Unblock the event loop during ingest, fit summarize in free-tier quota
beerohan
7935a97
Profiling a 120-page PDF showed ingest cost is almost entirely embedding:
parsing 0.09s, cleaning 0.00s, embedding 6.51s (98.6%). That embedding ran
synchronously inside the async /upload route, so it blocked the whole event
loop - concurrent uploads serialized and status polling stalled behind them,
which is what made multi-file uploads feel frozen.
Move add_document and the PDF/DOCX/text parsing onto worker threads via
asyncio.to_thread. /status now answers in ~3ms while uploads run, instead of
queueing behind a full embed. Wall time for three PDFs improves modestly
(12s -> 10s); embedding is CPU-bound, so threads cannot multiply throughput
on shared cores.
Larger embedding batches were benchmarked and rejected: batch_size 10/64/128
measured 3.47s/3.73s/3.80s, so the default of 10 stays.
Summarize retrieved similarity_top_k=8 chunks, roughly 8k input tokens, which
alone exhausts Groq's free-tier 8,000 tokens-per-minute budget and returned a
429 before generating anything. Lower it…
Rebuild frontend in React, add doc/session management, fix broken deps
beerohan
dd4a03a
Frontend rebuilt as a React + Vite + TypeScript SPA, replacing the vanilla
JS/CSS app. Adds dark mode, a document list with per-document delete,
multi-file upload, cancellable streaming, and chat history that survives a
page reload. Served by FastAPI from static/, which is now a build artifact
produced by the Node stage of a multi-stage Dockerfile.
Backend additions:
- DELETE /documents/{name} removes a single document from the Chroma index
- Chat history persisted to SQLite (app/services/history_service.py) with
GET/PATCH/DELETE /sessions routes; transcripts survive process restarts
Performance:
- /stream_query fetched citation sources by calling query() a second time,
running a full LLM generation whose text was discarded. Replaced with a
retrieval-only path, saving ~0.6s and one Groq call per message.
- Embedding model is warmed during startup so the first request no longer
pays the model-load cost.
Pre-existing breakages fixed:
- requirements.txt pinned llama-index-embed…
Flatten directory structure for deployment
beerohan
5ac3946
Update changes
beerohan
2537b99
Update README files
beerohan
1969b37
Set exact README HF configuration
beerohan
0a92a68
Fix README frontmatter strictly for HF
beerohan
cebcaaa
Update HuggingFace Space configuration in README frontmatter
beerohan
57b8cce
Update studyrag project files
beerohan
a0c24d5
Update README.md
Rohan B
Unverified signature
cd07daa
Fix header formatting in README.md
Rohan B
Unverified signature
ef36963
Create README.md
Rohan B
Unverified signature
b1adda7
Update all files for HuggingFace Spaces (port 7860)
beerohan
b99dd79
Configure for Hugging Face Spaces deployment
beerohan
489dcde
Update README to reflect FastEmbed
beerohan
be3ae40
Switch to FastEmbed for lower memory usage
beerohan
38c067f
Update README for Studyson with Groq, remove old references
beerohan
3106cc9
Rename to Studyson
beerohan
5af2bb9
Rename to studyrag, switch to Groq API, add deployment files
