19-August-2024

Tim Spann @PaaSDev
Milvus - Towhee - Attu - Feder - GPTCache - VectorDB Bench

AIM Weekly (Towhee - Attu - Milvus (Tim-Tam))

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

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

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 #151

Join us at the next meetup in September.

Our Best Friends

https://dev.to/chrischurilo/milvus-adventures-august-14-2024-27k3

Webinar Coming

https://zilliz.com/event/challenges-in-structured-doc-data-extraction-at-scale-with-llms

Tutorials

https://github.com/milvus-io/bootcamp/tree/master/bootcamp/tutorials/quickstart/apps/multimodal_rag_with_milvus

https://zilliz.com/learn/faiss

https://zilliz.com/learn/introduction-to-natural-language-processing-tokens-ngrams-bag-of-words-models

https://zilliz.com/learn/Neural-Networks-and-Embeddings-for-Language-Models

https://zilliz.com/learn/sparse-and-dense-embeddings

https://zilliz.com/learn/enhancing-information-retrieval-learned-sparse-embeddings

https://zilliz.com/learn/bge-m3-and-splade-two-machine-learning-models-for-generating-sparse-embeddings

https://zilliz.com/learn/comparing-splade-sparse-vectors-with-bm25

https://zilliz.com/learn/build-multimodal-rag-gemini-bge-m3-milvus-langchain

https://zilliz.com/blog/multimodal-RAG-with-CLIP-Llama3-and-milvus

https://zilliz.com/learn/multimodal-RAG

https://zilliz.com/learn/exploring-openai-clip-the-future-of-multimodal-ai-learning

https://zilliz.com/blog/build-better-multimodal-rag-pipelines-with-fiftyone-llamaindex-and-milvus

https://zilliz.com/learn/explore-colbert-token-level-embedding-and-ranking-model-for-similarity-search

https://zilliz.com/learn/A-Beginner-Guide-to-Natural-Language-Processing

https://zilliz.com/learn/nlp-technologies-in-deep-learning

https://zilliz.com/learn/popular-datasets-for-natural-language-processing

https://zilliz.com/learn/top-10-natural-language-processing-tools-and-platforms

https://zilliz.com/learn/introduction-to-natural-language-processing-tokens-ngrams-bag-of-words-models

https://zilliz.com/learn/top-5-nlp-applications

https://zilliz.com/learn/7-nlp-models

https://zilliz.com/learn/NLP-essentials-understanding-transformers-in-AI

https://zilliz.com/learn/Neural-Networks-and-Embeddings-for-Language-Models

https://zilliz.com/learn/large-language-models-and-search

https://zilliz.com/glossary/large-language-models-(llms)

https://zilliz.com/learn/top-llms-2024

https://zilliz.com/glossary/prompt-as-code-(prompt-engineering)

https://zilliz.com/blog/enhancing-chatgpt-intelligence-efficiency-langchain-milvus

https://zilliz.com/learn/guide-to-using-openai-tect-embedding-models

https://zilliz.com/learn/NLP-and-Vector%20Databases-Creating-a-Synergy-for-Advanced-Processing

Cool Stuff

https://milvus.io/docs/integrate_with_camel.md

https://milvus.io/docs/integrate_with_dspy.md

https://milvus.io/docs/integrate_with_airbyte.md

https://build.nvidia.com/nvidia/radtts-hifigan-tts

RagChecker https://arxiv.org/pdf/2408.08067

Articles

What's in the Air Tonight, Mr. Milvus. (Air Quality + Vector Database + RAG)
https://medium.com/@tspann/whats-in-the-air-tonight-mr-milvus-fbd42f06e482

AI and Vectors - Meetup Report
https://medium.com/@tspann/ai-and-vectors-in-the-sky-f28297c01546

AI Camp - 15 August 2024 Report
https://medium.com/@tspann/report-15-august-2025-ai-camp-45e2b5d87838

Milvus - The Unstructured Olympics of the Mind? AI? Data?
https://medium.com/@tspann/milvus-the-unstructured-olympics-of-the-mind-ai-data-b08ee4ba8c33

From Edge to the Cloud and Back Again
https://medium.com/@tspann/from-the-edge-to-the-cloud-and-back-again-01095e95a783

Milvus on EKS
https://milvus.io/blog/how-to-deploy-open-source-milvus-vector-database-on-amazon-eks.md

Milvus with NVIDIA for Retail Rag
https://resources.nvidia.com/en-us-llm-retail-shopping-advisor/retail-shopping-advisor-tech-brief?ncid=no-ncid

Work Flows Generative AI
https://docs.nvidia.com/ai-enterprise/workflows-generative-ai/0.1.0/technical-brief.html#rag-tech-brief

Landscape of Gen AI Ecosystem Beyond LLMs and Vector Databases
https://zilliz.com/blog/landscape-of-gen-ai-ecosystem-beyond-llms-and-vector-databases

What is Information Retrieval?
https://zilliz.com/learn/what-is-information-retrieval

NVIDIA Nemo Curator
https://developer.nvidia.com/blog/curating-custom-datasets-for-llm-parameter-efficient-fine-tuning-with-nvidia-nemo-curator/?

Evaluating LLM Conversations
https://zilliz.com/learn/streamlined-approach-to-evaluating-llm-conversations

Pokeman Embeddings
https://minimaxir.com/2024/06/pokemon-embeddings/

LLM Evaluation
https://www.linkedin.com/posts/the-milvus-project_llm-evaluation-demo-activity-7229240307396059138-ntvN?

Agent Q
https://www.multion.ai/blog/introducing-agent-q-research-breakthrough-for-the-next-generation-of-ai-agents-with-planning-and-self-healing-capabilities

The Landscape of OS Licensing in AI
https://medium.com/@zilliz_learn/the-landscape-of-open-source-licensing-in-ai-a-primer-on-llms-and-vector-databases-5effbccbccd5

Unlocking the Secrets of GPT 4.0
https://medium.com/@zilliz_learn/unlocking-the-secrets-of-gpt-4-0-and-large-language-models-0020f61b62c2

AI Databases Ensuring the Quality of LLMs in Chatbots
https://www.opensourceforu.com/2024/08/ai-databases-ensuring-the-quality-of-llms-in-chatbots/

Bringing Confidentially to Vector Search
https://developer.nvidia.com/blog/bringing-confidentiality-to-vector-search-with-cyborg-and-rapids-cuvs/

Google ImageGen3
https://arxiv.org/pdf/2408.07009

AI Bringing Voice to Peopl
https://indianexpress.com/article/world/als-stole-his-voice-ai-retrieved-it-9516953/

InfluxDB plus Milvus
https://www.influxdata.com/blog/time-series-influxdb-vector-database/

End to End Rag with Airbyte
https://airbyte.com/tutorials/end-to-end-rag-with-airbyte-cloud-microsoft-sharepoint-and-milvus-zilliz

How to Prune
https://developer.nvidia.com/blog/how-to-prune-and-distill-llama-3-1-8b-to-an-nvidia-llama-3-1-minitron-4b-model/

Streamling the Deployment of Enterprise GenAI
https://medium.com/@zilliz_learn/streamlining-the-deployment-of-enterprise-genai-apps-with-efficient-management-of-unstructured-data-2d3b1a2f2d85

Learn GenAI
https://zilliz.com/learn/generative-ai

LangChain - Milvus
https://api.python.langchain.com/en/latest/vectorstores/langchain_community.vectorstores.milvus.Milvus.html

Hybrid Search in Rag Apps
https://ai.plainenglish.io/the-role-of-hybrid-search-in-rag-applications-29bf46b95152

Agent Based Rag
https://valentinaalto.medium.com/introducing-agent-based-rag-9b7141ae1cd7

Rag2SQL
https://medium.com/@marvin_thompson/text2sql-is-out-rag2sql-is-in-5fd160a004f0

Understanding Transformers
https://medium.com/@zilliz_learn/nlp-essentials-understanding-transformers-in-ai-29d9d973a1fc

AI Agents
https://towardsdatascience.com/ai-agents-from-concepts-to-practical-implementation-in-python-fb26789b1560

Pandas, AI, OLLAMA
https://medium.com/free-or-open-source-software/pandasai-ollama-text2sql-llama3-ask-questions-from-excel-create-visualization-in-natural-language-fbfb14ac9360

Flink, Kafka, GenAI, Real-Time
https://medium.com/@zilliz_learn/build-real-time-genai-applications-with-zilliz-cloud-and-confluent-cloud-for-apache-flink-c1922b3a1603

How to import new model from HuggingFace to Ollama
https://medium.com/@raphael.mansuy/how-to-import-a-new-model-from-huggingface-for-ollama-9dfe9ffe1a0b

LangGraph Guide
https://bhavikjikadara.medium.com/langgraph-a-comprehensive-guide-for-beginners-ef17d3dd5383

Videos

AI Camp Videos - Pose Estimation

https://www.youtube.com/watch?v=R6UXk_iDY-w

https://youtu.be/dydqDmo4LoM

https://youtu.be/uwM5Dlnk6Jk

Fun Unstructured Friday
https://youtu.be/UyMUSXdH_lg

Quick Edge Demo
https://www.loom.com/share/f779fbe49e674c9f8e42369546c61ca0

NYC Replacement Talk
https://www.youtube.com/watch?v=AuWveijqcog

Live Fun Friday with Unstructed Data Preview
https://www.youtube.com/watch?v=_jQB62uPsvc

High Speed Inference with LLAMA CPP and Vicuna
https://pub.towardsai.net/high-speed-inference-with-llama-cpp-and-vicuna-on-cpu-136d28e7887b

Unstructured Data Processing at the Edge Webinar
https://zilliz.com/event/unstructured-data-processing-from-cloud-to-edge

Unstructured Meetup SF
https://www.youtube.com/watch?v=zQASWO7_FQg

Building an Agentic RAG locally with Milvus, Ollama and Llama Agents
https://www.youtube.com/watch?v=ZO0dbk4tF_Q

Slides

https://www.slideshare.net/slideshow/08-15-2024-ai-camp-meetup-human-pose-estimation-in-real-time-utilizing-edge-ai-accelerated-hardware/271017430

https://www.slideshare.net/slideshow/08-13-2024-nyc-meetup-unstructured-data-processing-from-cloud-to-edge-milvus/270956288

https://www.slideshare.net/slideshow/milvus-vector-database-integrating-semantic-search-capabilities-with-net-and-azure/270900882

https://www.slideshare.net/slideshow/nycmeetup07-25-2024-unstructured-data-processing-from-cloud-to-edge/270502823

https://www.slideshare.net/slideshow/unstructured-data-processing-from-cloud-to-edge-webinar/270673415

https://www.slideshare.net/slideshow/implement-agentic-rag-using-claude-3-5-sonnet-llamaindex-and-milvus/271015358

Events

August 20, 2024: DotNet Conf Virtual AI
https://focus.dotnetconf.net/

September 18, 2024: Unstructured Data Meetup NYC
https://lu.ma/9o3la3gf

https://allevents.in/manhattan/unstructured-data-meetup-new-york/80001083991651?ref=smdl

October 23, 2024: Unstructured Data Meetup NYC
https://lu.ma/naqu6xrd

October 27 - 29, Raleigh, NC - All Things Open
https://2024.allthingsopen.org/speakers/timothy-spann
https://2024.allthingsopen.org/sessions/advanced-retrieval-augmented-generation-rag-techniques

October 31 - Live stream from my Halloween decorations with three 12 foot skeletons

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

November 13-15, 2024: Build Stuff. Online. Adding Generative AI to Real-Time Streaming Pipelines

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

November 21, 2024: Big Data Conference 2024 EU

https://events.pinetool.ai/3254/#sessions/108389?referrer%5Bpathname%5D=%2Fsessions&referrer%5Bsearch%5D=&referrer%5Btitle%5D=Sessions

November 21, 2024: Unstructured Data Meetup NYC
https://lu.ma/cqxuproe

December 4, 2024: Grace Hopper Celebration - Open Source - Milvus
https://ghc.anitab.org/open-source/

December 10, 2024: Unstructured Data Meetup NYC
https://lu.ma/u2ijucyv

Code

• https://github.com/tspannhw/AIM-RPIAIKit-PoseEstimation
• https://github.com/tspannhw/AIM-RPIAIKit
• https://github.com/tspannhw/AIM-NYCStreetCams
• https://github.com/tspannhw/AIM-MotorVehicleCollisions
• https://github.com/tspannhw/AIM-Milvus-KB
• https://github.com/tspannhw/AIM-Milvus-DotNet
• https://github.com/tspannhw/AIM-JetsonAGXOrin
• https://github.com/milvus-io/milvus?utm_source=partner&utm_medium=referral&utm_campaign=2024_newsletter_tspann-ai-newsletters_external

Models

• https://github.com/aiola-lab/whisper-medusa
• https://huggingface.co/blog/falconmamba
• https://medium.com/@zilliz_learn/dense-vectors-in-ai-maximizing-data-potential-in-machine-learning-cbb6268f06e3
• https://github.com/togethercomputer/MoA
• https://huggingface.co/collections/DAMO-NLP-SG/videollama-2-6669b6b6f0493188305c87ed
• https://huggingface.co/vectara/hallucination_evaluation_model
• https://github.com/ZhengPeng7/BiRefNet

Tools

• https://www.jetson-ai-lab.com/tutorial_llamaspeak.html
• https://github.com/spion/adbfs-rootless
• https://github.com/apple/ml-mdm
• https://github.com/facebookresearch/vfusion3d
• https://github.com/context-labs/mactop
• https://github.com/devoxx/DevoxxGenieIDEAPlugin
• https://github.com/libAudioFlux/audioFlux
• https://github.com/jianchang512/pyvideotrans
• https://github.com/jbunke/stipple-effect
• https://www.infoq.com/news/2024/08/nvidia-nim-huggingface/
• https://github.com/cgzirim/seek-tune
• https://huggingface.co/m42-health
• https://github.com/IntelLabs/RAGFoundry
• https://huggingface.co/blog/mlabonne/sft-llama3
• https://github.com/unslothai/unsloth
• https://github.com/mlabonne/llm-datasets
• https://github.com/hypergrok/chunkit
• https://wezfurlong.org/wezterm/index.html
• https://github.com/janelia-cellmap/dacapo
• https://github.com/DioxusLabs/blitz
• https://github.com/ComposioHQ/composio
• https://github.com/Lightning-AI/litgpt#choose-from-20-llms
• https://github.com/llmware-ai/llmware
• https://github.com/stanfordnlp/dspy/blob/main/intro.ipynb
• https://github.com/Portkey-AI/gateway
• https://github.com/Arize-ai/phoenix
• https://github.com/vllm-project/vllm
• https://github.com/langchain-ai/langgraph
• https://github.com/radulucut/cleed
• https://pyscript.net/
• https://github.com/raznem/parsera
• https://www.swebench.com/
• https://github.com/vllm-project/llm-compressor
• https://github.com/rusq/slackdump
• https://www.cursor.com/
• https://poloclub.github.io/transformer-explainer/
• https://github.com/rfinnie/blockbuster
• https://github.com/run-llama/llama_parse/blob/main/examples/multimodal/multimodal_report_generation_agent.ipynb
• https://github.com/OSU-NLP-Group/HippoRAG
• https://medium.com/top-python-libraries/top-12-creative-one-liners-for-variable-formatting-in-python-52b8f1d750c2
• https://github.com/TomWright/dasel
• https://github.com/whyhow-ai/rule-based-retrieval
• https://github.com/whyhow-ai/rule-based-retrieval/blob/main/docs/milvus.md
• https://bold-edit.com/
• https://mpv.io/
• https://github.com/deepseek-ai/DeepSeek-Prover-V1.5
• https://github.com/facebookresearch/unibench
• https://towardsdatascience.com/the-art-of-chunking-boosting-ai-performance-in-rag-architectures-acdbdb8bdc2b

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

~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~

🖥️ Videos: https://www.youtube.com/@MilvusVectorDatabase/videos

X Twitter - / milvusio https://x.com/milvusio

🔗 Linkedin: / zilliz https://www.linkedin.com/company/zilliz/

😺 GitHub: https://github.com/milvus-io/milvus

🦾 Invitation to join discord: / discord https://discord.com/invite/FjCMmaJng6

https://discord.gg/9jdMRPJb?event=1273364262710022209