Uptrain

Latest version: v0.7.1

Safety actively analyzes 685670 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 3 of 10

0.6.5.post2

What's Changed
* Fix checkset run for managed user by ashish-1600 in https://github.com/uptrain-ai/uptrain/pull/572
* Fix Custom Prompt Eval by ashish-1600 in https://github.com/uptrain-ai/uptrain/pull/573

**Full Changelog**: https://github.com/uptrain-ai/uptrain/compare/v0.6.5.post1...v0.6.5.post2

0.6.5.post1

What's Changed
* Fix response matching operator by sourabhagr in https://github.com/uptrain-ai/uptrain/pull/570

**Full Changelog**: https://github.com/uptrain-ai/uptrain/compare/v0.6.5...v0.6.5.post1

0.6.5

Updated dependencies

0.6.4

All New User Interface
* **Dashboard**
- The new No-Code dashboard allows you to run evaluations without writing any code
- You can visualize these results locally by running the dashboard on your system

New Operators

Introducing three new operators that fit right into your RAG pipelines.

Query Enhancement Operators
* **Sub Query Completeness**
- See how well the sub-queries cover the main question

Contextual Operators
* **Context Reranking**
- Check whether the reranking improved the order of your documents
* **Context Conciseness**
- Check if a part of your context is as good as the original context to answer your query

Integrations

API Integrations
* **Mistral API Integration**
- Use the up-and-coming Mistral LLMs to perform your evaluations.

* **Langfuse Integration**
- View traces, analyse use cases and user segments while evaluating your LLMs

0.6.3

0.6.2

Page 3 of 10

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.