| [build-system] | |
| requires = ["hatchling"] | |
| build-backend = "hatchling.build" | |
| [project] | |
| name = "agent-service-data-eyond" | |
| version = "0.1.0" | |
| description = "Agentic Service Data Eyond — Multi-Agent AI Backend" | |
| requires-python = ">=3.12,<3.13" | |
| dependencies = [ | |
| # --- Web Framework --- | |
| "fastapi[standard]==0.115.6", | |
| "uvicorn[standard]==0.32.1", | |
| "python-multipart==0.0.12", | |
| "starlette==0.41.3", | |
| "sse-starlette==2.1.3", | |
| # --- LangChain Core Ecosystem (NO LiteLLM) --- | |
| "langchain==0.3.13", | |
| "langchain-core==0.3.28", | |
| "langchain-community==0.3.13", | |
| "langchain-openai==0.2.14", | |
| "langchain-postgres>=0.0.13", | |
| "langgraph==0.2.60", | |
| "langgraph-checkpoint-postgres==2.0.9", | |
| # --- LLM / Azure OpenAI --- | |
| "openai==1.58.1", | |
| "tiktoken==0.8.0", | |
| # --- Database --- | |
| "sqlalchemy[asyncio]==2.0.36", | |
| "asyncpg==0.30.0", | |
| "psycopg[binary,pool]==3.2.3", | |
| "pgvector==0.3.6", | |
| "alembic==1.14.0", | |
| # --- Azure --- | |
| "azure-storage-blob==12.23.1", | |
| "azure-identity==1.19.0", | |
| "azure-ai-documentintelligence==1.0.0", | |
| # --- Pydantic / Validation --- | |
| # Moved 2.10.3 -> 2.13.5 on 2026-09-08. `mistralai` requires >=2.11.2, and | |
| # Mistral OCR is now THE parser rather than an optional backend, so the old | |
| # pin made the parser uninstallable in the deployed Space. Pinned forward | |
| # rather than opened to a range, matching this file's convention. The full | |
| # suite (659 passed / 7 skipped) was green on 2.13.5 before the pin moved, | |
| # so this records a tested version rather than a hopeful one. | |
| "pydantic==2.13.5", | |
| "pydantic-settings==2.7.0", | |
| # --- Observability --- | |
| "langfuse==2.57.4", | |
| "structlog==24.4.0", | |
| "prometheus-client==0.21.1", | |
| # --- Security --- | |
| "passlib[bcrypt]==1.7.4", | |
| "cryptography==44.0.0", | |
| # --- Rate Limiting --- | |
| "slowapi==0.1.9", | |
| "redis==5.2.1", | |
| # --- Retry --- | |
| "tenacity==9.0.0", | |
| # --- Document Processing (for reading existing docs from blob) --- | |
| "pypdf==5.1.0", | |
| "python-docx==1.1.2", | |
| # Mistral OCR — the knowledge pipeline's parser. A MAIN dependency since | |
| # 2026-09-08, not an extra: the Dockerfile runs `uv sync --frozen --no-dev`, | |
| # which installs main dependencies only, so as an extra it was absent from | |
| # the Space and every ingest failed at parse with ModuleNotFoundError. That | |
| # went unnoticed while parsing was never on a deployed path. It is a small | |
| # API client; nothing on the request path imports it. | |
| # Pinned, not ranged, and pinned to 2.9.4 specifically: `>=1.9` resolved to | |
| # 1.12.4, while every end-to-end run that proved this pipeline works — the | |
| # full ingest of 2026-09-08, Mistral OCR through to 88 persisted entries — | |
| # ran on 2.9.4. Shipping the version nobody exercised, across a major | |
| # boundary, is not a saving. 2.x also drops the opentelemetry chain 1.x | |
| # pulled in. ⚠️ Sofhia declared `>=1.9`; if `knowledge_parsing` needs 1.x | |
| # semantics anywhere, this is the line to revisit. | |
| "mistralai==2.9.4", | |
| "openpyxl==3.1.5", | |
| "pandas==2.2.3", | |
| # --- Chart/Visualization --- | |
| "matplotlib==3.9.3", | |
| "plotly==5.24.1", | |
| "kaleido==0.2.1", | |
| # --- MCP --- | |
| "mcp==1.2.0", | |
| # --- Advanced RAG --- | |
| "rank-bm25==0.2.2", | |
| "sentence-transformers==3.3.1", | |
| # --- PII Detection (no LiteLLM) --- | |
| "presidio-analyzer==2.2.355", | |
| "presidio-anonymizer==2.2.355", | |
| "spacy==3.8.3", | |
| # --- Utilities --- | |
| "httpx==0.28.1", | |
| "anyio==4.7.0", | |
| "python-dotenv==1.0.1", | |
| "orjson==3.10.12", | |
| "cachetools==5.5.0", | |
| "apscheduler==3.10.4", | |
| "jsonpatch>=1.33", | |
| "psycopg2>=2.9.11", | |
| # --- SQL parsing / guardrails --- | |
| "sqlglot>=25.0.0", | |
| # --- User-DB connectors (db_pipeline) --- | |
| "pymysql>=1.1.1", | |
| "pymssql>=2.3.0", | |
| "sqlalchemy-bigquery>=1.11.0", | |
| "snowflake-sqlalchemy>=1.7.0", | |
| # --- OCR (pdf processing) --- | |
| "pdf2image>=1.17.0", | |
| "pytesseract>=0.3.13", | |
| "pypdf2>=3.0.1", | |
| "pyarrow>=24.0.0", | |
| "rapidfuzz>=3.14.5", | |
| "gliner>=0.2.13", | |
| # GLiNER's backend. CPU-pinned for Linux — see [tool.uv.sources] below. | |
| "torch>=2.6", | |
| ] | |
| [project.optional-dependencies] | |
| dev = [ | |
| "pytest==8.3.4", | |
| "pytest-asyncio==0.24.0", | |
| "pytest-cov==6.0.0", | |
| "httpx==0.28.1", | |
| "ruff==0.8.4", | |
| "mypy==1.13.0", | |
| "pre-commit==4.0.1", | |
| ] | |
| # Document parsing for the knowledge pipeline (src/knowledge_parsing/). | |
| # | |
| # Deliberately an EXTRA, not a main dependency: MinerU pulls torch and its model | |
| # tail (GBs), and the agent service never parses documents at request time — | |
| # parsing is an offline, admin-triggered batch job. Keeping it here means the | |
| # deployed Space does not build or ship any of it. | |
| # | |
| # pip install -e ".[parsing]" | |
| knowledge-parsing = [ | |
| # DROPPED 2026-09-07 (Rifqi): the pipeline runs on Mistral OCR. MinerU is no | |
| # longer used, and it is installed nowhere — not in the Space, and not in the | |
| # local venv (verified). Commented rather than deleted per the house | |
| # convention; the MinerU code paths in `src/knowledge_parsing/` are Sofhia's | |
| # and are untouched by this. | |
| # | |
| # It could not have stayed regardless: `mineru==3.4.4` requires | |
| # python-docx>=1.2.0 and a newer pypdf than this project pins, which made | |
| # `uv lock` fail OUTRIGHT — for the whole project, on every environment, not | |
| # just for this extra. The lock could not be regenerated at all, blocking | |
| # every dependency change including the CPU-torch pin below. It was already | |
| # absent from uv.lock for that reason, so nothing that resolved before stops | |
| # resolving now. | |
| # | |
| # Restoring it would mean moving the pinned python-docx and pypdf first — | |
| # a decision about the live RAG path (`src/knowledge/processing_service.py` | |
| # is the only `docx` consumer), not about parsing. | |
| # "mineru==3.4.4", | |
| # Mistral OCR moved to the MAIN dependencies 2026-09-08 — see the | |
| # "Document Parsing" block. It is the parser, and an extra is not installed | |
| # by `uv sync --frozen --no-dev`, so the Space would have shipped without | |
| # the one library ingestion cannot start without. | |
| ] | |
| # --- torch: CPU wheels on Linux (N7b, 2026-09-07) --------------------------- | |
| # | |
| # The default PyPI `torch` wheel for Linux bundles the entire CUDA runtime as | |
| # transitive `nvidia-*` dependencies — ~2.5 GB installed, in a Space that has no | |
| # GPU and never launches a kernel. Pinning the `+cpu` build from PyTorch's own | |
| # index drops all of those for roughly 200 MB, with no behavioural change: | |
| # nothing here ever ran on CUDA. | |
| # | |
| # Linux only, deliberately. PyPI's Windows and macOS wheels are already CPU-only, | |
| # so the marker leaves local development resolving exactly as it does today. | |
| # | |
| # `explicit = true` means this index is used ONLY for packages that name it — | |
| # without it, uv would search it for every dependency and could source something | |
| # else from there silently. | |
| # | |
| # torch cannot become an optional extra the way `mineru` is: GLiNER *is* the term | |
| # filter (`use_span_filter=False` yields zero mentions), so extraction in the | |
| # Space requires it installed. Only its size is negotiable, not its presence. | |
| [[tool.uv.index]] | |
| name = "pytorch-cpu" | |
| url = "https://download.pytorch.org/whl/cpu" | |
| explicit = true | |
| [tool.uv.sources] | |
| torch = [{ index = "pytorch-cpu", marker = "sys_platform == 'linux'" }] | |
| [tool.hatch.build.targets.wheel] | |
| packages = ["src/agent_service"] | |
| [tool.ruff] | |
| target-version = "py312" | |
| line-length = 100 | |
| [tool.ruff.lint] | |
| select = ["E", "F", "I", "N", "UP", "S", "B", "A", "C4", "T20"] | |
| ignore = [ | |
| "S101", # assert statements OK in tests | |
| "S105", # hardcoded passwords — false positives in config | |
| "S106", | |
| "B008", # FastAPI Depends() calls OK in function args | |
| ] | |
| [tool.ruff.lint.per-file-ignores] | |
| # S608: golden compiler tests assert literal SQL strings (incl. concatenated | |
| # suffixes) — they never execute against a DB, so it's a false positive here. | |
| "tests/**" = ["S101", "S105", "S106", "S608"] | |
| # T201: eval/ scripts are CLIs — print() is their intended output channel. | |
| "eval/**" = ["T201"] | |
| # Same rule, same reason: this is an operator-run CLI, and its printed output IS | |
| # the deliverable. | |
| "src/knowledge_extraction/cli.py" = ["T201"] | |
| # Same again for the knowledge-parsing CLI entry points. Scoped to the two files | |
| # rather than the package, so the library modules stay print-free. | |
| "src/knowledge_parsing/run.py" = ["T201"] | |
| "src/knowledge_parsing/report.py" = ["T201"] | |
| # Pembungkus pengembangan: print() memang saluran keluarannya, dan subprocess | |
| # memang tugasnya — dia menjalankan CLI parsing dengan env var yang sudah | |
| # disiapkan. Argumennya daftar, tidak pernah lewat shell. | |
| "scripts/parse.py" = ["T201", "S603"] | |
| [tool.mypy] | |
| python_version = "3.12" | |
| strict = true | |
| ignore_missing_imports = true | |
| plugins = ["pydantic.mypy"] | |
| [tool.pytest.ini_options] | |
| asyncio_mode = "auto" | |
| testpaths = ["tests"] | |
| filterwarnings = [ | |
| "ignore::DeprecationWarning", | |
| ] | |
| [dependency-groups] | |
| dev = [ | |
| "pytest>=8.3.4", | |
| "pytest-asyncio>=0.24.0", | |
| "ruff>=0.8.4", | |
| ] | |