Spaces:

bayan10
/

bayan-api

Sleeping

App Files Files Community

bayan-api / src

Commit History

Jun 17

22:40
fix: Remove duplicate /api/spelling route causing AssertionError

youssefreda9

738185d
22:35
feat: Enable ContextualCorrector (BERT MLM) for spelling - Pre-download AutoModelForMaskedLM in Dockerfile

youssefreda9

bcf3607
22:32
feat: Add AraSpell spelling correction endpoint (POST /api/spelling) with lazy model loading - Extract AraSpell pipeline into src/nlp/spelling/ (araspell_rules.py + araspell_service.py) - Pre-download AraBERT encoder-decoder + checkpoint in Dockerfile - Lazy load on first request, contextual=False to save RAM - Update health check to report spelling status

youssefreda9

53f433b
21:42
fix: Always load models on import (RENDER/GUNICORN_LOADED env vars not set in HF Spaces)

youssefreda9

ccf3eef
21:36
debug: Add startup error tracking + memory info to debug endpoint

youssefreda9

756045d
21:11
fix: Load summarization model locally with float16 (HF free tier has no outbound DNS)⁠

youssefreda9

d229a9c
21:04
fix: DNS endpoint discovery - test multiple HF hostnames to find reachable one

youssefreda9

922cc55
20:59
fix: Construct RequestParameters with all 6 required args (url, task, model, json, data, headers)

youssefreda9

625b5d7
20:55
fix: Construct RequestParameters properly using inspect.signature

youssefreda9

d3fe06e
20:50
fix: Try multiple _inner_post calling conventions + inspect signature

youssefreda9

06ff15b
20:45
fix: Use _inner_post transport from InferenceClient v1.19.0

youssefreda9

82a77dd
20:40
debug: Deep diagnostics to find InferenceClient internal transport

youssefreda9

dc7f39b
20:35
fix: Back to InferenceClient with correct method signatures + diagnostics

youssefreda9

8b888b0
20:29
fix: Use requests.post() directly instead of InferenceClient (version compat issue)

youssefreda9

0405b6b
20:25
fix: Use client.post() for all models, fix summarization params, better error capture

youssefreda9

e18c6c8
20:20
fix: Use huggingface_hub InferenceClient instead of raw urllib (fixes DNS inside HF Spaces)

youssefreda9

7cd5afa
20:15
fix: Add wait_for_model, debug endpoint, and better HF API error handling

youssefreda9

2df4f2d
20:07
feat: Switch all NLP models to HuggingFace Inference API⁠

youssefreda9

239c0bb

Jun 16

19:10
Fix: Google link failure now falls back to full sign-in instead of error toast

youssefreda9

d487585
19:05
Fix: Guest login navigates to home/landing page instead of editor

youssefreda9

349ddaa
18:15
authDone Ready for deployment

youssefreda9

bb51619
12:51
added light theme and ISLAMIC RAG and fixed the UI/UX issues and added the auth

MAtef24

012d0ac

Jan 23

13:51
initial UI

MAtef24

0c086e7

Oct 25, 2025

16:12
Initial commit: repository skeleton and folder READMEs

MAtef24

b366dff

Commit History

Jun 17

fix: Remove duplicate /api/spelling route causing AssertionError

feat: Enable ContextualCorrector (BERT MLM) for spelling - Pre-download AutoModelForMaskedLM in Dockerfile

fix: Always load models on import (RENDER/GUNICORN_LOADED env vars not set in HF Spaces)

debug: Add startup error tracking + memory info to debug endpoint

fix: Load summarization model locally with float16 (HF free tier has no outbound DNS)⁠

fix: DNS endpoint discovery - test multiple HF hostnames to find reachable one

fix: Construct RequestParameters with all 6 required args (url, task, model, json, data, headers)

fix: Construct RequestParameters properly using inspect.signature

fix: Try multiple _inner_post calling conventions + inspect signature

fix: Use _inner_post transport from InferenceClient v1.19.0

debug: Deep diagnostics to find InferenceClient internal transport

fix: Back to InferenceClient with correct method signatures + diagnostics

fix: Use requests.post() directly instead of InferenceClient (version compat issue)

fix: Use client.post() for all models, fix summarization params, better error capture

fix: Use huggingface_hub InferenceClient instead of raw urllib (fixes DNS inside HF Spaces)

fix: Add wait_for_model, debug endpoint, and better HF API error handling

feat: Switch all NLP models to HuggingFace Inference API⁠

Jun 16

Fix: Google link failure now falls back to full sign-in instead of error toast

Fix: Guest login navigates to home/landing page instead of editor

authDone Ready for deployment

added light theme and ISLAMIC RAG and fixed the UI/UX issues and added the auth

Jan 23

initial UI

Oct 25, 2025

Initial commit: repository skeleton and folder READMEs