fishy/Dynavera
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fixed readme errors

Browse source
This commit is contained in:
Viswamedha Nalabotu 2026-03-22 12:42:33 +00:00
parent 519af38758
commit 43618ee3f4
3 changed files with 7 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -56,7 +56,7 @@ High-level architecture diagram:
Key backend runtime entry points: Key backend runtime entry points:
- `apps/onboarding/consumers.py` for orchestration loop and WebSocket flow - `apps/onboarding/consumers/` for orchestration loop and WebSocket flow
- `apps/onboarding/mcp.py` for tool routing and backend tool execution - `apps/onboarding/mcp.py` for tool routing and backend tool execution
- `apps/knowledge/tasks.py` for ingestion/chunking/embedding workflow - `apps/knowledge/tasks.py` for ingestion/chunking/embedding workflow
- `gpu_server.py` for inference and embedding endpoints - `gpu_server.py` for inference and embedding endpoints

3
docs/deployment-topologies.md
View file

@ -26,7 +26,8 @@ Purpose: production-like separation of concerns.
## Operational Notes ## Operational Notes
- Confirm inference host/port values in runtime container env - Confirm inference host/port/protocol values in runtime container env
- Set `INFERENCE_USERNAME` and `INFERENCE_PASSWORD` — the GPU node requires HTTP Basic Auth on all endpoints
- Confirm pgvector extension is enabled in target database - Confirm pgvector extension is enabled in target database
- Keep role flow generation permissions constrained to trusted user types - Keep role flow generation permissions constrained to trusted user types

7
docs/distributed-runtime-flow.md
View file

@ -9,8 +9,9 @@ This is the tool-facing layer that lets the model request structured actions suc
Typical tool intents: Typical tool intents:
- `search_knowledge(query, role_uuid)` - `search_knowledge(query, role_uuid)`
- `get_user_progress(user/session context)` - `update_progress(session context)`
- `update_session_state(session_uuid, patch)` - `get_role_context(role_uuid)`
- `list_training_files(role_uuid)`
Conceptually, this layer translates model tool calls into standard Django queries and vector lookups. Conceptually, this layer translates model tool calls into standard Django queries and vector lookups.
@ -44,7 +45,7 @@ Using OpenAI-style request/response patterns keeps integration predictable.
| Component | Typical Path / Endpoint | Role | | Component | Typical Path / Endpoint | Role |
| :--- | :--- | :--- | | :--- | :--- | :--- |
| MCP Surface | Internal Django tool handlers (and/or MCP endpoint) | Data/tool translation | | MCP Surface | Internal Django tool handlers (and/or MCP endpoint) | Data/tool translation |
| Orchestrator | `apps.onboarding.consumers` | Coordination + streaming | | Orchestrator | `apps/onboarding/consumers/` | Coordination + streaming |
| GPU Inference | `gpu_server.py` HTTP endpoints | Generation + embeddings | | GPU Inference | `gpu_server.py` HTTP endpoints | Generation + embeddings |
## Navigation ## Navigation