shared IR. · `app/ir/extractors/csharp_extractor.py`
- [Schemas](https://github.com/lucasyzc/graphragx/tree/main/app/schemas): api contracts · Request and response models for API boundaries. · `app/schemas`

## Connections

- App entry → API router: mounts · Application startup composes the API surface.
- App entry → Runtime check: checks · Startup validates required infrastructure.
- API router → API deps: uses · Routes rely on shared dependency wiring.
- API router → Projects API: includes · Projects concern is routed into the API.
- API router → Sync API: includes · Sync and job control routes are registered.
- API router → Query API: includes · Retrieval endpoints are registered.
- API router → Chat API: includes · Conversation endpoints are registered.
- API router → Knowledge API: includes · Knowledge management endpoints are registered.
- API router → Symbols API: includes · Symbol access endpoints are registered.
- API router → Analysis API: includes · Impact analysis endpoints are registered.
- API router → Web routes: includes · Server-rendered console routes are registered.
- API router → Schemas: contracts · API endpoints use shared request and response models.
- Web routes → Project service: calls · UI actions delegate to project operations.
- Web routes → Sync service: calls · UI actions trigger sync workflows.
- Web routes → Retrieval service: calls · Search and review pages use retrieval.
- Projects API → Project service: calls · Project endpoints are backed by project orchestration.
- Sync API → Sync service: calls · Sync endpoints start ingestion flows.
- Sync API → Job service: calls · Job lifecycle and duplicate control are centralized.
- Query API → Retrieval service: calls · Primary retrieval endpoint is serviced here.
- Chat API → Chat service: calls · Conversation handling delegates to answer generation.
- Chat API → Retrieval service: calls · Chat is grounded through shared retrieval.
- Knowledge API → Knowledge service: calls · Knowledge ingestion and management flow through this service.
- Symbols API → Graph repo: calls · Symbol lookup is backed by graph persistence.
- Analysis API → Impact service: calls · Impact analysis requests use graph traversal logic.
- Project service → DB models: persists · Projects and governance state live in PostgreSQL.
- Job service → DB models: persists · Job state and recovery metadata are stored in PostgreSQL.
- Chat service → DB models: persists · Chat sessions and messages are stored in PostgreSQL.
- Knowledge service → DB models: persists · Knowledge sources and metadata are stored in PostgreSQL.
- Retrieval service → Vector repo: queries · Semantic retrieval uses the vector store.
- Retrieval service → DB models: reads · Metadata-backed search also uses relational state.
- Chat service → Embedding service: uses · Answers rely on embeddings and provider abstraction.
- Knowledge service → Embedding service: uses · Document chunks are embedded before upsert.
- Sync service → SCM service: uses · Sync reads code through source checkout and file access.
- Sync service → Indexing service: orchestrates · Sync delegates parsing and indexing stages.
- Indexing service → IR models: produces · Source is normalized into the shared IR.
- Indexing service → Python extractor: uses · Python code is extracted via AST-based parsing.
- Indexing service → Java extractor: uses · Java code is extracted via structural matching.
- Indexing service → C# extractor: uses · C# code is extracted via structural matching.
- Indexing service → Graph repo: writes · Symbol relations are persisted to Neo4j.
- Indexing service → Vector repo: writes · Chunks and snippets are upserted to Qdrant.
- Indexing service → Embedding service: uses · Vector preparation depends on embeddings.
- Impact service → Graph repo: traverses · Impact analysis expands over graph relationships.
- Knowledge service → Vector repo: writes · Knowledge chunks are indexed into the shared vector layer.
- Runtime check → DB session: verifies · Startup checks backing-store connectivity.
- DB session → DB models: supports · Session wiring serves the relational model.
