Spaces:

chrisjcc
/

fraud_model_explainability_assistant

Runtime error

App Files Files Community

Evaluation Pipeline and Langfuse Monitoring

#7

by chrisjcc - opened Jan 18

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

initial commit73ddec78

Fraud Model Explainability Assistant - Strands Agents27f4650a

Update Amazon Strands Agents SDK descriptiona960fc35

Create requirements.txtf6236324

Fixed the Gradio 6.0 compatibility issuesc60bbba1

Suppress asyncio "Invalid file descriptor" warnings in containerized environmentsd08f2ef2

Add missing import warnings16fa8bc3

add to launch ssr_mode=False77bdb144

Confluence integration would transform the fraud assistant from a demo tool into a production-ready compliance and investigation platform.bae9ca81

The fraud assistant is ready to run with Confluence integration87c817a6

Production features:77b035a9

Add a pip build wheelad817ec3

Update to confluence_ingestor-0.3.0-py3-none-any.whl version729efb4c

Try a different approach for build wheel39a338c3

Add mock Confluence pages for the 'cquisition-and-Credit-Risk' space, designed specifically to demonstrate the Fraud Model Explainability Assistant with Confluence integration.ecfbd817

Now the page titles will be displayed regardless of whether the space is newly ingested or already cached.f3d79f41

Only one requirements filef095b7d4

No PyPi install for confluence-ingestor lib yet0697233b

Remove phase phrasingae06c7d7

Add additional libraries6411d0c8

Tweaked code comment5ff387f7

Update System Prompt to improve LLM behavior75629691

Root Cause: Severe Content Truncationbf60203b

Fixed THREE critical issues:a0f7fc30

Obtain package from GitHub confluence-ingestor repo878f9cac

Try fixing import68b63fea

Create .space/config.yaml13958c3f

Migrate to Docker based space instead of Gradio7fb9f783

Add a Dockerfile to repo175b1add

Update Dockerfilef7ced4cf

Update Dockerfile13b0a31b

Remove private lib38463315

Update Dockerfile34d36dd8

GITHUB_TOKEN as a build argument77d0ad56

Update Dockerfile99cd0d70

Update Dockerfile0890467c

Update Dockerfilefa06c07a

Update README.md74f3f715

Update Dockerfile1c351162

Update Dockerfile8389a982

Update Dockerfile42fe9092

Update Dockerfile8c9db161

Update Dockerfile3ecd75e6

Quick test version (add debug)e954f40e

Update Dockerfile78b8ab65

Update Dockerfile56723fc0

The RUN stage with --mount=type=secret successfully authenticates (HTTP 200, token length 40 chars, detects releases array with length 2), extracts the tag, and prints "✅ Release found, continuing...",a264751c

Remove confluence-ingestor library5e55e89b

Use API asset URL (.assets[0].url) instead of browser_download_url - this requires authentication properly5ce5a2b0

Migrating Gradio app to Docker-based HF space1a6cb348

Update requirements.txt2b210b5c

Update README.md3ee010fd

Delete vendord9d2a083

Delete confluence_integration_example.py74401e7c

Delete confluence_integration_example_2.pybe4df709

Update app_with_confluence.pybcc08808

Refactoring App Structure (#1)db6dad60

Fix use app.py instead.2a06ef30

Made GITHUB_TOKEN variable reusabled92c3acc

You can now upload PDFs, CSVs, or images, and the agent will process them accordingly. (#2)ad75af3f

Debugging PDF uploader error7643ae06

Debugging PDF Upload Error (#3)b8c7ea09

Merge commit 'refs/pr/3' of https://huggingface.co/spaces/chrisjcc/fraud_model_explainability_assistant62db06ff

Update requirements.txt08821262

Iterate page-by-page: Instead of failing on the whole document, it now processes each page individually.ad92b4b2

Better support for docs and csv reading to provide as context (#4)0d0029d0

Add missing library (DOCX)4b6ce599

Update README.md709349ea

Integrated the SlidingWindowConversationManager into app.py.31861cb3

Default callback print log (#5)f28b6f30

Update Strands loggingfbb00e62

Update Strands loggingb87b596f

Owner Jan 18

No description provided.

Introduce Evaluation Pipeline & Langfuse Evaluation Monitoring154a24e8

chrisjcc changed pull request status to open Jan 24

chrisjcc changed pull request status to merged Jan 24

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment