World’s Fastest Talking AI: Deepgram + Groq

Поделиться
HTML-код
  • Опубликовано: 25 ноя 2024

Комментарии • 167

  • @matten_zero
    @matten_zero 8 месяцев назад +28

    Deepgram is the most slept on AI player.

    • @DataIndependent
      @DataIndependent  8 месяцев назад +3

      yeah they have a ton of good data to work with

    • @deepbhatt6339
      @deepbhatt6339 5 месяцев назад

      Hi is this completely free and opensource?

    • @kelvindimson
      @kelvindimson 5 месяцев назад

      @@deepbhatt6339you want deepgram to be free? 😂😂😂😂 you lot are funny

  • @geopopos
    @geopopos 8 месяцев назад +2

    I built a voice bot with this exact set up steaming and all quite a few months ago and the biggest issue was the latency! So excited to see this is no longer a Problem!

  • @StuartJ
    @StuartJ 8 месяцев назад +7

    I purchased a ReSpeaker Mic Array v2.0 for this purpose. It captures speech with great clarity. Works out of the box on Linux, so should be able to make a standalone voice assistant with it.

    • @DataIndependent
      @DataIndependent  8 месяцев назад +3

      Cool that sounds good, please share when it's out

  • @theflipbit01
    @theflipbit01 8 месяцев назад +5

    I experimented with integrating Groq with Siri shortcut, and it was quite interesting. The response time was pretty impressive.

    • @kaiwenhe5518
      @kaiwenhe5518 4 месяца назад +1

      how?

    • @theflipbit01
      @theflipbit01 4 месяца назад

      @@kaiwenhe5518 groq provides free API and it was a just matter of using that by selecting one of the free open source model with Siri shortcuts. You can see the examples on my channel. I have made the Siri shortcut available too on vid description that you can edit and try yourself...😃. I'm afraid it would be considered spamming if I post a link here lol.

  • @stevecoxiscool
    @stevecoxiscool 8 месяцев назад +6

    Great heads up on new STT/LLM/TTS technology. I had been working on a Unreal Meta Human demo which got pretty close to RT using a Google STT/ChatGPT/TTS. One of the other things to think about if one want's to get into 2D/3D talking head chat apps is streaming back viseme data as well as TTS audio. Plus maybe emotion tokens of some kind. I can't wait for all of this to be offered on one platform/api service.

    • @nerdyboi-p4l
      @nerdyboi-p4l 6 месяцев назад

      you can only have somewhat close to RT with Google or Deepgram, you should go with on-device

  • @avi7278
    @avi7278 8 месяцев назад +9

    This is exactly what I wanted to do this weekend. Great timing.

    • @damien2198
      @damien2198 8 месяцев назад

      Same, I want to try to do translation (language identification per speaker / switching whisper model could be tricky)

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      nice to both of you!

    • @avi7278
      @avi7278 8 месяцев назад +1

      @@DataIndependent I ended up pulling down your project and ran into a few issues, fixed them and made a few improvements like response interruption. It's pretty good but groq being limites to llama 2 and Mistral is a shame. It is at least able to fill the time of latency of the more powerful models so that at least it still feels more natural even if the first 10 seconds are filler until openai or Claude 3 ingests input and starts streaming.

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      @@avi7278 That's awesome! If you were open to doing a PR to add interruptions I would definitely want to share it with the community.
      Did you add filler too?

    • @avi7278
      @avi7278 8 месяцев назад

      @@DataIndependent it's on my list for this weekend, cheers, appreciate the starter.

  • @Slimshady68356
    @Slimshady68356 8 месяцев назад +3

    Thanks Greg you do alot for the community ,I have respect for you did in semantic chunking in langchain repo

  • @clumsymoe
    @clumsymoe 6 месяцев назад +5

    Thank you for creating this tutorial it's exactly what I was looking for. Great content!

  • @balubalaji9956
    @balubalaji9956 8 месяцев назад +4

    this is exactly i am looking for .
    thank you youtube.
    love you lots

  • @souravbarua3991
    @souravbarua3991 8 месяцев назад +2

    Looks cool. Thank you for showing this idea. Will definitely implement it in my project.

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Nice! Good luck! What is the project you're building?

    • @souravbarua3991
      @souravbarua3991 8 месяцев назад

      @@DataIndependent I didn't started yet. But I will start it soon.

  • @jeffersonhighsmith7757
    @jeffersonhighsmith7757 4 месяца назад

    "Filler words" this is hugely important, IMO. Because it's literally how human beings speak. They use these delaying tactics constantly.

  • @HideousSlots
    @HideousSlots 7 месяцев назад +1

    conversational endpointing is a great idea, but I'd like to see that combined with a small model agent that was only looking for breaks in the conversation and an appropriate time to interject. Maybe with a crude scale for the length of the response. So if the user has a break in the point they're trying to make - we don't want the user interrupted and the conversation moved on - what would be more appropriate would be a simple acknowledgement. But once the point is complete, we would then pass back that we want a longer response.

    • @frothyphilosophy7000
      @frothyphilosophy7000 7 месяцев назад

      This. I need something like this for a project, but I'm not very familiar with Groq or Deepgram yet; just starting to dig in. This thing starts responding with the first little pause, so it constantly cuts me off when I'm just pausing momentarily to think of how I want to phrase the rest of my sentence. If it wants to send data at every minor pause in order to understand context, predict the full query, and begin formulating a response, that's fine-- but it needs to wait until I've finished my entire input before verifying/sending its response. Out of the box, this is like a person who doesn't actually listen to what you're saying and is just waiting for their turn to speak. Is there an easy way to affect the response times and/or understanding of when the user has finished a full thought or do I need to develop logic/rules from scratch?

    • @HideousSlots
      @HideousSlots 7 месяцев назад

      @@frothyphilosophy7000 not that I’ve seen. And this would be a massive leap in improving conversation. It literally just needs a small model to parse the text at every pause and see if it’s an appropriate time to interject. Just the same as a polite human would do. The groq api should be able to do it. I’m really surprised we haven’t seen this effectively enabled anywhere yet.

    • @frothyphilosophy7000
      @frothyphilosophy7000 7 месяцев назад

      @@HideousSlots Gotcha. Yeah, guess I'll need to implement that, as it's unusable otherwise.

  • @abdelkrimdakouan7211
    @abdelkrimdakouan7211 8 месяцев назад +2

    Rasa NLU would be good for intention detection like greeting, closure , and the domain or custom intentions

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      I'm not familiar with that - thanks for sharing I'll check it out

  • @IvarDaigon
    @IvarDaigon 8 месяцев назад +2

    FYI you dont need to use an API for TTS or Speech to Text both can be run locally using Faster Whisper for TTS and Coqui for Speech even if you dont have the worlds most expensive GPU because both of those only use a couple of GB of Video Ram. Going forward, on device will be the way to go for TTS and STT because they simply do not require that much processing power.

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Nice - what kind of latency are you getting with those? Along with accuracy

    • @vaisakh_km
      @vaisakh_km 8 месяцев назад +1

      There is also Piper for tts, it's open source and wirks realy well in my non-gpu laptop

    • @moodiali7324
      @moodiali7324 7 месяцев назад +2

      there is a caveat with ur solution becuase fatser whisper does not detect silence out of the box and hence, you wouldnt know if the user has finished talking or not, which Deepgram does.

  • @ScottSummerill
    @ScottSummerill 8 месяцев назад +1

    The original Groq demo had an impressive speech demo. How did that work? Interviewer interrupted Groq repeatedly.

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Can you link it?

    • @ScottSummerill
      @ScottSummerill 8 месяцев назад

      ruclips.net/video/pRUddK6sxDg/видео.htmlsi=Kg15nRUEEr1AHTGx

  • @cameronlanier7169
    @cameronlanier7169 8 месяцев назад

    Super fast example - really highlights the power of this tech

  • @ajaykumarreddy8841
    @ajaykumarreddy8841 4 месяца назад +1

    Hi Greg. Great video! Thanks for sharing.
    But I have some issues when running the code:
    Firstly, the Speech-to-text performance is not very good. I literally have to shout into my mic for it to be able to hear. I thought it was my microphone issue and tested it normally on a simple voice recorder and it worked as expected.
    Secondly, the text-to-speech voice output keeps breaking in between. Not sure if that is expected because of ffplay but definitely wasn't as smooth as what you showed in the video.
    Thirdly, the voice input is not getting recognized immediately once I get the response. It seems there is a small but noticeable delay to when I get the response back as voice to when I can again start speaking even though it says "Listening" in the console. I have to wait for like 5-10 seconds before I start speaking for the program to recognize my voice or else it isn't doing so.
    Is anyone else facing the same issue?

  • @xXWillyxWonkaXx
    @xXWillyxWonkaXx Месяц назад

    So in a nutshell, streaming is basically using a websocket - getting a chunk of the text to analyze quickly rather than have bit sent over little by little?

  • @damien2198
    @damien2198 8 месяцев назад +4

    I suppose Whisper/ tiny model would be faster than this Deepgram ? have you tried?

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Nope not yet - let me know how it goes

  • @You_Got_Us
    @You_Got_Us 7 месяцев назад

    Great video, Greg!

  • @ParthivShah
    @ParthivShah Месяц назад

    Pretty Amazing! Thanks.

  • @darkreader01
    @darkreader01 8 месяцев назад +2

    This is exactly what I was looking for. Thanks. But the text to speech functions seems to be not working in my windows. I tried writing the audio in a wav file (for debugging purpose), but the file is also can not be played. I thought may be codec issue, so I tried to convert the file in online to mp3, but got an error message showing " Invalid data found when processing input".
    Any idea, how can I make the text to speech function working? Another note: it does not show any error message in terminal, it just does not play the audio.

    • @ocin3055
      @ocin3055 8 месяцев назад +1

      Same issue here. Hoping for an answer, too.

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Try again with these changes
      github.com/gkamradt/QuickAgent/commit/21ae2b0e286759e186e12a76addd250a5a491381

  • @lets-talk-ai
    @lets-talk-ai 4 месяца назад

    Amazing video as always, thanks Greg. Did anyone had some issues with ffplay?

  • @deeplearningdummy
    @deeplearningdummy 7 месяцев назад

    Awesome Greg! Best TTS-STT demo yet. Do you have any ideas on how to modify your example for two people having a conversation, and the AI participating as a third person. For example, debate students are debating and want the AI to be the judge to help them improve their debate skills. I would love to hear your thoughts on this. Thanks for this tutorial. I've been looking for this solution since the 90's!

  • @andrejss
    @andrejss 6 месяцев назад +1

    Thank you! Amazing!

  • @elirothblatt5602
    @elirothblatt5602 8 месяцев назад

    Awesome, subscribed on the strength of this video.

  • @jellybeanthe2nd223
    @jellybeanthe2nd223 2 месяца назад

    I'm having a lot of problems with the "building blocks" you put on github could you release the full finished script ?

  • @BlayneOliver
    @BlayneOliver 8 месяцев назад

    Wow that was fast… Grok literally went open source 😮

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      I was able to sneak early access for the video

  • @paulhilton74
    @paulhilton74 8 месяцев назад

    Amazing video.. Just wish it had a walk though of instructions

  • @kevinduck3714
    @kevinduck3714 8 месяцев назад

    Holy hell that is incredibly fast

  • @michielsmissaert
    @michielsmissaert 7 месяцев назад

    Great stuff! Did you not cut in the video to reduce the waiting time for the LLM response? If you did not, the speed is impressive! Thank you so much!

  • @106rutvik
    @106rutvik 8 месяцев назад +1

    Hi Greg, Rutvik here. We have created something similar to this but using GPT as LLM and Elevenlabs as TTS. We are facing issues with Silence detection with Deepgram. I know you did mentioned in your video at 3:53 that we need to make sure that we dont talk too slowly. And unfortunately Deepgram only has MAX value of 500 ms for endpointing (Silence detection). Can you confirm if we are using proper configurations with Deepgram? Following are my configurations.
    'punctuate': True,
    'interim_results': True,
    'language': 'en-US',
    'channels': 1,
    'sample_rate': 16000,
    'model': 'nova-2-conversationalai',
    'endpointing': 500

  • @princecanuma
    @princecanuma 8 месяцев назад

    Great video, Greg!
    You gave me some interesting ideas :)

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Awesome - excited to see what you build

  • @aliabassi1
    @aliabassi1 8 месяцев назад

    Thanks for this! Testing it now ... the TTS audio isn't streaming and im struggling to fix it but ... THANK You for sharing your code! Super helpful and informative video!

    • @TheColdharbour
      @TheColdharbour 8 месяцев назад +1

      I’m in the same situation, got the listening and response working great but no TTS. Spent all day breaking and fixing it 😂 still confused why it won’t talk! Great guide (I needed python 3.11 to get I back working and had some issues with dotenv, ended up hard coding the APIs) - it’s a great piece of work! 👍👍

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Try these updates
      github.com/gkamradt/QuickAgent/commit/21ae2b0e286759e186e12a76addd250a5a491381

  • @urglik
    @urglik 7 месяцев назад +1

    This app won't find my API keys either Groq or Openai though they are there. Too bad. Any suggestions greg?

    • @urglik
      @urglik 6 месяцев назад

      API's being found either!

  • @dgpreston5593
    @dgpreston5593 5 месяцев назад

    Nicely done

  • @AdrianIsfan
    @AdrianIsfan 8 месяцев назад +1

    Am i the only one not able to hear the TTS back even if i installed the ffmpeg? What am i mising? i tried both from vscode and from normal terminal.. nothing plays out, no errors though. connections to deepgram is checked and successful.
    Any hints?

    • @TheColdharbour
      @TheColdharbour 8 месяцев назад

      I’d also love to know this. I’m in the same boat! It works .. just silently for me too

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      I updated the code, try again or make these changes yourself
      github.com/gkamradt/QuickAgent/commit/21ae2b0e286759e186e12a76addd250a5a491381

  • @hjoseph777
    @hjoseph777 3 месяца назад

    Can that be installed locally? Can you provide more detail on how to do the first step. The transcription is extremely fast

  • @JOSEGARCIA-ch2jp
    @JOSEGARCIA-ch2jp 5 месяцев назад +1

    pricing, pricing, pricing always pricing.

  • @sethjchandler
    @sethjchandler 8 месяцев назад +2

    Would be great for training lawyers to take depositions and do other oral tasks.

    • @J3R3MI6
      @J3R3MI6 8 месяцев назад +2

      Yep it would… But unfortunately lawyers are probably done for… like 99% of them.

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      It'll help augment roles ha, not replace

  • @Todorkotev
    @Todorkotev 8 месяцев назад

    Getting error when firing off the "request" in "speak()" - "err_msg":"Failed to deserialize JSON payload. Please specify exactly one of `text` or `url` in the JSON body." It works though, if I take the "voice" attribute out of the the "payload" AND also change the model to the model in their docs, which is "aura-helios-en". Other than that, thank you so much for sharing! It's hard work!

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Thanks for this - I found this same problem. I had it working in beta (before the video game out) so these were the changes needed for their prod version.
      Updated!

    • @Todorkotev
      @Todorkotev 8 месяцев назад

      @@DataIndependent Thanks Greg! Awesome content! I appreciate you!

  • @InterpretingInterpretability
    @InterpretingInterpretability 6 месяцев назад

    Could you help me understand what's going on. I'm running this in Docker and keep getting an error when it gets to running the .py where it's trying to use ffmpeg audio player and pyaudio.

  • @interspacer4277
    @interspacer4277 8 месяцев назад

    ElevenLabs turbo with deepgram stt. As tested. Cant beat it.

  • @aravindchandrasekaran8838
    @aravindchandrasekaran8838 6 месяцев назад

    Could you also add the latency for Audio to text of your voice?

  • @digitald74
    @digitald74 8 месяцев назад

    very nice, many thanks. latency of the llm still way too high. maybe 6-12 months to bring it down to

  • @cyberthugFi
    @cyberthugFi 2 месяца назад

    Do you have any Github Repository to be able to git clone?

  • @kapilkevlani145
    @kapilkevlani145 5 месяцев назад

    can somebody helps me with interruption handling in this provided video as I have created a voicebot which is running on UI but unfortunately it cannot handle voice interruptions.

  • @VeronicaLightspeed
    @VeronicaLightspeed 6 месяцев назад +1

    how can we interrupt the ai??? plsss helpp

    • @kapilkevlani145
      @kapilkevlani145 5 месяцев назад

      Looking for the same. Did you got any solution?

  • @BezosAIDirector
    @BezosAIDirector 8 месяцев назад +3

    as a total beginner, I can't find a way to run this.

    • @mnagy0101
      @mnagy0101 7 месяцев назад

      Same here..

    • @hamishbrindle9754
      @hamishbrindle9754 6 месяцев назад

      aww

    • @lakshaynz
      @lakshaynz 3 месяца назад

      Whisper is free - demo is on huggingface

    • @lakshaynz
      @lakshaynz 3 месяца назад

      Google groq AI for the demo of ultrafast AI

  • @nessrinetrabelsi8581
    @nessrinetrabelsi8581 7 месяцев назад

    Thanks! How does it compare with assemblyai universal 1? do you know which speech-to-text support arabic with the best accuracy in real time?

  • @BitBlendAi
    @BitBlendAi 8 месяцев назад

    Facing WARNING: API key is missing
    Could not open socket: server rejected WebSocket connection: HTTP 401
    on Stt model

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Ya…you’ll need an API key which I can call out better in the read me

    • @BitBlendAi
      @BitBlendAi 8 месяцев назад

      I have my own api key with 300$ credit. Still it's showing this error
      Can you please send me a screenshot of your .env(hide your api)file​@@DataIndependent

    • @BitBlendAi
      @BitBlendAi 8 месяцев назад

      I have my api key with 300$ credit but still it's showing this error massage. So can you please send me your screenshot of.env( hide your API)​@@DataIndependent

  • @personal1872
    @personal1872 3 месяца назад

    I am not able to install PyAudio in WSL2

  • @viralbakchodi2296
    @viralbakchodi2296 7 месяцев назад

    Sir can you provide full tutorial of this plzzzz

  • @ahmadalis1517
    @ahmadalis1517 8 месяцев назад

    I miss your videos!

  • @igornefedovi
    @igornefedovi 8 месяцев назад

    Wow - incredible!

  • @janyshosmon7414
    @janyshosmon7414 8 месяцев назад

    This is great, thanks for the awesome demo. I’m not a tech person, but can I clone my sales agent’s voice using ElevenLabs and integrate it to this process? I guess I can train the LLM to respond in his tone and sales style? Thanks

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Yeah you could for sure. It would take a bit of work back and forth but it’s there

  • @arunarun0386
    @arunarun0386 3 месяца назад

    Can you provide us github url of this code

  • @Javed.humayun
    @Javed.humayun 3 месяца назад

    how can i put this in web app any idea?

  • @TheRealHassan789
    @TheRealHassan789 8 месяцев назад +1

    How’s this compare against VAPI ?

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Haven't tried that yet

    • @mmdls602
      @mmdls602 8 месяцев назад +1

      Vapi is extremely expensive. I think in a couple of months we should be close to Vapis performance with open sourced models and tooling.

    • @Blampa1456
      @Blampa1456 Месяц назад

      ​@@mmdls602 I have been using Vapi. It works perfectly how I want to integrate this into my clients, but it's $0.12/minute, which is too expensive. Do you have any suggestions? Thank you!

  • @NoidoDev
    @NoidoDev 2 месяца назад

    I want a LPU for home (local hosting).

  • @DadEncyclopedia
    @DadEncyclopedia 3 месяца назад

    I don’t know why there is no sound when running TTS.

    • @didarkamiljanow4488
      @didarkamiljanow4488 2 месяца назад

      same issue, did you figure out whit the sound isn't playing?

    • @Blampa1456
      @Blampa1456 Месяц назад

      @@didarkamiljanow4488 same issue have you figured it out? Haha

  • @tecnopadre
    @tecnopadre 8 месяцев назад

    on windows, having some problems with libraries. After fixing all dependencies, etc. I think I'm having problems with ffplay for the computer to send the audio to the speakers. Taking a look. Somehow I can't listen to ffplay.

    • @aiamaazing
      @aiamaazing 8 месяцев назад +1

      Debug the response from TTS without streaming first. I had to change the URL (it was some beta URL), they have changed it now and the one in Github right now returns an internal error (non 200 response), so the audio won't stream.

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      Both good points, I'll update the URL at least

    • @ferencdalnoki-veress163
      @ferencdalnoki-veress163 8 месяцев назад

      @@DataIndependent I tried it on Ubuntu Linux and (I think I) also have a problem with ffplay. However, somehow while it does convert my voice to text and LLM responds with text it does not convert text to sound. To test it I did different checks to verify that the connection with Deepgram is working. I used a test script where I used the Deepgram API with a text message and then I streamed the audio directly back to ffplay for playback and it worked. So that is why I am puzzled why the code is not working on the Linux side. Any help is appreciated. I truly enjoy your thoughtful tutorials and videos.

    • @ferencdalnoki-veress163
      @ferencdalnoki-veress163 8 месяцев назад +1

      There was an issue with payload. When I commented out the "voice": self.MODEL_NAME it worked. I also changed to pygame from ffplay on Linux. But that may not have been the issue.

  • @yudyjimeneztv692
    @yudyjimeneztv692 8 месяцев назад

    I have tthis error C:\Users\vnt>pip install deepgram
    ERROR: Could not find a version that satisfies the requirement deepgram (from versions: none)
    ERROR: No matching distribution found for deepgram

    • @Todorkotev
      @Todorkotev 8 месяцев назад

      You trying to use their python-sdk? Maybe try "pip install deepgram-sdk"

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Yeah - the suggestion here is the key
      github.com/deepgram/deepgram-python-sdk?tab=readme-ov-file#installation

  • @crystalstudioswebdesign
    @crystalstudioswebdesign 7 месяцев назад

    Can this be added to a website?

  • @loryo80
    @loryo80 8 месяцев назад

    thank you so much for this video, i have a problem when i run the scipt : i have this error message :" Could not open socket: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: certificate has expired (_ssl.c:997) "
    any help please

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      I had this problem a while back too and it was super annoying. The solution was a lot of googling and I think I might have even used it as a push to upgrade my python

    • @loryo80
      @loryo80 8 месяцев назад

      @@DataIndependent This doesn't look good for me then, hhhhhh, was the solution obvious or did it require a lot of manipulation?

  • @RADKIT
    @RADKIT 8 месяцев назад

    Showcase it within a streamlet app doing Langchain shenanigans! Please!

    • @DataIndependent
      @DataIndependent  8 месяцев назад +1

      Like what kind of shenanigans?

    • @RADKIT
      @RADKIT 8 месяцев назад

      @@DataIndependent
      Starter difficulty
      Steamlit app using Langchain and Deepgramdeepgram that allows you to upload a pdf / embed then when ready we can simply chat with it live , asking a question , retrieving information
      Advanced difficulty / Aspirational
      An agent using function calling and a set of tools like web search / calculators etc ...
      if we can have an asynchronous continues conversation with one supervisor agent who asynchronously can "ask" other agents to do time consuming tasks, like being able to talk to the supervisor agent in Langgraph schema

  • @thedoctor5478
    @thedoctor5478 8 месяцев назад

    Doesn't this suck? I've been subscribed to Deepgram for quite a while now. You'd think they would have some good competition. Alas, none that have stuck around, and open-source is infested of dragons.

  • @gjsxnobody7534
    @gjsxnobody7534 8 месяцев назад

    how to add those filler words?

  • @VeronicaLightspeed
    @VeronicaLightspeed 6 месяцев назад

    how could we interrupt the voicebot can anyone help (pls)

  • @hiranga
    @hiranga 8 месяцев назад

    @DataIndependent great video! Do you know how to get ChatGrok / Mixtral working with Langchain 'bind_tools'? I'd love to swap out my ChatOpenAI for ChatGrok if possible!

  • @zahaby
    @zahaby 7 месяцев назад

    Thank you very much for the vide, how can I integrate RAG into this pipeline?

    • @DataIndependent
      @DataIndependent  7 месяцев назад +1

      Put it in the LLM step, set up a retriever and then call to it

    • @zahaby
      @zahaby 7 месяцев назад

      @@DataIndependent Yes, thank you very much.
      vectordb = FAISS.from_documents(all_splits, embeddings)
      retriever = vectordb.as_retriever()
      BUT LLM doesn't accept retriver param,
      So I used ConversationalRetrievalChain

  • @mnagy0101
    @mnagy0101 7 месяцев назад

    Is there any developper who can help me to set up this?

  • @FedeTango
    @FedeTango 7 месяцев назад

    Is there any alternative for Spanish? I cannot find it.

  • @Celso-tb6eb
    @Celso-tb6eb 7 месяцев назад

    i cloned the code but response time is like 12 seconds. 4 weeks past and i'm late to the party

  • @SzamBacsi
    @SzamBacsi Месяц назад

    Groq performs well with English but struggles with more complex languages such as Hungarian.

  • @JasonHamilton38
    @JasonHamilton38 7 месяцев назад

    I'm not a coder, but can someone please build one of these that I can pay for so I can basically have my own Jarvis to talk to on my computer?

  • @coopernelson6947
    @coopernelson6947 6 месяцев назад

    Yuppppp

  • @andrewtschesnok5582
    @andrewtschesnok5582 7 месяцев назад +1

    Nice. But in reality your demo is 3,500-4,000 ms from when you stop speaking to getting a response. It does not match the numbers you are printing...

  • @suvarnadhiraj
    @suvarnadhiraj 8 месяцев назад

    do you know if any of the open source models (STT and TTS) with Groq give the same latency?

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      My guess is no - oss usually isn't as fast as paid

  • @gaborm5673
    @gaborm5673 8 месяцев назад

    I can't drop the LLM below 3000ms :( maybe im fucking it up?

  • @EDUSidekick
    @EDUSidekick 4 месяца назад

    The voices are all terrible, imho. They would work well in a cyberpunk game - but that's about it. :D

  • @gaijinshacho
    @gaijinshacho 8 месяцев назад

    No good can come of this.....lol

    • @DataIndependent
      @DataIndependent  8 месяцев назад

      yeah - it'll be tricky to navigate but there will be use somewhere

  • @maxxflyer
    @maxxflyer 3 месяца назад

    what languages will work? where can I check it? thanks