Pamela Fox
Pamela Fox
  • Видео 83
  • Просмотров 478 443
RAG Chat App with Speech Input/Ouput
A demo of speech input for azure-search-openai-demo, using SpeechRecognition SDK in the browser and Azure Speech SDK on the server.
Просмотров: 165

Видео

AI RAG Chat App Evaluation
Просмотров 1,9 тыс.4 месяца назад
AI RAG Chat App Evaluation
AI RAG Chat App: CI/CD Deployment
Просмотров 1,8 тыс.5 месяцев назад
AI RAG Chat App: CI/CD Deployment
Overview of RAG Chat App using Azure AI Search with OpenAI in Python
Просмотров 14 тыс.6 месяцев назад
Overview of RAG Chat App using Azure AI Search with OpenAI in Python
Useful tools for contributing to Python open source projects
Просмотров 2737 месяцев назад
Useful tools for contributing to Python open source projects
Viewing Playwright Traces from GitHub Actions Artifacts
Просмотров 6567 месяцев назад
Viewing Playwright Traces from GitHub Actions Artifacts
Logging calls for Python apps on App Service
Просмотров 1,1 тыс.8 месяцев назад
Logging calls for Python apps on App Service
Deploying FastAPI app to Azure Functions + API Management
Просмотров 3,5 тыс.Год назад
Deploying FastAPI app to Azure Functions API Management
Running a Flask+PostgreSQL server in Codespaces
Просмотров 1,1 тыс.Год назад
Running a Flask PostgreSQL server in Codespaces
Deploying a Flask app to Azure with azd
Просмотров 422Год назад
Deploying a Flask app to Azure with azd
Deploying a Django app to Azure with azd
Просмотров 782Год назад
Deploying a Django app to Azure with azd
Monarch butterfly's first flight
Просмотров 105Год назад
Monarch butterfly's first flight
Alexa-controlled LED Laser cut sign
Просмотров 1332 года назад
Alexa-controlled LED Laser cut sign
Riffle Shuffle (Demo)
Просмотров 6733 года назад
Riffle Shuffle (Demo)
Progressive Muscle Relaxation
Просмотров 1886 лет назад
Progressive Muscle Relaxation
Self Compassion Meditation
Просмотров 1,9 тыс.6 лет назад
Self Compassion Meditation
Kurt Schwitters - Ursonate "Bo" Progression (with Verses Displayed)
Просмотров 7737 лет назад
Kurt Schwitters - Ursonate "Bo" Progression (with Verses Displayed)
Schwitters - Ursonate - Complete Poem (with Verses Displayed)
Просмотров 39 тыс.7 лет назад
Schwitters - Ursonate - Complete Poem (with Verses Displayed)
Kurt Schwitters - Ursonate - Part 1 (with Lyrics Displayed)
Просмотров 8097 лет назад
Kurt Schwitters - Ursonate - Part 1 (with Lyrics Displayed)
Kurt Schwitters - Ursonate - Part 3 (with Lyrics Displayed)
Просмотров 3857 лет назад
Kurt Schwitters - Ursonate - Part 3 (with Lyrics Displayed)
Kurt Schwitters - Ursonate - Part 2 (with Lyrics Displayed)
Просмотров 1757 лет назад
Kurt Schwitters - Ursonate - Part 2 (with Lyrics Displayed)
Kurt Schwitters - Ursonate - Part 4 (with Lyrics Displayed)
Просмотров 2077 лет назад
Kurt Schwitters - Ursonate - Part 4 (with Lyrics Displayed)
Our Cat; The Spider Killer
Просмотров 72310 лет назад
Our Cat; The Spider Killer
Sizzling Stylus Game Demo
Просмотров 19913 лет назад
Sizzling Stylus Game Demo
Using Wave at Google I/O
Просмотров 11 тыс.14 лет назад
Using Wave at Google I/O
Deferry Sample
Просмотров 10614 лет назад
Deferry Sample
Google Wave Conversation Model
Просмотров 57814 лет назад
Google Wave Conversation Model
Conference Bot: Webdu
Просмотров 24114 лет назад
Conference Bot: Webdu
Forum Botty: A Wave-Based Forum
Просмотров 69114 лет назад
Forum Botty: A Wave-Based Forum
Active Robots API: Waverizer
Просмотров 28614 лет назад
Active Robots API: Waverizer

Комментарии

  • @wasiffarooqui1026
    @wasiffarooqui1026 3 дня назад

    Complete tutorial?

  • @francoisroux1346
    @francoisroux1346 5 дней назад

    @Pamela - What PDF viewer did you use for this repo? Thanks

  • @zeeshanm6778
    @zeeshanm6778 6 дней назад

    Thank you Pamela, great learning

  • @138charlieB
    @138charlieB 8 дней назад

    Nice! When will this be merged into main, or is there a PR for this?

    • @PamelaFox
      @PamelaFox 6 дней назад

      I'm just finishing up some tests for it, aim to merge this week. (At Build this week in Seattle so I need to give that talk first!)

  • @andreus4266
    @andreus4266 8 дней назад

    Just in time for 4o, looking forward to the merge into main. thank you!

  • @matteopulega560
    @matteopulega560 8 дней назад

    so, azure ai search could be better then a simple postgre pgvector for RAG?

  • @SurajKumar-uf6it
    @SurajKumar-uf6it 10 дней назад

    Mam, How to find the api version of Azure OpenAI of gpt-35-turbo? Can tell the steps to find it

  • @mohammadrokibulislam2952
    @mohammadrokibulislam2952 21 день назад

    If you want to run this tests on GH actions in headed mode (instead of default headless mode), what should be done?

  • @camilotorres4219
    @camilotorres4219 27 дней назад

    Thanks for the video. I've a question, how can I configure the project to use the gpt-35-turbo-instruct model? I tried to do it but it gives me a chatCompletion error, not a valid operation.

    • @PamelaFox
      @PamelaFox 26 дней назад

      The gpt-35-turbo-instruct model does not support function calling, as far as I understand, so I'm guessing that's the error you're seeing. You can remove "tools" and "tool_choice" from the chat completion call and see if that fixes the error.

    • @SurajKumar-uf6it
      @SurajKumar-uf6it 9 дней назад

      @@PamelaFox Mam how can I know the API Version of a Model Name like gpt-35-turbo through azure portal.

  • @andrehass-sh8pm
    @andrehass-sh8pm 27 дней назад

    Thanks for the video. I will try it soon. Could you do it also for this azure sample? Azure-Samples/azure-search-openai-demo-csharp. Would be great.

  • @SiarheiKarko
    @SiarheiKarko Месяц назад

    Hello Pamela, while searching for a pgvector tutorial, I came across your video recommendation. Typically, I rapidly scroll through content, seeking specific answers to my questions. However, your video proved so engaging that I watched it in its entirety, from start to finish. Thank you for your dedication and for creating such compelling content. Please continue to share your amazing videos!

    • @PamelaFox
      @PamelaFox Месяц назад

      Aw thank you that's so kind of you to say. Glad it was helpful!

  • @Quoteoftheday228
    @Quoteoftheday228 Месяц назад

    Hey can I connect with you pamela

  • @hemanthkumar-tj4hs
    @hemanthkumar-tj4hs Месяц назад

    👌

  • @vishalpatel8033
    @vishalpatel8033 Месяц назад

    great video! any thoughts on how we can convert the web app to an API? we would like to integrate it with other system that would feed prompt to API instead of web app. or is there a way to feed prompt to search service directly?

    • @PamelaFox
      @PamelaFox Месяц назад

      This app is structured to output a JSON API. You can see a description of the output format here: github.com/Azure-Samples/ai-chat-app-protocol The frontend sends user messages to that API, but you can send requests to it directly as well.

  • @theindynomad
    @theindynomad Месяц назад

    I've struggled to explain to folks about how vector semantic is different from text search.. finally found somone who explained this so clearly. Thanks, enjoyed this highly informative session.

  • @Southpaw101
    @Southpaw101 Месяц назад

    Hi @PamelaFox is there a way to use this app with Azure AI api and not open AI. I do have an deployment of the Turbo GPT 3.5 and Ada002 in Azure and would like to use this with those api. Can you recommend how I can do this. This blocks me from using this app. I followed your other video on setting up the chat but it only shows Azure AI. Please recommend any alternative I only see these entries in setting for low cost Thanks for your help. . azd env set OPENAI_HOST openai azd env set OPENAI_ORGANIZATION {Your OpenAI organization} azd env set OPENAI_API_KEY {Your OpenAI API key}

    • @PamelaFox
      @PamelaFox Месяц назад

      Hm, I'm confused as to whether you're trying to use it with OpenAI.com or Azure OpenAI? We do support both. If it's not working, please file an issue in the repo where we have better support for code sharing.

  • @mohamedmaf
    @mohamedmaf Месяц назад

    Thanks a lot

  • @nachoalonsoportillo
    @nachoalonsoportillo Месяц назад

    Thanks for putting together this session Pamela. Very useful, indeed.

  • @lovekesh88
    @lovekesh88 Месяц назад

    cone analogy was really good. Thanks.

  • @Southpaw101
    @Southpaw101 Месяц назад

    When does this live stream happen... Is there fixed time ?

    • @PamelaFox
      @PamelaFox Месяц назад

      I haven't been very consistent, so let me try to see if I can be better about that, starting tomorrow (Friday 10 AM PT).

  • @Southpaw101
    @Southpaw101 Месяц назад

    Great Video.. very informative. Thanks

  • @mohdkashif9830
    @mohdkashif9830 Месяц назад

    are you going to provide the videos you talked about on Khan Academy ?

    • @PamelaFox
      @PamelaFox Месяц назад

      Hm, which videos did I discuss? I don't currently work for Khan Academy, so I don't have any plans to put videos on Khan Academy.

    • @mohdkashif9830
      @mohdkashif9830 10 дней назад

      Oh i see...btw it would have been a pleasure learning from you

  • @MatthewMcMaster82
    @MatthewMcMaster82 Месяц назад

    Thank you, always engaging walkthroughs

  • @afneto
    @afneto Месяц назад

    Great material, Thanks.

  • @AbhishekSpeaking
    @AbhishekSpeaking 2 месяца назад

    Quite literally my first RUclips comment, and the first channel I subscribed to in a long time. :) Thanks for the great content Pamela. Trying out Langfuse now.

  • @vladnedelea05
    @vladnedelea05 2 месяца назад

    hi Pamela - your videos are really helpful. :) One question perhaps not appropriate: I am trying to modify the app to create a proposal builder tool for the nonprofit i work for (rag to draw from past proposals and helps user build a new one, section by section). I'd like to create a functionality where the chatbot and context is passed along on a section by section basis for the proposal (e.g., for the intro section - there's a set interaction between user and system with context passed to the LLM- maybe bot even askes some questions to gather input and eventually draws on sources to produce an intro section for the proposal). Then i'd like to move on to building another section of a proposal (e.g., "what can we do for you") , but have the chat bot use a different prompt / instructions, sources for this part of the chat bot. Any ideas how i can do this in the simplest way? Thanks a lot and thanks for creating this. I dont know all that much about coding but learning a ton by just deconstructing this app and figuring out how it works.

    • @PamelaFox
      @PamelaFox 2 месяца назад

      Hm, good question. I'm thinking you can set a flag in the frontend that you pass to the backend, like conversation_stage="spec". Then in the approach run method, if you see conversation_stage=spec, you vary the prompt as needed. It might be a bit hairy as the code isn't setup off-the-bat for this sort of multi-phase conversations.

    • @vladnedelea05
      @vladnedelea05 2 месяца назад

      thanks for the suggestion@@PamelaFox​. I'll play around with it although implementing will be a challenge for me lol - chat gpt take the wheels

  • @nickt4200
    @nickt4200 2 месяца назад

    These are so helpful and ahead of their time. File uploads would be helpful so +1

  • @anagocevska
    @anagocevska 2 месяца назад

    Really enjoyed this explanation! Everything covered to really understand what's happening behind the scenes. Thank you! :)

  • @nickt4200
    @nickt4200 2 месяца назад

    Any idea how we get access to GraphRAG is it GA? Should we ask our rep.

    • @PamelaFox
      @PamelaFox 2 месяца назад

      That came from the research group, and they haven't published code/services for others to use GraphRAG yet. Hope we hear more in the future.

  • @bugexploit
    @bugexploit 2 месяца назад

    This is one of best video I have watched so far on RAG. Great explanation in simple terms and to the point. please keep making more videos.

  • @sergtimosh
    @sergtimosh 2 месяца назад

    Unfortunatelly the video title is missleading. It's not viewing from GH actions, it's viewing locally via standalone site. I'm looking the way for viewing the traces at least from withing downloaded test report byt the link. Tha would be so much more convenient. Do you maybe know the way?

    • @PamelaFox
      @PamelaFox 2 месяца назад

      Are you saying you want to use the hosted trace viewer from Microsoft?

  • @MatthewMcMaster82
    @MatthewMcMaster82 3 месяца назад

    24:28 Good discussion of how a comprehensive list or question across a larger corpus may not work well with traditional RAG. Good video!

  • @nalinrajsubramanian744
    @nalinrajsubramanian744 3 месяца назад

    Great Explanation. can you explain about ai enrichments that we can add in ai search especially reading text images from pdfs using ocr

  • @PANDURANG99
    @PANDURANG99 3 месяца назад

    Open ai key

  • @girishkurup3143
    @girishkurup3143 3 месяца назад

    Amazing . Thanks for making this valuable video

  • @hemanthkumar-tj4hs
    @hemanthkumar-tj4hs 3 месяца назад

    seeing this video in 2024

  • @vikassalaria24
    @vikassalaria24 3 месяца назад

    Thanks Pamela.

  • @Woodborn
    @Woodborn 3 месяца назад

    Amazing stuff. This reference RAG application code is great, thanks.

  • @InternationalIndianIcon
    @InternationalIndianIcon 3 месяца назад

    Nice session, please post more such sessions. got lot of clarity on embedding and search

  • @ankitnarula6134
    @ankitnarula6134 3 месяца назад

    Ai search + open ai seems to give different answers for same user prompts. Even the chunks returned for answering seem different based on citations even for same prompt. What causes this? Facing issues with consistency of outputs.

    • @PamelaFox
      @PamelaFox 3 месяца назад

      I've written up a guide to debugging answer variance here: github.com/Azure-Samples/azure-search-openai-demo/blob/main/docs/customization.md#improving-answer-quality ...that's specific to that repo but is also a general approach for other RAG apps. Does that help?

  • @jimbocho660
    @jimbocho660 3 месяца назад

    This is one of the best talks on applied LLMs on youtube. Thank you.

  • @dgm1949
    @dgm1949 3 месяца назад

    Thanks for your video. I really like the elephant.

  • @joshuacunningham7912
    @joshuacunningham7912 3 месяца назад

    Thank you so much! I especially appreciate the vector similarity lesson in this video. 👏

  • @st-tube
    @st-tube 3 месяца назад

    Fantastic. Great work

  • @gangs0846
    @gangs0846 3 месяца назад

    Fantastic

  • @ChalkToday
    @ChalkToday 3 месяца назад

    Very nice Content on the video a different approach from others. Are you open to questions at any time?

  • @meenan4243
    @meenan4243 3 месяца назад

    Amazing Tutorial, Thank you

  • @juanok2775
    @juanok2775 3 месяца назад

    very helpful thanks

  • @mr.daniish
    @mr.daniish 3 месяца назад

    Amazing tutorial

  • @Hungrydelights
    @Hungrydelights 3 месяца назад

    How to use local pdf parser if I am running this on GitHub codespaces?