Guest Host Xavier Portilla returns to chat with Allen about some of the latest additions to Dialogflow CX. New system functions make some of the processing you can do on inputs easier and faster, while prebuilt flows and flow scoped parameters make it easier to have clearly defined, and reusable, components in your conversation design. More info: https://cloud.google.com/dialogflow/docs/release-notes#July_05_2023
Guest host Xavier Portilla joins Allen to take a look at a new slot type that the Alexa team has in public beta. How can this new type be used? How does it differ from previous slot types? And what is a slot type anyway?
Guest Host Leslie Pound joins Allen to discuss her perspective on software development and #GenerativeAI and how, rather than trying to translate our fuzzy side, developers should think about how it helps us be more aware of how users are seeking to be more inspired or creative.
Noble Ackerson returns to discuss about a recent presentation that Allen made to the Google Developer Group NYC chapter where he illustrates how #GenerativeAI can be used as a bridge between the discrete nature of computers and the "fuzzy" nature of humans. He and Noble discuss how Large Language Models, such as OpenAI and Google's PaLM 2, along with libraries like LangChain become a powerful tool in every developer's toolbox.
Allen is joined by Noble Ackerson to discuss the latest feature that OpenAI has included with it's GPT models. Functions provide a well defined way for developers to turn unstructured human input to a more structured format that can be processed by your code or using a library such as LangChain. We take a look at both how they can be used, but some of the open questions that remain about their use. More info: - https://platform.openai.com/docs/guides/gpt/function-calling...
This week, Google completed the "sunset" of Conversational Actions for the Google Assistant. Mark and Allen discuss the ups and downs of Actions on Google, how it fit into the #VoiceFirst landscape, and what may come next.
Another milestone episode! Mark and Allen take advantage of the event to look back at our predictions from episode 100, look back at how #VoiceFirst development has changed over the past 50 episodes (and several years), and look forward to what we'll be talking about in the next 50 episodes.
It's been a busy week! What have we been up to? Mark has released a new set of cards that summarize and illustrate different AI concepts. Called "AI Explorer Cards of Discovery", we chat about the objectives and the process to create this deck. (And there's a special offer for listeners!) Meanwhile, Allen has been working with Google's new PaLM model as part of Google Cloud's Vertex AI platform and has contributed changes to the popular LangChainJS package to make PaLM available through the open...
SO MUCH packed into this episode! Recently, Allen participated in a hackathon sponsored by VoiceFlow, and he used the opportunity to explore ways that LLMs could be used to build on his work talking with spreadsheets in Vodo Drive (see episode 116). He and Mark explore how he did it - from the prompts that were required to integration with VoiceFlow and Google App Script, to how tools like LangChain will help build similar things. We also explore what lessons are learned, how our experience in #...
It's Google I/O time again! And although Allen couldn't attend in person, he and Mark review the latest announcements relevant to #VoiceFirst and #ConversationalAI developers. From new AI availability to AI workspace, with stops along the way to discuss AI powered hardware, there was lots to hear about. Also some subtle hints from what wasn't said. But did we mention the AI? Learn more: * https://blog.google/technology/developers/google-io-2023-100-announcements/...
We've touched on the use of vector databases as we've started to explore how LLMs and conversational AIs can be useful, but what are they and how do they work? How are they used for more than just LLMs? Mark and Allen explore some of the classic vector DBs, such as HNSW, and some of the newer fully managed ones, including Metal and Pinecone. We even start to ponder what a fully managed embedding and vector db system might look like from the likes of Google, Azure, or AWS, and are surprised that ...
Long teased, the ability for developers to create Alexa Widgets is finally generally available! Mark, an Alexa Champion, has had access for a while now, so he and Allen discuss what it takes to make a Widget, what's new and different, and how it fits into the #VoiceFirst world of skills.
We're still exploring what LangChain can do, and this week we dive into a tutorial put out by the Voiceflow team that discusses some ways that it can be integrated with ChatGPT using LangChain, bringing the #VoiceFirst and #ConversationalAI worlds closer together. Also a great example of how we go about learning and understanding code that is new to us. Resources: * The tutorial we were following: https://www.voiceflow.com/blog/voiceflow-assistant-openai-gpt...
Over the past few weeks, Mark and Allen have been playing with LangChain and OpenAI, exploring where #ConversationalAI and #VoiceFirst design intersects, and we recorded some of our experiments. In this early one, we take a look at how LangChain with a memory chain can work and keep track of what's going on in the conversation. All in just a few lines of code. More significantly, we discuss the role that LangChain can play in putting together AI and other API components to create voice, web, and...
The latest update for the Alexa Presentation Language, APL 2023.1, has been out for a little bit, and Mark and Allen already discussed one of the biggest features - speech marks. But there was more to this release! Allen is, perhaps, even more excited about how selectors can enable some very dynamic APL interactions, and video subtitles and new graphic masks round out what's new. More info: * https://developer.amazon.com/en-US/docs/alexa/alexa-presentation-language/apl-latest-version.html - What...
Guest host Noble Ackerson returns to tie all the pieces of LangChain together and help Allen understand what it does, why it is an increasingly valuable toolkit for many #ConversationalAI developers, and how we can use it to help build #VoiceFirst applications. Resources: * LangChain: https://github.com/hwchase17/langchain * LangChainJS: https://github.com/hwchase17/langchainjs
With the announcement last week that ChatGPT will soon be supporting plugins, Mark and Allen explore what this means for developers, particularly developers who are used to #VoiceFirst development with Amazon Alexa, Google Assistant, and Samsung Bixby. OpenAI is launching it with some interesting features, including hints at how to monetize plugins, but there are still many questions that developers will need answers to. We explore what will be coming, how to prepare for it, what OpenAI still ne...
Allen has been trying to get into building apps that include LLMs, and has been hearing a lot about the LangChain library. But trying to understand it can be... dizzying. Guest host Noble Ackerson joins to help answer some of the questions about LangChain and how it can bring #ConversationalAI to the #VoiceFirst world and how to use it with your existing APIs.
With Daylight Saving Time ending in the US last weekend, Mark and Allen figured it would be a good... time... to take a look at what date and time features are available to voice developers on Alexa, Alexa APL, Google Dialogflow, Google App Actions, and Jovo. Not to mention discussing the role of ISO-8601 date/time formats, JavaScript libraries such as Luxon, and why UTC isn't always the right time zone. Resources: Luxon: https://moment.github.io/luxon/ Alexa Date/Time slots: https://developer.a...
With Google's Universal Analytics sunsetting, everyone is looking at what other tools are available to record user activity in our skills and chatbots. At Allen's suggestion, Mark had checked out the BigQuery service offered by Google Cloud Platform, and created a Jovo plugin to make it available for everyone. We discuss BigQuery and how to use it and this new plugin. Resources: https://www.jovo.tech/marketplace/analytics-bigquery https://cloud.google.com/bigquery...
We've been exploring some new tools, concepts, and libraries - Mark has been looking at tools to do Named Entity Recognition, while Allen has been exploring the LangChain AI library. But this leads to the question - as you're just starting to learn something new, how do you do so? Do you start with example code? Or YouTube videos? Or what? We share what has worked well for us, along with some early discoveries about what we've been looking at.
If you're working on a #VoiceFirst application that requires Speech to Text in a controlled environment (for example, on an embedded device or in a medical environment), you don't want to have to rely on cloud processing such as those available from Google or AWS. Even if you are willing to use the cloud, it may be cheaper to run your own STT service. Mark and Allen discuss one such way to do so - using the Leopard STT product from Picovoice. Additional info: Serverless Speech to Text article: h...
One of our favorite #VoiceFirst features (and not just because of the name) has come to Alexa! Allen and Mark (the real Mark) discuss the new onSpeechMark event that is now available in APL, how it compares to the feature in the Google Assistant Interactive Canvas, and some ways that you can use it to make more powerful and dynamic APL displays.
In our previous episode, Allen and Mark talked about the differences between Dialogflow ES and CX and how both had a notion of front-end integrations. This week, they go in a little deeper, discussing the various ways you can write your own integration if you need to - either by sending text or audio to the Dialogflow API.
Many #VoiceFirst developers know of Dialogflow as a Natural Language Understanding (NLU) system. But is there more to it? Mark and Allen discuss what's different between Dialogflow ES and CX, what's the same, and how both of them provide added value to voice developers (as well as designers).
Did you know Google Chat has an API? That you can build bots for? And that it can even integrate directly with Dialogflow, PubSub, or Google's App Script? Allen introduces Mark to some of the unique and powerful features that the Google Chat API has, explores the various ways you can use it, and ponders some things we can learn when developing for #VoiceFirst.
How is a chatbot different from what we usually think about in the #VoiceFirst world? There are parallels, so Mark discusses some of his recent explorations in what is going on with Microsoft and support for chatbots and Allen compares to some other technology available to developers. There are some interesting updates and changes in progress!
More third party widgets are becoming available for Amazon Alexa, so Mark takes the opportunity to share what he can about how widgets work, how they go beyond a #VoiceFirst design, and how you can get started designing them to accompany your skills. Allen... has some choice facial reactions in response.
As we kick off the new year, Allen and Mark look ahead at what's coming (or what we *hope* is coming) in the #VoiceFirst world this year. From Amazon Alexa and the Google Assistant to custom agents and AI, what do we think the year ahead will bring? What are you looking forward to?
As the end of 2022 looms, Mark and Allen look back at some of the highlights of the show, of #VoiceFirst development, of working with Amazon Alexa and the Google Assistant, and of talking to all of you.
