AIM Weekly 17 June 2024

17-June-2024

Tim Spann @PaaSDev

Milvus — Towhee — Attu — Feder — GPTCache — VectorDB Bench

Happy Father’s Day To All! Also Happy Flag Day to Those in the United States.

AIM Weekly

Towhee — Attu — Milvus (Tim-Tam)

FLaNK — FLiPN

With a name like that I am not sure how I don’t add that to my group.

SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search https://proceedings.neurips.cc/paper/2021/hash/299dc35e747eb77177d9cea10a802da2-Abstract.html

Congrats to Milvus https://www.dbta.com/Editorial/Trends-and-Applications/DBTA-100-2024-The-Companies-That-Matter-Most-in-Data-164289.aspx

GitHub - milvus-io/milvus: A cloud-native vector database, storage for next generation AI…

https://pebble.is/PaaSDev

https://vimeo.com/flankstack

https://www.youtube.com/@FLaNK-Stack

https://www.threads.net/@tspannhw

https://medium.com/@tspann/subscribe

https://ossinsight.io/analyze/tspannhw

CODE + COMMUNITY

Please join my meetup group NJ/NYC/Philly/Virtual.

Unstructured Data Meetup New York | Meetup

This is Issue #142

New Releases

Milvus Release 2.4.4

Release Notes | Milvus Documentation

Release date: May 31, 2024

It includes a critical bug fix, so if you use bulk insert definitely upgrade now. Also some compilation updates for other platforms.

Release milvus-2.4.4 · milvus-io/milvus

Hardware

BeagleY®-AI

Upcoming

Summary of the Last Awesome Meetup https://www.linkedin.com/feed/update/urn:li:activity:7202803256891248640/

Cool Stuff

TIMM (Pytorch Image Models) https://timm.fast.ai/

Ben has gone deep on this article on the Future of Vector Search linking to some of Milvus & Zilliz’ scalability and horizontal scalability deep description and highlighting a lot of interesting things going on.

The Future of Vector Search

See: https://zilliz.com/learn/scaling-vector-databases-to-meet-enterprise-demands?utm_source=tim

Articles

There’s a lot of cool stuff with Milvus and new models, techniques, libraries and use cases.

Not Every Field is Just Text, Numbers or Vectors

Unstructured Street Data in New York

Tech Week — Soft Meetup Debut — June 2024

Shining Some Light on The New Milvus Lite

Using Vector Search to Better Understand Computer Vision Data

https://www.infoq.com/presentations/ai-monopoly/

https://python.plainenglish.io/claude-3-the-king-of-data-extraction-f06ad161aabf

https://towardsdatascience.com/rag-vs-finetuning-which-is-the-best-tool-to-boost-your-llm-application-94654b1eaba7

https://medium.com/@zilliz_learn/using-vector-search-to-better-understand-computer-vision-data-08e137df9c6c

https://zilliz.com/blog/exploring-multimodal-embeddings-with-fiftyone-and-milvus

https://medium.com/aiguys/yolov9-new-object-detection-king-6fc97b93dc9a

https://www.linkedin.com/pulse/nifi-retrieval-augmented-generation-chris-gambino-gfsec/?trackingId=OliHLynzQEKic3SgAznO5w%3D%3D

https://ml.dssconf.pl/

https://medium.com/@zilliz_learn/milvus-reference-architectures-e30a27c9f3c2

https://docs.openlit.io/latest/integrations/milvus

https://builtin.com/articles/real-time-data-ai

https://medium.com/@zilliz_learn/image-embeddings-for-enhanced-image-search-an-in-depth-explainer-6831859bedf0

https://medium.com/@zilliz_learn/semantic-search-with-milvus-and-openai-32573de80307

https://medium.com/@zilliz_learn/how-to-detect-and-correct-logical-fallacies-from-genai-models-3e4a9852d2ef

https://gradientflow.substack.com/p/the-future-of-vector-search

https://medium.com/vector-database/introducing-pymilvus-integration-with-embedding-models-a82f10d516ea

https://medium.com/@zilliz_learn/local-agentic-rag-with-langgraph-and-llama-3-6c962979821f

https://blogs.nvidia.com/blog/nemotron-4-synthetic-data-generation-llm-training/?utm_source=tim

https://medium.com/walmartglobaltech/reliably-processing-trillions-of-kafka-messages-per-day-23494f553ef9

https://jack-vanlightly.com/blog/2024/6/10/a-cost-analysis-of-replication-vs-s3-express-one-zone-in-transactional-data-systems?utm_source=tim

DSPy — Getting interesting https://medium.com/@sandyeep70/the-decline-of-traditional-prompt-engineering-and-the-rise-of-dspy-b27b9a5adc45

Why How + Milvus Lite https://medium.com/enterprise-rag/kickstart-your-genai-applications-with-milvus-lite-and-whyhow-ais-open-source-rule-based-retrieval-70873c7576f1

Voyage AI Embeddings and Rerankers for Search and RAG

Voyage AI Embeddings and Rerankers for Search and RAG

Evaluate RAG Apps

How to Evaluate RAG Applications

Videos

Using JSON Fields with Milvus

Street Cams + Milvus

Unstructured Street Data in New York

Conf42: ML: Emerging GenAI

Generative AI with Milvus

SF Unstructured Meetup — 03 June 2024

Fueling AI with Airbyte

Fueling AI with Great Data

Milvus Webinar

AI Generated Videos

Slides

Generative AI on Enterprise Cloud with NiFi and Milvus

06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Data and AI

{{ 'metatags.title_user_account' | translate }}

DSSML24_tspann_CodelessGenerativeAIPipelines

06-12-2024-BudapestDataForum-BuildingReal-timePipelineswithFLaNK AIM

Events

June 18, 2024: Princeton Meetup

Applied Generative AI Innovators and Entrepreneurs, 18 Jun 2024, 06:30 PM, Tue, Jun 18, 2024, 6:30…

GenAI Gathering | Startup Grind

June 20, 2024: AI Camp Meetup. NYC.

Affiliate Event: AI Camp | New York | AI, LLMs, ML and Data Meetup, Thu, Jun 20, 2024, 5:30 PM |…

Nov 5–7, 10–12, 2024: CloudX. Online/Santa Clara.

https://www.developerweek.com/cloudx/

Nov 19, 2024: XtremePython. Online.

XtremePython 2024 Online Conference

Code

• https://github.com/tspannhw/FLaNK-python-processors
• https://github.com/tspannhw/AIM-MilvusLite
• https://github.com/tspannhw/AIM-NYCStreetCams
• https://github.com/stephen37/Milvus_demo/tree/main/llama_index_demos
• https://github.com/tspannhw/AIM-MotorVehicleCollisions

Models

• https://huggingface.co/mistralai/Codestral-22B-v0.1
• https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1
• https://www.mixedbread.ai/blog/mxbai-embed-large-v1
• https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
• https://huggingface.co/nvidia/Nemotron-4-340B-Reward
• https://huggingface.co/spaces/allenai/reward-bench

Tools

• https://github.com/verazuo/jailbreak_llms
• https://github.com/open-webui/open-webui
• https://datafusion.apache.org/user-guide/example-usage.html
• https://github.com/timeseries/qstudio
• https://github.com/redotvideo/revideo
• https://github.com/coqui-ai/TTS
• https://flameshot.org/
• https://github.com/dflib/dflib
• https://valentinaalto.medium.com/rag-with-phi-3-medium-as-a-model-as-a-service-from-azure-model-catalog-62e1411948f3
• https://github.com/iyaja/llama-fs
• https://github.com/airbnb/chronon?
• https://huggingface.co/stabilityai/stable-audio-open-1.0
• https://github.com/keylase/nvidia-patch
• https://github.com/livekit/livekit
• https://github.com/1943time/bluestone
• https://litellm.vercel.app/docs/simple_proxy
• https://github.com/cohere-ai/cohere-toolkit
• https://github.com/lavague-ai/LaVague
• https://contrib.rocks/preview?repo=milvus-io%2Fmilvus
• https://github.com/mrHeavenli/akkufetch
• https://github.com/visual-layer/fastdup
• https://github.com/fastfetch-cli/fastfetch
• https://github.com/allenai/PlaSma
• https://github.com/letmutex/htmd
• https://github.com/rossant/collatepdf
• https://github.com/milvus-io/milvus-haystack

Cool

Let’s do the Time Sync Again

milvus/docs/design_docs/20211215-milvus_timesync.md at master · milvus-io/milvus

© 2020–2024 Tim Spann https://www.youtube.com/@FLaNK-Stack

🎥 Playlist:  Unstructured Data Meetup  [https://www.meetup.com/unstructured-data-bay-area/events/](https://www.meetup.com/unstructured-data-bay-area/events/)
🖥️ Website:  [https://www.youtube.com/@MilvusVectorDatabase/videos](https://www.youtube.com/@MilvusVectorDatabase/videos)
X Twitter -   / milvusio  [https://x.com/milvusio](https://x.com/milvusio)
🔗 Linkedin:  / zilliz  [https://www.linkedin.com/company/zilliz/](https://www.linkedin.com/company/zilliz/)
😺 GitHub: [https://github.com/milvus-io/milvus](https://github.com/milvus-io/milvus)
🦾 Invitation to join discord:   / discord  [https://discord.com/invite/FjCMmaJng6](https://discord.com/invite/FjCMmaJng6)