SAGEMAKER_REGION, SAGEMAKER_ACCESS_KEY and SAGEMAKER_SECRET_KEY survive
only as a fallback for the S3_* credentials. They carry
Field(deprecated=...) now, so any read emits a DeprecationWarning naming
the replacement and the generated reference shows the notice. The S3
store is the one sanctioned reader; it silences that warning locally
because it already logs its own operator-facing one when the fallback
is actually used.
DEFAULT_MAX_HISTORY was referenced nowhere. RETRIEVERS_ENABLED was read by
no code at all, while two docs pages described it as an enforced
allow-list; both the setting and those claims are removed.
The hand-maintained settings page documented 95 of 258 settings and
.env-template 42, and both drifted as fields were added. The field
descriptions now live on the model, so the reference is rendered from it:
python -m docsgpt.core.settings.reference --write
writes docs/content/Deploying/Settings-Reference.mdx, one section per
settings group with each field's type, default, constraints, aliases and
description. --check reports a stale page, and tests/core/test_settings.py
fails when the checked-in page no longer matches the definitions, so a
new setting cannot land undocumented.
test_settings.py also pins the composition contract: every group field is
a flat Settings attribute, no field is defined twice, every field has a
description, and the secret-normalising validator of every group is
applied (the case that a shared method name would silently drop).
The App Configuration page points at the reference instead of at
settings.py, and the reference is listed in the Deploying navigation.
- Ship tiktoken's cl100k_base inside the package and build the encoding
from it, so token counting never downloads anything.
- Default EMBEDDINGS_CACHE_DIR to <data home>/models instead of FastEmbed's
temp dir, and read tokenizer.json and repo metadata from that cache, so
a model downloads once and survives reboots.
- TTS_PROVIDER=none and STT_PROVIDER=none switch the speech features off:
the endpoints return 404, audio files fail to ingest with a clear
message, /api/config reports tts_available/stt_available, and the UI
hides the Speak and microphone buttons.
- Drop the Google Fonts Roboto import from the web UI.
- prefetch-models fills the cache the app reads; verify-offline checks the
packaged encoding.
- Docs: new Air-Gapped Deployment guide, settings and cache notes.
pip install docsgpt now brings the web UI with it: `docsgpt api` serves the
API and the UI on one port.
- scripts/build_frontend.sh builds the frontend into docsgpt/static
(gitignored) the way the frontend image does: .env.development as the
production baseline, and index.html loading /config.js ahead of the
bundle. hatch admits the directory into the wheel and the sdist through
`artifacts`; the package workflows run the script before `uv build` and
fail if the wheel lacks the UI. The backend image keeps ignoring it.
- docsgpt/ui.py serves the build in front of Flask: files as they are,
hashed assets immutable, Flask's own path prefixes (taken from its URL map,
so new blueprints need no registration) passed through, every other GET
rendered as index.html for the client-side router. /config.js is generated
per request with VITE_API_HOST and VITE_BASE_URL set to the page's origin,
VITE_* environment variables winning. SERVE_UI=false leaves the API alone.
- docsgpt api configures gunicorn in code (gunicorn.app.base.Application)
instead of rewriting sys.argv, so the SIGUSR2 re-exec that gunicorn uses
for zero-downtime upgrades runs the docsgpt console script again and
works; verified with a live handover.
- Docs: the pip page says the UI is included, that DOCSGPT_HOME and
DOCSGPT_ENV_FILE are process environment variables rather than .env
entries, and the settings page describes SERVE_UI.
The backend import package is now docsgpt, the name it will carry on PyPI;
application was far too generic to install into anyone's site-packages.
git mv plus a mechanical rewrite of every import, dotted string and path
reference: 734 Python files, the compose files, Dockerfile, workflows, docs,
setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage
config, .gitignore. Behaviour is unchanged.
Kept for one release:
- A top-level application package whose meta-path finder resolves
application.x.y to the already-imported docsgpt.x.y object, so old imports
and entry points (celery -A application.app.celery,
uvicorn application.asgi:asgi_app) keep working with a FutureWarning.
- Celery registers every application.* task name as an alias of its
docsgpt.* task on start-up, so messages queued by the previous release still
run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries
the previous release wrote are left unread instead of firing twice.
The backend image builds from the repository root (docker build -f
docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore
allow-lists docsgpt/ and application/ and keeps caches, local data, .env
files, the sample index files and the Dockerfile out. Compose and the image
workflows point at the new context.
OMP_NUM_THREADS=4 capped torch in the old image, but FastEmbed runs on
onnxruntime, which ignores it and sizes its pool to the host's core count.
A CPU-limited container still reports every host core, so embedding ran with
64 threads on a 4-CPU sandbox and took up to 12x longer per file. The image
now sets EMBEDDINGS_THREADS=4 next to the existing caps; the settings guide
documents the knob.
- append_compression_point only skips a point when both query_index and
compressed_summary are present and match the last one; points without
those fields (as in the repository tests) were all being treated as
duplicates.
- The incremental compression tail and the orchestrator's "anything new
since the last point" check exclude the visible summary row, which the
prompt already receives through existing_compressions.
- Summary rows carry a persisted metadata marker; replay filters on the
marker, and falls back to the label only for rows written before it that
have no tool calls and no per-turn metadata, so a user who types the
label text keeps their turn.
- The prompt_cache_key is a hash of the user id, never the id itself.
- Describe truncation="auto" as dropping the oldest items.
In store mode every user turn chained onto the previous response, so the
provider's stored transcript grew without bound (measured: 889k prompt
tokens for a 37k-token saved history) while every local guard, the
compression pipeline included, measured the saved history. Each chained
tool round also re-sent the system message, which the server appends rather
than dedupes, and a saved compression point was applied exactly once, in the
turn that made it.
Chaining is now bounded. A turn starts from the saved history when the
previous turn's reported prompt reached the chain budget (default: the
model's context window), when the conversation was compressed after that
turn was produced, or when OPENAI_RESPONSES_CHAIN_ACROSS_TURNS is off.
Chained rounds omit an unchanged system head (hash carried in the persisted
Responses state). truncation="auto" is available behind a setting as a
backstop against a chain that outgrows the model's window.
Compression: a saved point is applied at every turn start; the threshold
counts the summary plus the queries after the point instead of the raw
history; re-compression summarises only the tail on top of the last point;
the mid-execution path marks itself persisted and resets the provider chain
so the rebuilt messages are the context; an empty summary is rejected; the
visible "[Context Compression Summary]" rows are no longer replayed as
history; appending the same point twice is a no-op.
Cache hints: a per-user prompt_cache_key and an optional
prompt_cache_retention on Responses API calls.
Measured on Azure with the same client shape as production (stateless
OpenAI client, server-side tools, PDF part): tokens billed on the sixth turn
fell from 58k to 35k, tool rounds add tens of tokens instead of ~2.8k, the
turn after a compression reused the saved summary in under two seconds
instead of re-summarising, and the round after a mid-execution compression
started from the compressed context instead of the full stored transcript.
Conflicts, and how each was taken:
- application/core/settings.py — ours. The renamed OCR_ENABLED /
OCR_ATTACHMENTS_ENABLED / OCR_MIN_CHARS_PER_PAGE accept main's
DOCLING_OCR_* spellings as AliasChoices, so nothing is dropped.
- application/Dockerfile — both. Main's install layers plus the
INSTALL_DOCLING build arg.
- application/parser/file/constants.py — both imports.
- deployment/docker-compose.yaml — both. The INSTALL_DOCLING /
INSTALL_TESSERACT build args on backend and worker, and main's
-Q docsgpt,parsing,embeddings, which query embedding needs.
- tests/conftest.py — theirs. Both sides fixed the same pytest-postgresql
9.0.0 autocommit= breakage; main's spelling is the one already on main.
- application/requirements.txt — the comments claimed different reasons
torch is in core. Main's is the true one now: it removed
sentence-transformers, so docling is torch's only remaining consumer.
Two things the merge broke without conflicting:
- onnxruntime. This branch moved it out of core into the docling extra;
main meanwhile made it the runtime local embeddings execute on
(fastembed). Git took the deletion, leaving fastembed with no pinned
runtime in a repo that pins everything. Restored to core, and no longer
pinned twice from the extra.
- The frontend copy of ATTACHMENT_PARSER_EXTENSIONS. The backend list is
derived and picked up the anydoc suffixes; the hand-kept frontend mirror
did not, so the composer would refuse files the API accepts.
tests/parser/file/test_constants.py is what caught it.
ruff, pytest (9897 passed), frontend build and docs build all pass. The
image build is unverified: no Docker daemon on this machine.
Five defects from a review of the embeddings work, four of them silent.
- Write local files atomically. `LocalStorage.save_file` streamed straight onto
the destination, so an interrupted write left a truncated file. `reembed`
rewrites every index it touches, and a half-written `index.faiss` loads at
neither the old width nor the new one -- the source was unrecoverable, with
no backup and no temp file left behind. Bytes now land beside the destination
and move into place with `os.replace`. S3 was already safe (single PUT).
- Read pgvector chunks a page at a time. `reembed_pgvector` materialised every
`(id, text)` row for a source before embedding -- ~1.6 GB at 200k chunks and
several times that for non-Latin scripts, with the `PGresult` held alongside
until the cursor closed. Inside the shipped 4Gi limit, while also holding the
model, that is an OOMKill -- which is exactly the SIGKILL the point above
turned into a destroyed index. It now walks the source by keyset.
- Bound the first wave of delegated embeds. The failure cooldown is only latched
once the first `get()` returns, so every request already in flight paid the
full EMBEDDINGS_DELEGATE_TIMEOUT: measured 64 threads all timing out together,
and at the shipped 60s across a 96-thread WSGI pool that is an API serving
nothing at all, health checks included. One caller now probes while the rest
fail fast; after a single success the gate leaves the path entirely.
- Ship EMBEDDINGS_NAME commented in .env-template. The comment directly above it
says to leave it commented when upgrading, and the line shipped set. Any value
reaching `.env` lands in `model_fields_set`, which makes `resolve_embeddings_pin`
bail -- so a template-derived `.env` disabled the legacy pin outright and
repointed a populated index at a different 768-dim model, where no width check
fires. The pin already picks granite for a fresh install and mpnet for an
existing one, so nothing needs to be set by hand.
- Stamp `sources.model` on wiki sources. They were created with the column NULL
and then embedded like any other source, and the boot check reads NULL as
"pre-dates the column, therefore the legacy model" -- reporting a correctly
embedded source as stale on every startup of every process. Stamped at
creation, and again on each page re-embed so existing rows heal.
The two docs that promised the FAISS index survives a failed run said so of the
embed only; both now describe the write, and upgrading.mdx says to stop ingest
for the duration.
Query embedding moved to the Celery worker, but nothing that ships was
updated to consume the queue it dispatches to.
- Add `embeddings` to every worker `-Q` list (compose x3, k8s, devcontainer,
sandbox README). Without it a search blocked for EMBEDDINGS_DELEGATE_TIMEOUT
and then answered with no retrieved context, because classic_rag swallows the
dispatch error and skips the source -- bad answers, not an error.
- Skip the task_postrun heap reclaim for the embed task. The full gc.collect()
was written for docling/torch parses; on a worker holding the ONNX model it
measured ~86ms against ~8ms for the embed itself, a 9x slowdown of the round
trip for a task that allocates a few kilobytes.
- Resolve the installation pin in the re-embed script. It never imports
application.app, so an install pinned in app_metadata with no EMBEDDINGS_NAME
set -- every stock k8s deployment, whose manifests carry no embedding config
-- would rewrite its whole index with the legacy default and stamp
sources.model to match, then be told by the boot warning to run it again.
- Fail fast for 30s after a failed dispatch. fanout.embed_questions falls back
to letting each store embed its own query, so one dead-worker retrieval paid
the timeout once in the fan-out and again per source.
- Forget the task result. Nothing reads it back: the key is per-dispatch UUID,
not content-addressed, so a repeated query mints another. Left alone every
search leaked ~17KB for result_expires (7 days) into the Redis the broker
shares -- on the bundled k8s manifest (1Gi, no maxmemory policy) that is an
OOMKill that takes the broker with it.
- Release the model ensure_vector_schema loads to read the width of an
unregistered model, in a process that delegates and would never call it.
The width still comes from the model, not the table, so the mismatch check
the hook exists for keeps working.
- Correct the docs that said otherwise: embeddings.md claimed the standard
deployment worked unchanged, upgrading.mdx said no action was needed, and
the settings table listed none of the three delegation settings.
The API embeds every query it serves, so it held its own copy of the model:
~890 MB it never needed. EMBEDDINGS_DELEGATE_TO_WORKER (on by default) sends
the text to the Celery worker instead and gets the vector back, taking an API
process from 1176 MB to 285 MB with no ONNX Runtime imported at all. The client
embeds locally when it finds itself inside a worker task, so the worker never
dispatches to itself -- the same self-deadlock DOCUMENT_PARSE_QUEUE avoids on
the parsing side. EMBEDDINGS_BASE_URL still wins over it, and remains the right
answer for production.
ensure_vector_schema was constructing the embeddings instance purely to read
.dimension off it, loading several hundred MB of ONNX into every API and worker
process at import. For a model the registry describes that is a lookup; only an
unregistered name now falls back to loading.
EMBEDDINGS_BATCH_SIZE was sizing two unrelated things: chunks per store
transaction (and per remote embed request) and documents per ONNX forward pass.
Each pass pads every input up to its longest, and that waste grows with the
square of chunk length, so at the 1250-token default a batch of 32 peaked at
6.6 GB and took 326s where a batch of 1 peaked at 2.9 GB and took 90s. The
forward pass is now sized by EMBEDDINGS_MODEL_BATCH_SIZE, defaulting to 1;
storage and remote batching are unchanged at 32.
reembed embeds in-process: a batch job that walks the whole index should not
round-trip every chunk through a broker, and loading the model there reports a
real failure instead of timing out against an empty queue.
Also drops the mpnet zip download from the docs and the devcontainer, which
pointed at a SentenceTransformers export with no ONNX graph and had been inert
since the FastEmbed swap; corrects the claim that any sentence-transformers
model works; and settles the Configuring/Settings pages on what the registry
and the repository metadata actually decide.
- Replay prior-turn assistant text as input_text, not output_text: a
Responses easy-input message only accepts input_* content parts, so the
old shape would 400 on the second turn of every conversation (default
store=false resends prior turns inline).
- Always request include=["reasoning.encrypted_content"] so in-turn
reasoning carryover works whether or not the response is also stored
server-side (OPENAI_RESPONSES_STORE).
- Add detail="auto" to input_image parts.
- Remove the now-dead azure_openai option from setup.sh / setup.ps1 and
the docs, completing the AzureOpenAILLM removal.
- Tests: correct the input_text / image-detail / include assertions and
add parallel tool-call and stream-error coverage.
arc53-machine