Spaces:
Paused
Paused
Commit History
-
fix: adjust temperature setting for generation to improve output quality
a248d59
-
fix: виправлення кодування Промт 8.txt (CP1251 → UTF-8) та форматування prompts.py
0c56107 -
feat: introduce few-shot prompting with semantic similarity for EU legal assistant
8184d8d
-
feat: setup progress bar for analysis action and swap batch/settings tabs
397d321 -
extend provider-specific prompt caching to analysis path
Ayonae8ea072 -
refactor prompt assembly for provider-specific caching
Ayona240f6e7 -
docs: Update HELP.md with analysis thinking info and latest models
f8e9d1e -
feat: Add thinking parameters to Analysis mode and update models list in README
0b3ee40 -
handoff: align help and trim debug leakage
Ayona8f359a6 -
handoff: harden config and align MVP surface
Ayona22df219
-
docs: mark legacy/summary files as pointers to canonical docs (dedup)
Ayona601f5a4 -
docs: reorganize markdown files into docs/; add docs index
Ayona4e70645 -
docs: clarify scope (generation-first) and index snapshot freshness
Ayona4c6d96a
-
feat: Refine legal position prompts for clarity and specificity in analysis workflow
eaccccc
-
feat: Add validation to skip duplicate header rows in batch processing
- Skip rows where majority of cell values match column names (header duplicates) - Add tests_data/ to .gitignore to prevent binary xlsx files from being committed Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>805748d -
feat: Allow default analysis model in PrecedentAnalysisWorkflow if not specified
028f33a -
feat: Update OpenAI generation models to include display names and remove deprecated models
e575bd8 -
feat: Update OpenAI generation model configuration to include display name and default setting for GPT-5.4
8bb8a00 -
feat: Update generation models in configuration to include GPT-5.4 as default
402f9ad
-
feat: Revise legal position prompt structure and rules for clarity and application
db4aa79 -
refactor: Update legal position prompts for clarity and specificity
79ed684
-
feat: Add support for GPT-5.3 Chat Latest model in configuration and reasoning parameters
8571f1b
-
feat: Enhance OpenAI reasoning capabilities with configurable parameters
b2f09af -
I cannot generate a commit message without knowing the specific changes made to `interface.py`.
014edbb -
test: Add script to verify Anthropic adaptive thinking and output effort parameters.
71dc9f7 -
Support output_config effort parameter for Claude Adaptive Thinking
86d1da5 -
Re-enable extended thinking for Claude Haiku 4.5 models
28552c9 -
Fix Anthropic thinking mode configuration logic
09efcd1 -
chore: Update dependencies and adjust interface logic.
085df7b
-
chore: Update ignored files and refine prompt content.
6a09f03 -
feat: Introduce `document` input variable to the legal analysis prompt and update `PromptTemplate` import path.
5eeca45 -
feat: enhance text cleaning utility to remove HTML tags and entities, update documentation, and requirements.
3418cd7
-
feat: Enhance interactivity of Gradio interface and improve handling of empty response in PrecedentAnalysisWorkflow
59a8fbf -
feat: Update system prompt structure to include cache control in LLMAnalyzer and generate_legal_position functions
d0c3228 -
feat: Optimize caching for Anthropic and OpenAI prompts, restructure prompt variables for efficiency
b434018
-
feat: Initialize search components at module level for HF Spaces
ca73321 -
feat: Improve user feedback during legal position generation with loading message and button interactivity
3d8fd57 -
feat: Suppress asyncio event loop warnings on HF Spaces shutdown
b79a815 -
feat: Enhance save button interactivity in Gradio interface for prompt changes
eb76688 -
feat: Update system prompt and legal position template for clarity and specificity
1596c7f -
feat: Add debug prompt logging functionality with environment variable support
0c2542b
-
feat: Оновлення UI для GPT-5.2 та додавання контролю MaxTokens
a765e3e
-
feat: Інтеграція GPT-5.2 з підтримкою reasoning
✨ Додано: - Модель GPT-5.2 для генерації та аналізу правових позицій - Підтримка параметрів reasoning_effort (low/medium/high) - Підтримка параметрів verbosity (low/medium/high) - Опція store=false для конфіденційності даних 📝 Оновлено: - config/environments/default.yaml - додано GPT-5.2 - config/models.py - enum ключ GPT5_2 - main.py - підтримка нових параметрів OpenAI API - requirements.txt - openai>=1.58.0 - README.md - інформація про GPT-5.2 📚 Документація: - GPT5_2_INTEGRATION.md - повна документація - GPT5_2_QUICKSTART.md - швидкий старт - examples/gpt5_2_example.py - робочі приклади - CHANGELOG_GPT5_2.md - детальний changelog - GPT5_2_SUMMARY.md - підсумок інтеграції 🎯 Версія: 2.2.0492b465
-
Add diagnostic logging and raw httpx connectivity test for OpenAI API
98f5eca -
Disable HTTP/2 in httpx client for OpenAI and DeepSeek to avoid 421 Misdirected Request errors and ensure consistent connections in HF Spaces
381cd06 -
Refactor httpx client usage for OpenAI and DeepSeek: implement context management to prevent socket leaks and improve error logging
3e63a13 -
Fix OpenAI/DeepSeek HF Spaces connectivity: use custom httpx.Client to handle asyncio conflicts
60a364a -
Enhance API key debugging: add length and prefix display for OPENAI_API_KEY; update provider availability checks to use os.getenv for real-time state
71df805 -
Enhance provider management: normalize response keys, add availability checks, and improve Gradio interface for AI providers
a09e8cb -
Revert httpx.Client customization: use default OpenAI SDK settings for async compatibility in HF Spaces
5c25abd