Files
chat_backend/pyproject.toml
T
westfarn 093e5462a5
Deploy Beta / unit-tests (push) Successful in 11s
Unit Tests / test (push) Successful in 11s
Deploy Beta / docker (push) Successful in 30s
Deploy Beta / deploy-beta (push) Successful in 7m19s
Eval harness (#62 P4), status frames, and agentic runs (#63) (#71)
## Summary
- Closes Phase 4 of [#62](#62): `evals/suite.json` (≥40 graded questions), `run_evals` management command, and manually-triggered `.gitea/workflows/run-evals.yml`.
- Emits versioned WS `status` frames during grounded chat (evaluating / searching / reading_sources / refining / writing) for [chat_web_app#96](ai_ml_operations/chat_web_app#96).
- Implements [#63](#63): Redis/Celery optional infra, `AgentRun`/`AgentStep`, tool registry (SSRF-safe `fetch_url`, tenant-scoped docs), LangGraph orchestrator, progress frames, REST `GET/POST /api/agent_runs/…`, gated by `ALLOW_AGENTIC_TASKS` (default off).

## Test plan
- [x] `SKIP_RAG_INIT=1 uv run python manage.py test` for evals, ws frames, agent tools, consumers, grounding
- [ ] Manual: with `ALLOW_AGENTIC_TASKS=false`, chat identical to today
- [ ] Manual: status frames visible in FE with #96 branch
- [ ] Manual (GPU): `python manage.py run_evals --runs 3`
- [ ] Manual: `ALLOW_AGENTIC_TASKS=true` multi-step research prompt creates AgentRun + framesReviewed-on: #71
2026-08-04 04:08:50 -07:00

67 lines
1.9 KiB
TOML

[project]
name = "chat-backend"
version = "0.1.0"
description = "Django chat backend for AIML Operations"
readme = "README.md"
requires-python = ">=3.12"
dependencies = [
"Django==6.0",
"channels==4.3.2",
"daphne==4.2.1",
"uvicorn==0.38.0",
"gunicorn==23.0.0",
"psycopg2-binary==2.9.10",
"whitenoise==6.9.0",
"djangorestframework==3.16.1",
"djangorestframework-simplejwt==5.5.1",
"django-cors-headers==4.9.0",
"django-autoslug==1.9.9",
"django-filter==25.2",
"ollama==0.6.1",
"langchain==1.3.14",
"langchain-core==1.5.1",
"langchain-community==0.4.2",
"langchain-classic==1.0.8",
"langchain-ollama==1.1.0",
"langchain-chroma==1.1.0",
"langchain-text-splitters==1.1.2",
# langgraph stack is no longer force-pinned. langchain / langgraph
# require langchain-core>=1.4.7 (Reviver allowed_objects). Let
# langgraph resolve checkpoint / prebuilt / sdk transitively.
# Supported: langgraph>=1.2.5,<1.3 (matches langchain 1.3.x).
"langgraph>=1.2.5,<1.3.0",
"chromadb==1.3.5",
# Fallback loader uses UnstructuredFileLoader; xlsx partition needs the
# [xlsx] extra (networkx, msoffcrypto-tool, xlrd, openpyxl, pandas).
"unstructured[xlsx]==0.18.21",
"pypdf==6.4.0",
"python-docx==1.2.0",
"docx2txt==0.8",
"openpyxl==3.1.5",
"pandas==2.3.3",
"numpy==2.2.6",
"matplotlib==3.10.7",
"pillow==12.0.0",
"beautifulsoup4==4.14.3",
"ddgs==9.9.3",
"requests>=2.32,<3",
"httpx==0.28.1",
"python-dateutil==2.9.0.post0",
"pytz==2025.2",
"stripe>=12.0.0,<14.0.0",
# Agentic task execution (#63): Redis-backed channel layer for multi-worker
# progress fan-out, plus Celery for durable long-running agent runs.
"channels-redis==4.3.0",
"redis==6.4.0",
"celery==5.5.3",
]
[dependency-groups]
dev = [
"parameterized==0.9.0",
"black==25.11.0",
]
[tool.uv]
package = false