- Private RAG Hosting & CostTranscription provided by Huntsville AI Transcribe It’s got some pretty heavy-handed companies associated. Locally, we got Deloitte and Booz Allen, UAH, I think Proud and Tears local. Technically some of the others like AWS and Microsoft have local offices and stuff, but I don’t know if people talking would be local. That’d be fun to do.… Read more: Private RAG Hosting & Cost
- RAG Prompt EngineeringTranscription provided by Huntsville AI Transcribe Hey, we’re recording. Here. All right. So if we do drop, I will try to, I’ll try to notice. And then stop and get back on it. So what we’re talking about tonight is prompt engineering for RAG, which is retrieval augment generation. We’ve been a foster minute. We’ve been… Read more: RAG Prompt Engineering
- Vector Storage with WeaviateTranscription provided by Huntsville AI Transcribe NOTE – we cover a lot of preliminary material about embeddings before we get to Weaviate. You may want to skip to the halfway point. TRANSCRIPT: It’s hard enough hearing myself talk on a recording. Much less also got to see myself while. Yes, so with that said, the what… Read more: Vector Storage with Weaviate
- Law & AITranscription provided by Huntsville AI Transcribe Yep. Okay, good deal. So welcome. First off, we’re thankful for Hudson Alpha for letting us use the space. It’s seriously appreciated along with their nice technology that lets us connect over Zoom. So tonight we’ve got Sam Landrood from Wimbledon, Dixon, Dickinson. I keep messing that name up in… Read more: Law & AI
- OpenAI APITranscription provided by Huntsville AI Transcribe How we got here was that we’ve been using this library, Lama CPP-Python, mostly to introduce a RAG system which is retrieval on the generation. We can go back a bit if we need to and cover what that is and what should be with it. We might if we… Read more: OpenAI API
- Llama-Cpp-PythonTranscription provided by Huntsville AI Transcribe What we have been doing, again last year, there were some things we were doing before the large language model explosion, where usually when we were running console AI, we would do demos or tutorials at schools or anything like that. We would normally use Google Colab and make it… Read more: Llama-Cpp-Python
- 2024-2 SBIR/STTR TopicsTranscription provided by Huntsville AI Transcribe Anyway, let me share and we will go through the stuff. Let’s see that. All right. So we are at our favorite site for SBIRs for DoD, SBIRs and STTRs. There are others. There’s NASA. There’s we’ve had the Department of Transportation actually has SBIR topics. This is just… Read more: 2024-2 SBIR/STTR Topics
- Choosing an Embedding Model
- Chunking with LLM SherpaTranscription provided by Huntsville AI Transcribe So what we’re talking about tonight, we’re gonna do that part. We’ve been going through this retrieval augmented generation brag kind of approach for the NASA space apps piece we’ve done a couple years ago. And as part of that, we had initially gone through and done everything with… Read more: Chunking with LLM Sherpa
- Vector Store with ChromaDB
- Retrieval Augmented Generation
- AI Breakthroughs in VideoTranscription provided by Huntsville AI Transcribe All right. So what we’re talking about today, I’m actually going to walk through this backward. Because initially, I think it was mad if you’re actually, if you’re not on our discord channel, the bottom of this email that you probably got has a link where you cannot play… Read more: AI Breakthroughs in Video
- AI Challenges and CompetitionsTranscription provided by Huntsville AI Transcribe Alright, so what we’re going to talk about the theme for tonight, we’ll cover some of the other pieces, probably stop recording before we jump into some of that. So that when we first started, the main challenge kind of site out there for competition through machine learning, mostly… Read more: AI Challenges and Competitions
- AI without Python?Transcription provided by Huntsville AI Transcribe So let’s jump right into it. So welcome Alex, talking about data science outside of Python. Hi, so I’ll front here. So a lot of the stems out of, I do a lot of data aggregation work at Northrop and Northrop has kind of completed all the private packages.… Read more: AI without Python?
- Mixture of Experts: Harnessing the Hidden Architecture of GPT4Transcription provided by Huntsville AI Transcribe Yeah, sure. That’s fine. Yep. No worries. Yeah, actually I’m going to copy before I post new things. That’s like, you know, okay. All right. Thank you. Thank you for your recording. So let’s go back over here. All right. So while we’re around, I kind of got a… Read more: Mixture of Experts: Harnessing the Hidden Architecture of GPT4
- AI Hackathon Starter KitTranscript generated by https://transcribe.hsv.ai So one of the other things we do as part of Huntsville AI is we make sure that when we talk about stuff, especially in our weekly meetups and stuff, we try to make sure everything is as public as it can be. We really don’t like people coming and giving… Read more: AI Hackathon Starter Kit
- Fun with AWS FargateI was finally able to get the Streamlit app for the transcription approach to work with AWS Fargate. It was a LOT more complicated than I initially expected. It all makes sense now that I know how it works, but putting all the pieces together was tricky. Hopefully I can get the rest of the… Read more: Fun with AWS Fargate
- MLOps with AWS LambdaAt this meetup we walked through an exercise to try and put the speech to text application into a docker container and attach it to an AWS Lambda function that runs automatically when we add a video or audio to an S3 bucket. In addition to the speech to text model, I’ve been working with… Read more: MLOps with AWS Lambda
- Speech to Text with Hugging Face Wav2VecThis meetup covered an approach for using Hugging Face transformers to convert audio files to text transcriptions. We also went through an approach using DeepSpeech, but did not see any reasonable improvement in the transcript.
- Fine-tuning DistilGPT2 and Generating TextWe have some really exciting stuff to cover this week! Even folks that aren’t into the in-depth side of AI should be interested to see how well this can be used to create text from a simple prompt. We will cover the process used to train this model using a collection of SBIR topics, using… Read more: Fine-tuning DistilGPT2 and Generating Text
- GitHub Runners (Part 2)This week we will continue our journey to set up hosted runners with GitHub. Hopefully we’re successful with getting this off the ground this week. Related links:Product Recommendation repoGitHub RunnersSecurity for Runners?CML for Self Hosted Runners
- GitHub Runners (Part 1)This week we will attempt to configure and connect a remote runner using Amazon AWS and connect it to GitHub to perform actions on the Product Recommendation repository. Nothing like a live demo to get the heart pumping! We will go through the latest updates for reporting on datasets for the repo and discuss the… Read more: GitHub Runners (Part 1)
- Community Support with Little Orange FishThis week we will have Daniel Adamek, Executive Director of Little Orange Fish present their “Here for You” initiative. We will brainstorm AI related ideas that may help them accomplish their goals. This will be an IN-PERSON meetup that we will also attempt to stream and record. Little Orange Fish Concept: A strong community is… Read more: Community Support with Little Orange Fish
- Intro to Hugging FaceThis week we will begin a series that covers Hugging Face and transformers provided through their community-driven approach. This will be one of the first times that we’ve covered Hugging Face, so please take some time to read ahead and help drive the discussion.Also, we’re trying to plan ahead a bit better, so that you… Read more: Intro to Hugging Face
- Continuing (again) MLOps with Kedro PipelinesThis week we will continue our continuation of our MLOps series by looking at the pipeline approach for machine learning operations. We will complete the Kedro for the implementation framework and discuss other products and frameworks that provide a similar approach. We will use our product recommendation project as a concrete example of building pipelines.… Read more: Continuing (again) MLOps with Kedro Pipelines
- Continuing MLOps with Kedro PipelinesThis week we will continue our MLOps series by looking at the pipeline approach for machine learning operations. In our case, we will use Kedro for the implementation framework and discuss other products and frameworks that provide a similar approach. We will use our product recommendation project as a concrete example of building pipelines. By… Read more: Continuing MLOps with Kedro Pipelines
- Getting Started with ML OperationsThis week we started working through an MLOps setup for a recommendation engine. This week we will learn about what MLOps is (according to the internet) and why we need it. Here’s the URL for the Google paper we covered: https://cloud.google.com/architecture/mlops-continuous-delivery-and-automation-pipelines-in-machine-learning
- Overview of KedroThis week we will walk through an overview of the Kedro framework. From their website:“Kedro is an open-source Python framework for creating reproducible, maintainable and modular data science code. It borrows concepts from software engineering best-practice and applies them to machine-learning code; applied concepts include modularity, separation of concerns and versioning.” As a starting point,… Read more: Overview of Kedro