FLaNK-AIM Weekly for 06 May 2024

06-May-2024

Apache NiFi, Apache Kafka, Apache Flink, LLM, Generative AI

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

FLaNK / KNIFe AI / FLaNK-AIM Weekly

http://knifeai.org/

Tim Spann @PaaSDev

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://www.cloudera.com/campaign/apache-nifi-for-dummies.html

https://ossinsight.io/analyze/tspannhw

CODE + COMMUNITY

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

http://www.meetup.com/futureofdata-princeton/

https://www.meetup.com/futureofdata-newyork/

https://www.meetup.com/futureofdata-philadelphia/

**This is Issue #136 **

https://github.com/tspannhw/FLiPStackWeekly

https://www.cloudera.com/solutions/dim-developer.html

Articles

https://medium.com/@tspann/building-a-milvus-connector-for-nifi-34372cb3c7fa

Small Language Models (SML) for the Win

Maybe Four Smaller Open “LLM”s are Better Than One?

Searching Slack from Apache NiFi

Events, Streams, Flows and Maps

Storing Meetup User Data as Events

Real-Time in Boston: Part 1

NSA AI Security https://www.nsa.gov/Press-Room/Press-Releases-Statements/Press-Release-View/Article/3741371/nsa-publishes-guidance-for-strengthening-ai-system-security/

https://zilliz.com/learn/Sentence-Transformers-for-Long-Form-Text

https://zilliz.com/zilliz-cloud-pipelines

https://huggingface.co/BAAI/bge-large-en-v1.5

https://github.com/cloudevents/sdk-python/blob/main/samples/http-json-cloudevents/client.py

https://medium.com/@tspann/building-a-milvus-connector-for-nifi-34372cb3c7fa

https://docs.cloudera.com/machine-learning/cloud/release-notes/topics/ml-whats-new.html#ml_workspace_resource_tags

https://zilliz.com/blog/finding-right-fit-embedding-support-for-RAG-in-zilliz-cloud-pipelines-from-voyageai-openai-and-oss

https://hazelcast.com/glossary/streaming-data/

https://postgres.ai/blog/20220525-common-db-schema-change-mistakes

https://medium.com/cloudera-inc/consuming-rss-feeds-from-flink-sql-eaf33c1a5a23

https://medium.com/cloudera-inc/adding-generative-ai-results-to-sql-streams-513e1fd2a6af

https://www.linuxfoundation.org/press/lf-ai-data-foundation-launches-open-platform-for-enterprise-ai-opea

https://blog.mozilla.ai/local-llm-as-judge-evaluation-with-lm-buddy-prometheus-and-llamafile/

https://blog.mozilla.ai/open-source-in-the-age-of-llms/

https://www.pinecone.io/learn/structured-data/

https://medium.com/@stoty/a-bug-for-ages-fixing-time-zone-handling-in-apache-phoenix-e9934d7acd80

https://www.geeknarrator.com/blog/stream-processing/stream-processing-concepts

https://blog.cloudera.com/setting-up-and-getting-started-with-clouderas-new-sql-ai-assistant/

https://thenewstack.io/how-to-cure-llm-weaknesses-with-vector-databases/

https://dev.to/zilliz/exploring-bge-m3-and-splade-two-machine-learning-models-for-generating-sparse-embeddings-22p1

https://zilliz.com/learn/transforming-pdfs-into-insights-vectorizing-and-ingesting-with-zilliz-cloud-pipelines

https://zilliz.com/blog/how-to-evaluate-and-optimize-performance-of-milvus-storage

https://datavolo.io/2024/05/apache-nifi-designed-for-extension-at-scale/

Videos

Generative AI with Milvus

Four Models at Once

Search Slack

MBTA Transit Live with LLM

Events, Streams, Maps with Irish Rail

FLaNK AI Channel

Data in Motion - How To Be a Streaming Engineer

NiFi

Slides

https://www.slideshare.net/slideshow/generative-ai-on-enterprise-cloud-with-nifi-and-milvus/267678399

Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines

GitHub - tspannhw/FLaNK-Milvus: Flink - NiFi - Kafka - Milvus - Zilliz -Cloudera

Building a Milvus Connector For NiFi

Generative AI on Enterprise Cloud with NiFi and Milvus

Events

May 8–9, 2024: Data Summit 2024. Boston, MA. https://www.dbta.com/DataSummit/2024/default.aspx https://www.dbta.com/DataSummit/2024/Timothy-Spann.aspx

https://twitter.com/DBTADataSummit/status/1778393005646397636

May 21, 2024: Gen AI and Beyond with NiFi 2.0. Virtual.

May 30, 2024: Conf42: Machine learning https://www.conf42.com/Machine_Learning_2024_Tim_Spann_enriching_generative_events

June 12, 2024: Budapest Data + ML Forum. Virtual.

https://budapestml.hu/2024/en/speakers/

June 20, 2024: AI Camp Meetup. NYC.

Sept 24, 2024: JConf.Dev. Dallas.

https://2024.jconf.dev/session/598816

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

Nov 19, 2024: XtremePython. Online.

https://xtremepython.dev/2024/

Cloudera Events

https://www.cloudera.com/about/events.html

https://www.cloudera.com/events/cloudera-now-cdp.html?internal_keyplay=ALL&internal_campaign=FY25-Q1-AMER-WS-Cloudera-Now-Events-Page-P06&cid=701Hr000000tW6qIAE&internal_link=p06

More Events: https://www.linkedin.com/pulse/schedule-2024-tim-spann--y4coe

Code

• https://github.com/tspannhw/FLaNK-python-processors
• https://github.com/tspannhw/FLANKAI-Boston
• https://github.com/tspannhw/FLaNK-IrelandTransit

Models

• https://github.com/ollama/ollama/releases/tag/v0.1.33-rc5
• https://github.com/vikhyat/moondream
• https://huggingface.co/apple/OpenELM-3B-Instruct
• https://huggingface.co/namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA

Tools

• https://krasjet.com/voice/pdf.tocgen/
• https://github.com/rcoh/angle-grinder
• https://www.brandur.org/logfmt
• https://iss.matteason.co.uk/
• https://echarts.apache.org/handbook/en/concepts/dataset
• https://www.chartjs.org/docs/latest/getting-started/usage.html
• https://js.cytoscape.org/
• https://github.com/apexcharts/apexcharts.js/
• https://github.com/andrewcourtice/ripl
• https://unovis.dev/gallery
• https://vega.github.io/vega-lite/
• https://observablehq.com/@observablehq/plot-gallery
• https://www.tremor.so/
• https://os-world.github.io/
• https://ollama.com/library/moondream
• https://forums.developer.nvidia.com/t/introducing-ollama-support-for-jetson-devices/289333
• https://www.youtube.com/@FLaNK-Stack
• https://github.com/kaytu-io/kaytu
• https://github.com/hashhar/jsonschema2sql
• https://threlte.xyz/
• https://github.com/kingjulio8238/memary
• https://zilliz.com/learn/how-to-enhance-the-performance-of-your-rag-pipeline
• https://medium.com/cloudera-inc/consuming-rss-feeds-from-flink-sql-eaf33c1a5a23
• https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1
• https://github.com/JetBrains/xodus
• https://github.com/towhee-io/examples/tree/main/nlp/text_search
• https://github.com/openvinotoolkit/openvino_notebooks/tree/recipes/recipes
• https://github.com/zilliztech/kafka-connect-milvus
• https://github.com/timeplus-io/proton/tree/develop/examples/real-time-ai
• https://zilliz.com/what-is-gptcache
• https://github.com/zilliztech/VectorDBBench
• https://github.com/zilliztech/milvus_cli
• https://github.com/towhee-io/examples/blob/main/nlp/text_search/search_article_in_medium.ipynb
• https://seeed-studio.github.io/SenseCraft-Web-Toolkit/#/setup/process
• https://github.com/McGill-NLP/webllama
• https://github.com/Mozilla-Ocho/llamafile
• https://prometheus-eval.github.io/prometheus
• https://github.com/mozilla-ai/lm-buddy
• https://github.com/databonsai/databonsai
• https://github.com/cohere-ai/cohere-toolkit
• https://github.com/InternLM/lmdeploy
• https://github.com/TagStudioDev/TagStudio
• https://github.com/Axorax/tkforge
• https://github.com/hiyouga/LLaMA-Factory
• https://pub.towardsai.net/rag-2-0-finally-getting-rag-right-f74d0194a720
• https://github.com/brettdidonato/trendr-bot
• https://github.com/cloudera/CML_AMP_Intelligent-QA-Chatbot-with-NiFi-Pinecone-and-Llama2
• https://github.com/pydantic/logfire
• https://www.terminal.shop/
• https://github.com/penpot
• https://github.com/ytang07/ai_agents_cookbooks/tree/main/langchain
• https://voxel51.com/fiftyone/
• https://huggingface.co/apple/OpenELM-450M-Instruct?library=true
• https://zilliz.com/learn/effortless-ai-workflows-a-beginners-guide-to-hugging-face-and-pymilvus
• https://github.com/NVlabs/DoRA
• https://github.com/Blealtan/efficient-kan
• https://github.com/habuma/spring-ai-examples/tree/main/vector-store-loader
• https://github.com/eureka-research/DrEureka
• https://haystack.deepset.ai/integrations/milvus-document-store
• https://github.com/TencentARC/InstantMesh
• https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B
• https://kai-waehner.medium.com/genai-demo-with-kafka-flink-langchain-and-openai-8c9b7263770a
• https://medium.com/@amanatulla1606/llm-web-scraping-with-scrapegraphai-a-breakthrough-in-data-extraction-d6596b282b4d
• https://news.mit.edu/2024/mit-faculty-instructors-students-experiment-generative-ai-teaching-learning-0429
• https://zilliz.com/blog/spring-ai-and-milvus-using-milvus-as-spring-ai-vector-store

Cool Tool

Convert Spark SQL to Trino SQL https://github.com/linkedin/coral

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

FLaNK-AIM with LLAMA 3