build(deps): declare dependencies in pyproject.toml with docling and milvus extras

requirements.txt pinned torch and transformers in core although only docling
needs them, and on Linux torch pulls the CUDA 13 stack: 2.7 GB of the 3.0 GB
wheel download. Direct dependencies now live in pyproject.toml, uv.lock pins
everything, and application/requirements*.txt are exported from the lock by
scripts/export_requirements.sh (each file is the core set plus one extra).

The docling extra pins torch/torchvision/transformers itself and, on Linux,
resolves torch from the CPU-only PyTorch index (no nvidia packages). milvus
(pymilvus + milvus-lite, which pulls pyarrow) is the second extra.

application/core/optional_deps.py is the one place install hints come from;
the milvus store and the docling call sites use it so a missing extra fails
with the exact command to run.

docs/content/Deploying/Development-Environment.mdx

@@ -94,13 +94,25 @@ To run the DocsGPT backend locally, you'll need to set up a Python environment a
     pip install -r application/requirements.txt
     ```
 
-    Optionally add the docling parser engine (OCR, `structured` output for
-    `read_document`; the default anydoc engine does not need it):
+    Dependencies are declared in `pyproject.toml` and locked in `uv.lock`; the
+    `requirements*.txt` files are exported from that lock, so with
+    [uv](https://docs.astral.sh/uv/) installed `uv sync` sets up the same
+    environment (plus the test tools) in one step.
+
+    Optional extras are not installed by default. Add them when you need the
+    feature (each file is the core set plus the extra):
 
     ```bash
-    pip install -r application/requirements-docling.txt
+    pip install -r application/requirements-docling.txt   # docling parser engine: OCR backend, read_document structured output
+    pip install -r application/requirements-milvus.txt    # VECTOR_STORE=milvus
+    # or with uv: uv sync --extra docling --extra milvus
     ```
 
+    A feature whose extra is missing fails with the exact command to run.
+    After changing `pyproject.toml`, run `uv lock` and
+    `bash scripts/export_requirements.sh` so the exported files stay in sync
+    (CI checks this).
+
 5.  **Run the Backend:**
 
     For local development, run the ASGI composition under uvicorn. It serves the **whole** application, hot-reloads on source changes, and matches the production runtime: