trulens
flyte
trulens | flyte | |
---|---|---|
14 | 31 | |
1,629 | 4,779 | |
7.9% | 2.3% | |
9.8 | 9.8 | |
4 days ago | 4 days ago | |
Jupyter Notebook | Go | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
trulens
-
Why Vector Compression Matters
Retrieval using a single vector is called dense passage retrieval (DPR), because an entire passage (dozens to hundreds of tokens) is encoded as a single vector. ColBERT instead encodes a vector-per-token, where each vector is influenced by surrounding context. This leads to meaningfully better results; for example, here’s ColBERT running on Astra DB compared to DPR using openai-v3-small vectors, compared with TruLens for the Braintrust Coda Help Desk data set. ColBERT easily beats DPR at correctness, context relevance, and groundedness.
- FLaNK AI Weekly 18 March 2024
-
First 15 Open Source Advent projects
12. TruLens by TruEra | Github | tutorial
-
trulens VS agenta - a user suggested alternative
2 projects | 22 Nov 2023
-
How are generative AI companies monitoring their systems in production?
3) Hallucination is probably the biggest problem we solve for. To do evals for hallucination, we typically see our users use a combination of groundedness (does the context support the LLM response) and context relevance (is the retrieved context relevant to the query). There's also a bunch more for the evaluations you mentioned (moderation models, sentiment, usefulness, etc.) and it's pretty easy to add custom evals.
Also - my hot take is that gpt-3.5 is good enough for evals (sometimes better) than gpt-4 if you give the LLM enough instructions on how to do the eval.
website: https://www.trulens.org/
- FLaNK Stack Weekly 28 August 2023
-
[P] TruLens-Eval is an open source project for eval & tracking LLM experiments.
The team at TruEra recently released an open source project for evaluation & tracking of LLM applications called TruLens-Eval. We’ve specifically targeted retrieval-augmented QA as a core use case and so far we’ve seen it used for comparing different models and parameters, prompts, vector-db configurations and query planning strategies. I’d love to get your feedback on it.
- [D] Hardest thing about building with LLMs?
- Stop Evaluating LLMs on Vibes
- OSS library for attribution and interpretation methods for deep nets
flyte
-
First 15 Open Source Advent projects
9. Flyte by Union AI | Github | tutorial
-
Flyte 1.10: Self-hosted solution to build production-grade data and ML pipelines; now ships with monorepo, new agents and sensors, eager workflows and more 🚀 (4.1k stars on GitHub)
GitHub: https://github.com/flyteorg/flyte
-
Flyte: Open-source orchestrator for building production-grade ML pipelines
This is actually but a link to Flyte, this is a link to the documentation for the Flyte integration in LangChain, a separate product.
Flyte's homepage is https://flyte.org/
- Flyte: Advanced workflow orchestration alternative to Apache Airflow
-
Orchestration: Thoughts on Dagster, Airflow and Prefect?
Anyone tried Flyte?
-
Flyte 1.6.0: Self-hosted solution to build production-grade data and ML pipelines; now ships with PyTorch elastic training, image specification without dockerfile, enhanced task execution insights and more 🚀 (3.4k stars on GitHub)
Website: https://flyte.org/
-
Flyte(v1.5.0) - Self-hosted solution to build production-grade data and ML pipelines; now ships with streaming support, pod templates, partial tasks and more 🚀 (3.2k stars on GitHub)
Flyte is an open source orchestration tool for managing the workflow of machine learning and AI projects. It runs on top of Kubernetes.
- Flyte: Open-Source Kubernetes-Native ML Orchestrator Implemented in Go
-
What is MLOps and how to get started? | MLOps series | Deploying ML in production
I have a question though, what is your opinion on https://flyte.org. My pipeline uses this and it’ll be interesting to get your perspectives on it’s capabilities.
-
Github alternative for ML?
Have you looked at flyte.org. It aims to bring "versioning", "compute" and "reproducibility" together in one package.
What are some alternatives?
langfuse - 🪢 Open source LLM engineering platform: Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
metaflow - :rocket: Build and manage real-life ML, AI, and data science projects with ease!
shapash - 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
argo - Workflow Engine for Kubernetes
probability - Probabilistic reasoning and statistical analysis in TensorFlow
temporal - Temporal service
LIME - Tutorial notebooks on explainable Machine Learning with LIME (Original work: https://arxiv.org/abs/1602.04938)
kubeflow - Machine Learning Toolkit for Kubernetes
embedchain - Personalizing LLM Responses
Celery-Kubernetes-Operator - An operator to manage celery clusters on Kubernetes (Work in Progress)
machine_learning_basics - Plain python implementations of basic machine learning algorithms
Kedro - Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.