Project Atlas AetherDev project hub
Atlas project concept

PrivateGPTConf/env/default

Ship a known-good PrivateGPT configuration snapshot that the setup scripts can copy into a local installation. Provide default settings.yaml profiles and model/runtime configs. Support ingestion and serving workflows via included scripts and Makefile targets. Act as the baseline environment copied into a local PrivateGPT install.

Type
Component
Lifecycle
Prototyping
Last touched
2024-09-26
Visibility
Public

Purpose

Ship a known-good PrivateGPT configuration snapshot that the setup scripts can copy into a local installation.

Current state

Last touched: 2024-09-26. Functionality and completeness: Default environment mirrors upstream PrivateGPT; customization is expected.

Next step

Add baseline automated tests to cover critical flows; Add CI pipeline for build/test/lint; Document deployment/runtime environment (or add Dockerfile); Document interfaces (CLI flags, API endpoints, file formats); Add structured logging and basic health checks.

Interfaces

Inputs
  • settings.yaml profiles, local_data paths, model files
Outputs
  • vector store data, API responses, UI outputs
  • embeddings/vector store

Reality to Action trace

Reality Ingestion

Contributes in this stage.

Canonical Storage

Contributes in this stage.

Automation Engines

Contributes in this stage.

Human Interfaces

Contributes in this stage.

Operational Adoption

Contributes in this stage.

Core workflow

TBD. Document the 5-10 steps that define the core workflow.

Artifacts

  • OpenAI-compatible API schema for chat/completions

Operational notes

Constraints and scars

  • Heavy model dependencies and storage requirements; local hardware limits apply.

Reliability posture

Failure modes and safe behavior: Missing models or vector store failures prevent ingestion or query. Idempotency / retries / batching behavior: Ingestion re-runs reindex documents; no built-in retry policy.

Observability

  • Logs: FastAPI/Uvicorn logs and application output
  • Metrics/health checks: None documented

Security and privacy

settings.yaml includes placeholder secrets; replace with secure local values. Local_data and embeddings can contain sensitive content; restrict access.

Dependencies

Upstream
  • Optional model providers configured in settings

Ownership

Owners

Josh Barton

Users

Josh Barton (owner)

PrivateGPTConf/env/default

Architecture & Major Components

  • High-level diagram (text):

    • Entry/trigger -> core logic -> outputs (details per docs below)

  • Entry points: settings.yaml and scripts in env/default

  • Top-level folders: local_data, models, private_gpt, scripts, tests, settings*.yaml

  • Key abstractions: settings profiles, ingestion scripts, FastAPI server

Setup / Build / Run

  • Build system(s): Python (pyproject).
  • Uses Makefile targets for ingest/run; profiles are selected via settings.