AIM Weekly for 24 June 2024

See: https://dev.to/tspannhw/aim-weekly-for-24-june-2024-4o5l

24-June-2024

Tim Spann @PaaSDev

Milvus - Towhee - Attu - Feder - GPTCache - VectorDB Bench

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

https://github.com/milvus-io/milvus?utm_source=partner&utm_medium=referral&utm_campaign=2024_newsletter_tspann-ai-newsletters_external

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.

https://www.meetup.com/unstructured-data-meetup-new-york/?utm_source=partner&utm_medium=referral&utm_campaign=2024_newsletter_tspann-ai-newsletters_external

This is Issue #143

Join me:

July 25, 2024 5:30 to 8:30 PM in NYC @ Cloudera 101 5th Ave · New York, NY Cloudera office - 8th Floor https://www.meetup.com/unstructured-data-meetup-new-york/events/301720478/

New Releases

Hardware

Raspberry Pi AI Kit

Upcoming

July 18 - Meetup - AI Camp NYC @ Microsoft Reactor July 25 - Meetup @ Cloudera NYC August 13 - Meetup @ Hudson Yards NYC

Cool Stuff

Look at this cool MAD Map for Real-Time Python with Milvus listed https://bytewax.io/blog/bytewax-mad-map

Token price of most the major models https://github.com/AgentOps-AI/tokencost

Launch into PyTorch Lightning Studio https://lightning.ai/badge

Low Code AutoGen Studio https://github.com/microsoft/autogen/tree/main/samples/apps/autogen-studio

Another great work by Victor D!

A really great article by Rakuten on Milvus https://symphony.rakuten.com/blog/rakuten-symphony-makes-llms-breakthrough-with-ipv6-innovation

Milvus has fast insert https://zilliz.com/blog/clear-up-misconceptions-about-data-insertion-speed-in-milvus

Articles

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

https://medium.com/@tspann/summer-ai-camp-in-times-square-20-june-2024-report-842543bc587b

https://medium.com/@tspann/unstructured-data-processing-with-a-raspberry-pi-ai-kit-c959dd7fff47

https://medium.com/@tspann/startup-grind-princeton-report-for-18-june-2024-ed7b9928a725

https://medium.com/@tspann/not-every-field-is-just-text-numbers-or-vectors-976231e90e4d

https://developer.nvidia.com/blog/tips-for-building-a-rag-pipeline-with-nvidia-ai-langchain-ai-endpoints/?dysig_tid=00412d783bcd4bf3acd6c76be95c699f

https://github.com/nicanorflavier/spf-dkim-dmarc-simplified

https://www.infoq.com/news/2024/06/meta-llm-megalodon

https://github.com/mistralai/cookbook/blob/main/third_party/LlamaIndex/ollama_mistral_llamaindex.ipynb

https://www.decube.io/post/ingest-data-vector-database-milvus?utm_source=partner&utm_medium=referral&utm_campaign=2024_newsletter_tspann-ai-newsletters_external

https://medium.com/@zilliz_learn/crafting-superior-rag-for-code-intensive-texts-with-zilliz-cloud-pipelines-and-voyage-ai-49cba221f76e

https://medium.datadriveninvestor.com/llmops-monitoring-for-agent-ai-platforms-dee474b2877f

https://medium.com/sourcescribes/7-open-source-tools-you-will-find-very-useful-06eddb20518b

https://medium.com/ubiai-nlp/fine-tuning-mistral-7b-for-named-entity-recognition-ner-bbb96af918d3

https://thenewstack.io/generate-learned-sparse-embeddings-with-bge-m3/

https://thenewstack.io/install-ollama-ai-on-ubuntu-linux-to-use-llms-on-your-own-machine/?utm_source=

https://medium.com/@enrico.randellini/exploring-microsoft-phi3-vision-language-model-as-ocr-for-document-data-extraction-c269f7694d62

https://ai.plainenglish.io/top-9-open-source-text-to-speech-tts-models-7ac572cfc7d4

https://augmentedstartups.medium.com/yolov10-vs-yolov9-vs-yolov8-8a3c3d596b6f

Videos

Unstructured Data Processing with RPI 5 AI Kit https://www.youtube.com/watch?v=tZFJ1DDkD1Q

Using JSON Fields with Milvus https://www.youtube.com/watch?v=HP5L3Hr6Mt8

DSS ML Talk https://www.youtube.com/watch?v=t17Ga4l5gvo

RPI Videos https://www.youtube.com/watch?v=lrLAjqWsYjU https://www.youtube.com/watch?v=GgxLWPNLf9I https://www.youtube.com/watch?v=OMy7ggCVeEY https://www.youtube.com/watch?v=gRP9y3w_Ago https://www.youtube.com/watch?v=myZgzNfY08U https://www.youtube.com/watch?v=gYVbj2nLVYc https://www.youtube.com/watch?v=396ZN4T66uA https://www.youtube.com/watch?v=i_caGhsFwMM

Slides

https://www.slideshare.net/slideshow/06-20-2024-ai-camp-meetup-unstructured-data-and-vector-databases/269789268

https://www.slideshare.net/slideshow/06-18-2024-princeton-meetup-introduction-to-milvus/269765983

https://www.slideshare.net/slideshow/06-12-2024-budapestdataforum-buildingreal-timepipelineswithflank-aim/269645846

Events

Oct 27 - 29, Raleigh, NC - All Things Open https://2024.allthingsopen.org/speakers/timothy-spann

Nov 5-7, 10-12, 2024: CloudX. Online/Santa Clara. https://www.developerweek.com/cloudx/

Nov 19, 2024: XtremePython. Online. https://xtremepython.dev/2024/

Code

• https://github.com/tspannhw/AIM-MilvusLite

• https://github.com/tspannhw/AIM-NYCStreetCams

• https://github.com/tspannhw/AIM-MotorVehicleCollisions

• https://github.com/milvus-io/milvus?utm_source=partner&utm_medium=referral&utm_campaign=2024_newsletter_tspann-ai-newsletters_external

Models

• https://huggingface.co/mistralai/Codestral-22B-v0.1

Tools

• https://opensustain.tech/

• https://amphi.ai/

• https://omid.dev/2024/06/19/advanced-shell-scripting-techniques-automating-complex-tasks-with-bash/

• https://blog.christianperone.com/2023/06/appreciating-llms-data-pipelines/

• https://github.com/Canner/wren-engine

• https://github.com/Helicone/helicone

• https://github.com/BasedHardware/OpenGlass

• https://www.firecrawl.dev/

• https://github.com/mendableai/firecrawl

• https://github.com/OpenBMB/MiniCPM/blob/main/README-en.md

• https://github.com/nomic-ai/nomic

• https://github.com/AiuniAI/Unique3D

• https://github.com/mayneyao/eidos

• https://event-driven-io.github.io/emmett/getting-started.html

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

🖥️ Videos:  [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)M