chrislemke

Dear Alfred Community,

I am writing to share an important update about the ChatFred project.

As the project has grown and evolved, it has been a privilege to work with all of you. Your contributions and feedback have been invaluable, and together, we've built something truly special. However, due to an increasingly demanding schedule, I am no longer able to dedicate the necessary time to maintain ChatFred with the justice it deserves.

The advent of numerous advancements from OpenAI has opened up exciting new possibilities for ChatFred, marking a perfect moment for fresh energy and leadership to take the helm. Therefore, I am in search of someone with the passion and expertise to carry forward this legacy.

If you have a strong interest in the project and believe you have what it takes to lead it into its next chapter, please reach out. Your role would involve steering development, managing the community, and integrating the latest AI technologies to keep ChatFred at the forefront.

I am optimistic about the future of ChatFred under new stewardship and look forward to seeing it continue to thrive. Please direct inquiries and expressions of interest to the contact information listed below.

Thank you for your understanding and continuous support.

Best regards,

Chris

BTW: This text was written by ChatFred 😉

Hey!

Sponge_bink a contributor to this project implemented a feature to get ChatGPT's response as a stream. Check out those screenshots. This feature will be available in the Alfred Workflow gallery soon.
 

On 9/1/2023 at 6:23 PM, jhalmu said:

Hi. Thanks foe superb addon. I added my openapi free api key to right place but It says only "You have reached your ratelimit..." in chatgpt's own page I can ask questions?

 

OK. So I have to put card to get API work. Confusing that it works in openai's page...

Hey @jhalmu!

Great that you like the workflow. It is really hard to tell the issue without more information. Please checkout this readme for some troubleshooting tips. 

1 hour ago, todoublez said:

how do i configure my api key to the chatfred ?

Just use the "Configure Workflow..." in the left top corner of the workflow overview. I hope this was helpful! 

On 5/9/2023 at 8:31 PM, energyd said:

Hey @chrislemke

good stuff! I recently started using ChatFred with ChatGpt-4. One thing I really miss is the interactive experience I gained through chat.openai.com. I often found myself having to going back and forth with chatGpt and work towards my final solution. ChatGpt was asked to ask clarifying question to me first before working on a solution. 

 

With ChatFred, seems I can only send standalone query to openAI and then it would lost previous context when I ask a follow up question. Do you know a way to make it work interactively (e.g. remembering the context of the conversation)? 

Hey @energyd!
Sorry for the delay. With "ChatGPT history length" in the workflows configuration you can tell ChatFred how long it should remember. Is this any helpful?

Hey! 

Sorry for being "offline" for so long. 

Troubleshooting is always a very important part of software and I would like to improve it. Thanks to @vitor for already improving the misleading readme. I want to improve it even more and would like to receive feedback on your experience concerning troubleshooting this workflow. I already read some interesting notes.

Thanks in advance. 

9 hours ago, TomBenz said:

You get transcript for first 2-3 min and then for last few seconds of the video / audio. fyi.

Hey @TomBenz!

Thanks for the update. I suggest we continue the discussion here so we don't fill up this post with our talk about your idea. Okay for you?

BTW: I also tested "fast_whisper" and I have to admit that I am quite fascinated by it. It is really fast and the different models provide the opportunity to adjust the quality/speed ratio in a very simple way. But even the tiny model is pretty huge (~75MB) not really sure how to put this into ChatFred without requiring additional downloads/installs.

Hey @TomBenz!

Thanks for your contribution and the code example. I was actually already looking into it. The problem is, that the whisper model is huge and most of them would blow up the workflow. At the moment I am having a look at this. 

from faster_whisper import WhisperModel

model_size = "tiny"

model = model = WhisperModel(model_size, device="cpu", compute_type="int8")



segments, info = model.transcribe("SOME_FILE.mp3", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

It is not only smaller and does not use so much CPU but it is also much much faster. Try it out. You can also change the model_size to: "tiny", "tiny.en", "base", "base.en", "small", "small.en", "medium", "medium.en", "large-v1", or "large-v2".

3 minutes ago, TomBenz said:

I think the reference is to Python etc code properly formatted and shown in the chatGPT web browser.

In this case, ChatGPT's API returns three backticks (```) as plain text. I thought about handling them in a certain way but it will be hard to distinguish if the backticks are a part of the response or a formatting character.

Hey @s95hc8!

Sorry that the troubleshooting section was not helpful. If you need any further help please let me know. 

Here are the answers to your question:

1) Unfortunately there is no way to speed up the workflow. It seems that OpenAI gives higher priority to their WebUI than to the API. I hope this will improve soon.

2) If you want to change the size of the text you can change it in the workflow. Check the screenshot to see where to find it.

3) There are multiple ways to archive this. By default, ChatFred pastes ChatGPT's response automatically to Alfred's clipboard history. You can also set the Paste response to frontmost app in the workflow's configuration so that ChatFred will not show the response in the dissipating window but will paste it to the frontmost app.

4) I'm not really sure what are you talking about but the response from the OpenAI API is usually just plain text. 

5) You actually don't have to wait for the response of ChatFred. Since it will automatically copy the response to Alfred's clipboard history you can continue working with Alfred and come back to ChatFred's response whenever needed. Just open the clipboard history and find the response.

You may want to have a look at the documentation. It may be a bit long and confusing but maybe you find some help. 

I hope this was somehow helpful. 

9 hours ago, s95hc8 said:

thank you very much. I will go through the troubleshooting step by step today and will report back. 

Cool! Let me know if you need any more help.

7 hours ago, s95hc8 said:

I am not able to get this to work.

I type "CF joke" and Alfred is stuck at displaying "ChatFred loading"

Nothing happens.

I have installed the latest version 1.4 of the workflow and have inserted my ChatGPT API key as instructed.
ChatGPT web works for my account.

What am I doing wrong?

Hey @s95hc8!

Did you have a look at the troubleshooting section? Otherwise, I would need a bit more information like the debugger printout to help you effectively. 

4 minutes ago, TomBenz said:

 

Transformation using chatGPT itself. Below is the screenshot

 

 

I use universal action and use send to chatGPT (press shift key) and get a summary or re-phrased version of the content. would like to see how I can get multiple options such as "summarize", and "list top 10 bullet points" in universal action on selected text. 

Ah, got it. Sorry for my misunderstanding. There are two ways to archive your goal. But to be fair non of them is really perfect. The first one is to change the transformation prompt. But I guess that is not really helpful. The other solution is to store the first prompt like "summarize this text" and then append another prompt using the universal action. Check out the Combined prompts in the Universal action & combined prompts section. 

I also just released a new version to improve combining the functionality of automatically pasting the response to the frontmost app and the transformation feature. If you are interested just check out the first section: Talk to ChatGPT. At the end of it, I added an example of how to let ChatGPT write documentation for Python code. Maybe this can also be interesting for you.

You actually have a good point concerning providing the functionality to have multiple text transformation texts. Maybe you have a cool idea on how to implement it? Feel free two write about your idea in the New Ideas thread.

2 hours ago, TomBenz said:

Hi @chrislemke I don't find the option to top up the balance. Request you to guide or suggest a direct link? 

 

Is it possible to see all API calls on chatGPT dashboard? How do you set multiple transformations in the workflow? Like Summarize in a few sentences or Give the top 2-3 keywords?  

 

 

Hey @TomBenz!

As far as I know, you can not top up your balance. You have to add a Credit Card to keep using it once your free credits are empty or expired. 

It is not possible to see all API calls in the dashboard. Concerning your question about "multiple transformations" I guess you are referring to the InstructGPT models and not to ChatGPT, right? The InstructGPT implementation is actually pretty simple it does not provide a lot of functionality. 

I agree with you sometimes the speed is not really good. I was already working on it to improve it. Unfortunately, it is the API call itself that takes 99% of the time. It seems that OpenAI gives its own Website UI a higher priority.    

1 hour ago, albertkinng said:

Why I can’t use ChatFred if I still have free time?

Hey @albertkinng!

If I am not mistaken your your free 18$ expired on April 1. Did you add some Credit Cards? Since this Workflow uses the API the usage will not be for free but I also use it all day long. And on average I pay less than 0.04$ a day.

You are a genius. That's it! Thanks a lot for your help!!

Hey!

I just added the "automatically paste to frontmost app" functionality to the "Copy to clipboard" step of the ChatFred (1.3.3) workflow. For some reason, it is not working. I debugged it and checked how it works in other workflows but I still could not figure out what I did wrong. Maybe someone can help? Thanks a lot in advance!

11 hours ago, Robis74 said:

I seem to be running into an issue when choosing GPT4 instead of ChatGPT3.5 - the prompts do not want to load an answer. Any idea why?

 

I do have ChatGPTPlus, so actually no clue what the issue might be.

 

Thanks

You need to be on the GPT-4 list to use this feature.

10 hours ago, TomBenz said:

Thanks Chris. Does chatFred work both with free and paid version of chatGPT? I see 18 $ credits granted initially and will check if it is daily or cumulative value.

 

On whisper, I read a comparison with other tools at https://towardsdatascience.com/transcribe-audio-files-with-openais-whisper-e973ae348aa7 I have tried the online tool as well, and it looks good. I currently use Microsoft streams to upload meetings and get transcripts for it. I would like to check and find out if whisper gives better quality transcripts. Is there an Alfred workflow available that use Whisper to transcribe audio to text? I will explore the two links below as well:

 

https://andrewmayneblog.wordpress.com/2022/10/16/the-easy-guide-to-using-openais-whisper-model-to-transcribe-video-and-audio/

 

https://github.com/openai/whisper

Hey!

Since ChatFred works using OpenAI's API it is neither using the free nor the paid version of ChatGPT. You actually have to pay for every request. OpenAI gives you 5 $ to spend for the first three month. Here you can find the prices for the usage of ChatGPT and the other models.

Concerning Whisper, I have not found a Alfred workflow which uses it for pure transcription but maybe we can implement this feature in ChatFred. You could open an issue for it. 

11 hours ago, TomBenz said:

@chrislemke This is a great workflow. many thanks for developing and sharing it. I want to check if we can set multiple transform request such as 1. Rephrase this 2. Give 1-3 words title for text provided. Also, what is the limit for API access? Is it a daily or monthly limit? Can mp3/mp4 be directly transcribed to text using chatGPT?

 

regards, 

Hey! @TomBenz! 

Great that you like the workflow. Concerning the API limit - there is no default limit but you can set it yourself. Check this link. For handling mp3 files the workflow uses Whisper. So if you just want to transcribe text you actually don't need to use ChatGPT itself. Hope I could help.

Best,

Chris 

18 minutes ago, Benny4 said:

Thanks @vitor for moving my post to the right section. @chrislemke I reinstalled the workflow and noticed that I didn't press on "continue after verification" now everything works great 

Great! Thanks for the feedback. Enjoy!

6 hours ago, Benny4 said:

I bought a subscription on openai. (The temporary hold 5$ subscription) and I created a private api key and put it into the Alfred workflow. However when I type CF and then a question it goes to „search google/Amazon Wikipedia“

anyone know what to do?

Thanks in advance 

Hey @Benny4!

Happy to help! You could check out the troubleshooting section. Maybe this helps you already. If not perhaps you can provide some additional information like the debug printout?

4 hours ago, Belfong said:

Arg.. I don’t have python installed. This is the reason nothing is happening. Thank you for the tip in the Troubleshooting page. 

Thanks for the feedback!

Happy that I could help. Enjoy!

2 hours ago, Belfong said:

I am using the V1.1.0 and when I type "cf where is Malaysia?" and press enter, nothing happened. I have put the API key. Any way I can troubleshoot this pls? I have use a different API key via drafts and it works, so I suspect I am have done something wrong in Alfred. Thank you.

Hey @Belfong!

First please uninstall the workflow, download the newest version and install it. Maybe this already fixes your problem. Otherwise, please check out the troubleshooting section. Maybe this help. If not please create an issue with as much information as possible I will then investigate your problem. If you don't have a GitHub account you can also just shares logs and debug information here.