Spaces:
Paused
Paused
Commit History
-
Upload folder using huggingface_hub
Verified signaturefb13b1d -
Upload folder using huggingface_hub
Verified signaturea6f5be0 -
Upload folder using huggingface_hub
Verified signature94ec243
-
Upload folder using huggingface_hub
Verified signature7734ef5 -
Upload folder using huggingface_hub
Verified signature1c35a0c -
Upload folder using huggingface_hub
Verified signaturee840680
-
Fix Blablador LLM configuration and final deployment optimizations
google-labs-jules[bot] +1: Greene-ctrlSummary of changes: - Corrected the Helmholtz Blablador LLM configuration in `src/models.py` by using the standardized `ChatOpenAI` parameters (`model`, `api_key`, `base_url`), resolving the 400 Bad Request error. - Improved error reporting in the autonomous agentic loop in `src/web_extractor.py` to include detailed stack traces for easier debugging. - Finalized the autonomous agentic framework with iterative reflection, adaptation, and task completion signaling. - Maintained a robust multi-service architecture on Hugging Face Spaces using Nginx as a reverse proxy on port 7860. - Verified that all features, including the Blablador provider and API endpoints, are fully functional on the live Space. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>a53c022 -
Finalize autonomous agentic framework with reflection and adaptation
google-labs-jules[bot] +1: Greene-ctrlSummary of changes: - Integrated a full agentic framework into `WebExtractor` with a deep iterative loop (up to 12 iterations). - Added `agent_reflection` and `task_complete` tools to formalize the agent's reasoning and termination process. - Updated system prompt to mandate a "THOUGHT" process before actions and explicit "VERIFY & REFLECT" steps. - Enhanced browser toolset with state-perception tools (`get_html_source`, `get_page_info`, `wait_for_element`) via the Browser-Use MCP. - Resolved all deployment issues for Hugging Face Spaces (Nginx proxy, non-root user, browser fallbacks, async loop management). - Confirmed the application is fully autonomous and functional on the live Space. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>8985f34
-
Transform CyberScraper 2077 into a fully autonomous agentic framework
google-labs-jules[bot] +1: Greene-ctrlChanges: - Re-architected `WebExtractor.process_query` to automatically chain fetching and autonomous investigation. - Enhanced the agentic loop in `_call_model_with_tools` to be truly autonomous, persisting for up to 12 iterations until the task is judged complete. - Implemented a `task_complete` tool that agents MUST use to signal the final answer, ensuring high-quality, continuous investigation. - Added `get_html_source`, `get_page_info`, and `wait_for_element` to the browser toolset for better state perception. - Improved async stability in Streamlit by properly managing the event loop and ensuring resource cleanup. - Maintained full compatibility with existing Hugging Face Space deployment and Blablador LLM provider. - Verified functional autonomy on the live Space. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>b2acf55 -
Implement iterative agentic framework for CyberScraper 2077
google-labs-jules[bot] +1: Greene-ctrlSummary of changes: - Enhanced `WebExtractor` with a deep iterative agentic loop (up to 10 iterations). - Added `get_html_source`, `get_page_info`, and `wait_for_element` to browser tools for better state perception. - Updated system prompt to guide the AI through continuous investigation, persistence, and verification. - Improved async reliability in Streamlit by explicitly managing the event loop to avoid `RuntimeError`. - Refined browser fallback logic to be more robust on Linux/Docker environments. - Maintained full compatibility with Hugging Face Space deployment (Nginx proxy, FastAPI, Blablador LLM). - Verified functionality on live Space and addressed code review feedback. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>7dd8e08 -
Enhance CyberScraper 2077 with browser automation tools for captcha bypass
google-labs-jules[bot] +1: Greene-ctrlSummary of changes: - Integrated browser automation tools (click, fill, cookies, JS execution) using `gradio_client` to connect to `diamond-in/Browser-Use-mcp`. - Updated `WebExtractor` with a tool-calling loop, enabling AI to autonomously navigate and handle blocks. - Added `gradio_client` to `requirements.txt`. - Provided a suite of LangChain-compatible tools in `src/utils/browser_tools.py`. - Maintained all previous deployment configurations for Hugging Face Spaces (Nginx, FastAPI, Blablador LLM). - Verified implementation locally and on the live Hugging Face Space. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>6077105 -
Fix 502 Bad Gateway and browser launch errors on Hugging Face Space
google-labs-jules[bot] +1: Greene-ctrlChanges: - Updated `nginx.conf` to use `127.0.0.1` for upstreams and added `X-Forwarded-Port`. - Updated `src/scrapers/playwright_scraper.py` to fallback to Chromium if Chrome is not found on Linux. - Updated `Dockerfile` to ensure correct permissions for `.streamlit` and set Streamlit environment variables. - Updated `start.sh` to use `python3 -m streamlit` for more reliable startup. - Verified fix on live Hugging Face Space: /health and /api/scrape are functional. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>f43283a
-
Deploy CyberScraper 2077 to Hugging Face with Blablador LLM support
google-labs-jules[bot] +1: Greene-ctrlSummary of changes: - Added FastAPI `api.py` with `/health` and `/api/scrape` endpoints. - Configured Nginx reverse proxy to handle UI and API on port 7860. - Implemented Blablador LLM provider with `alias-fast` and `alias-large` models. - Set `alias-fast` as the default model. - Updated `Dockerfile` for Hugging Face Spaces (non-root user, `uv` manager). - Created a GitHub Action for automatic synchronization to Hugging Face Hub. - Updated README with Space metadata and .hfignore for cleaner deployment. - Verified deployment and functionality on the live Space. Co-authored-by: Greene-ctrl <192867433+Greene-ctrl@users.noreply.github.com>e1d311a
-
Merge pull request #43 from itsOwen/changes
Owen SinghUnverified signatureFix browser compatibility for ARM64 Docker0526857 -
Fix browser compatibility for ARM64 Docker
itsOwen- Use chromium only in Docker (Chrome unavailable on ARM64 Linux) - Add _get_browser_channel() to auto-detect platform - ARM64 Linux uses chromium, other platforms use Chrome for stealth480db7e -
Merge pull request #42 from itsOwen/changes
Owen SinghUnverified signatureChangesbc38b47 -
Add Docker browser support and suppress Streamlit warnings
itsOwen- Add Chrome browser installation for Patchright in Docker - Add browser dependencies for Playwright/Patchright - Add .dockerignore for cleaner builds - Suppress Pydantic V1 warning for Python 3.14 compatibility - Suppress ScriptRunContext warnings during shutdowna6dab34 -
Clean up README and improve extraction prompt
itsOwen- Simplify README structure - Update prompt to extract ALL items from multipage content - Clarify that entry limits only apply when explicitly requested1dfdc1c -
Fix multipage scraping with captcha mode - now scrapes all pages after CAPTCHA solved
itsOwene0f5917 -
Update Dockerfile to Python 3.12 and remove redundant installs
itsOwen2317670 -
Clean up codebase and update dependencies to latest versions
itsOwenCode cleanup: - Remove unused imports (lru_cache, alru_cache, base64, os, streamlit, re, etc.) - Delete dead functions (_format_as_text, format_to_markdown, format_from_markdown) - Remove stub scraper files (html_scraper.py, json_scraper.py, mixins.py) - Remove unused utilities (proxy_manager.py, markdown_formatter.py) - Consolidate duplicate extract_url and get_website_name functions - Update scrapers __init__.py to remove deleted imports - Rename "Conversation History" to "CyberScraper-2077" in UI - Remove "Scraping... This may take a moment" message Dependencies updated to latest versions: - streamlit 1.53.0, pandas 2.3.3, langchain 1.2.6 - openai 2.15.0, patchright 1.57.2, aiohttp 3.13.3 - All other packages updated to Jan 2026 releasesa4f5992 -
Remove .DS_Store files from tracking
itsOwen62bae53 -
Add conversational chatbot mode with on-demand data export
itsOwen- Transform from JSON-only extractor to intelligent conversational assistant - Add conversation history support for context-aware responses - Only return structured data (CSV/JSON/Excel) when explicitly requested - Add Rebecca (Cyberpunk 2077) personality to the AI - Let LLM handle greetings and chat naturally when no URL provided - Improve JSON extraction with multiple fallback methods47cb030 -
Replace Playwright with Patchright for undetected browser automation
itsOwen- Switch from playwright to patchright (undetected fork) - Add persistent context support with channel="chrome" for max stealth - Add locale and timezone_id config for fingerprint consistency - Disable custom headers/user-agent by default (creates signatures) - Use no_viewport=True to remove viewport fingerprint - Update Dockerfile and requirements.txt for patchright5910dc8 -
Update scraper with multiple improvements and fixes
itsOwen- Fix deprecated google.generativeai import, use langchain directly - Fix CAPTCHA handling: use 'load' instead of 'networkidle', reuse same page - Fix error detection for HTML content containing 'Error:' string - Increase Tor timeout to 120s for slow onion sites - Add Tor install/start instructions to error messages - Simplify Tor detection to check if port 9050 is open - Fix README URL anchors for Tor documentation - Add centralized error handler with user-friendly messages - Update models to gpt-4.1-mini and gpt-4o-mini - Truncate long website names (onion URLs) in chat history - Update Google Sheets detection to check for client_secret.json file - Reduce gap in Setup Help text - Various code refactoring and improvementse555dc3
-
Merge pull request #41 from AYastrebov/fix/update-langchain-imports
Owen SinghUnverified signatureFix deprecated langchain imports625b15a -
Fix deprecated langchain imports for compatibility with newer versions
Andrey YastrebovUnverified signatureUpdate import paths that were moved from `langchain.*` to `langchain_core.*` and `langchain_text_splitters` in recent langchain releases. This fixes ModuleNotFoundError when running the app with current langchain packages.9c54480
-
Merge pull request #40 from romanrocks4/contribute
Owen SinghUnverified signatureAdd inline comments.7cfa721 -
Add inline comments.
romanrocks4f6d990b
-
removed non working email
Owen SinghUnverified signatureremoved old email3dcf593
-
Update README.md
Owen SinghUnverified signature264426e -
Update README.md
Owen SinghUnverified signature83973fc -
Update README.md
Owen SinghUnverified signature90b0772
-
Update README.md
Owen SinghUnverified signaturec766781
-
Update README.md
Owen SinghUnverified signaturefc61439 -
Update README.md
Owen SinghUnverified signaturea9312bc -
Update README.md
Owen SinghUnverified signature05e5589
-
Update README.md
Owen SinghUnverified signaturea9a9d45
-
Update README.md
Owen SinghUnverified signature7dffe13
-
global tor issue fixed
itsOwen02752bd
-
Update issue templates
Owen SinghUnverified signaturef20fb86 -
Create CODE_OF_CONDUCT.md
Owen SinghUnverified signature01f83a2 -
Create SECURITY.md
Owen SinghUnverified signature610eca5 -
Create CONTRIBUTING.md
Owen SinghUnverified signaturec381a65
-
readme fix
itsOwen4dca1c6 -
Scrape Tor/Onion Links
itsOwene19fad5
-
Merge pull request #21 from scattter/fix/ollama-model-init-error
Owen SinghUnverified signaturefix ollama model init errore3c19a6 -
fix ollama model init error
2cb4206
-
docker issue fixed
itsOwen1008610
-
readme fix
Owen SinghUnverified signature70c6f6e