• State Suggested Answer
  • +5 person also asked this people also asked this
  • Replies 30 replies
  • Answers 7 answers
  • Subscribers 189 subscribers
  • Views 6725 views
  • Users 0 members are here
Options
Related

OpenAi Translator error:

Begoña Manzano Garrido

Hello, 

I've downloaded the app and installed it, I've also created an account in OpenAI and created the API key but I get the following errors when trying to use it:

1. When selecting Model GPT-4, I get the "Not found" error 

2. When selecting GPT3.5 TURBO or TEXT DAVINCI 003, I get the "Bad request" error:

I tried with all the Prompts and I get the same error for all of them, except for the "No 3rd person singluar pronouns" that I get the "Too many requests" one. 

Could you please help me on this one?

Thanks, 

Bego,
emoji
Rate translation
×
Suggest better translation
×
Parents
  • 0

     

    Nice to see you trying this one out... I think you may be the first to provide any feedback!

    An observation at this stage would be that you don't seem to have selected anything from the Search dropdown ad it's blank.  I'm not sure why this would be as it's always populated for me and I have choose between source or target.  Perhaps you can try selecting something first?

    You show this for example:

    I have this:

    However, I have also noticed that the OpenAI server is so slow at the moment that multiple calls seem to result in nothing at all.  Can you also test this with the default prompt that only asks for a single translation?  That works for me.

    We'll do some more testing but I have a feeling this could be a problem on the OpenAI end as they have been inundated in the last months with an unexpected demand and they need to do a lot of work to improve their ability to support the demand.

    Paul Filkin | RWS Group

    ________________________
    Design your own training!
    You've done the courses and still need to go a little further, or still not clear? 
    Tell us what you need in our Community Solutions Hub

    emoji
  • 0 in reply to Paul

    I got the same Bad Request error, but I fixed it by adding my credit card data to my account. However the "Not found" error pops up as soon as I select the GPT-4 Model.
    emoji
  • 0 in reply to Ziad Chama

    We will investigate these errors, and interpret better the messages that are returned from the OpenAI API.  As you already noted, this is most likely related to a time-out as the gpt-3.5-turbo and especially gpt-4 models don't seem to be provisioned appropriately for public consumption at the scale they are used.

    Also Consider that you need a paid account to access both gpt-3.5-turbo and gpt-4.  Additionally, some countries are not allowed access to the API entirely, like Italy.

    The model text-davinci-003 (e.g. gpt 3.0) is available for free for the first 3 months and is resonably fast, so might be worth confirming if this working, just to confirm you are able to communicate with the OpenAI API.  It will help to narrow down the cause.
    emoji
  • 0 in reply to Patrick Andrew Hartnett

    Hi Patrick, 

    Thanks for all the details. Do you know if Spain is one of these countries not allowed to access the API? 

    I get the "Bad request" error when selecting the text-davinci-003 model too. 

    Let me know if you need any further details.

    Thanks!
    emoji
  • 0 in reply to Begoña Manzano Garrido

    Countries such as North Korea, Iran, China, Cuba, and Syria are among the countries where ChatGPT is not accessible.

    Italy banned ChatGPT over Data Privacy Concerns and talks that Germany and France will soon follow. I'm reading now that Spain opened an offical investigation into OpenAI's ChatGPT over a potential data breach in the last days...  not sure what that means exactly with general accessiblity.

    One way to confirm definitively if you can access the OpenAI API from where you are located in the world, is to load the website in a browser: https://platform.openai.com/ and login
    emoji
  • 0 in reply to Patrick Andrew Hartnett

    Thanks, Patrick. I could create the account and the API key so I do have access to the platform Slight smile
    emoji
  • 0 in reply to Begoña Manzano Garrido

    touché :-)
    let me mull over it for a bit; trying to idenfity better ways of tackling these types of problems; possibly including more information in the log that might help with more context to idnetify the root cause etc...
    emoji
  • +1 in reply to Patrick Andrew Hartnett

     

    Hi, Patrick. I'm having the same problem as Begoña. I got either "Bad request" or "Not found". Then, after I entered my credit card information in OpenAI, I got the same messages or "Unauthorized". I can log into the OpenAi platform without a problem, but not activate my API key for Trados 2022. I created several API keys and tried with all of them, and with several segments from a project too. I also filled out the "Search from" field.  
    emoji
  • 0 in reply to Rocío Valero

    Hi  ,

    There are several reasons why you are receiving this error, incorrect API key, rate limiting, account suspension, but also could be related to system requiring a proxy connection.

    I've used ChatGPT to help me articulate the response, underneath. Can you review these responses and lets see if we can narrorow down the cause?

    Q: Explain why a user would receive an unauthorized http response from a plugin integration with OpenAI API?

    A: There are several reasons why a user might receive an "unauthorized" response when attempting to integrate with the OpenAI API. Here are some possible explanations:

    1. Incorrect API Key: The most common reason for an "unauthorized" response is an incorrect API key. OpenAI requires an API key for authentication purposes, and if the key is incorrect, the API will reject the request. Developers should ensure that they are using the correct API key for their integration.

    2. Missing Permissions: OpenAI's API is divided into several endpoints, each with its own set of permissions. Developers should ensure that their API key has the necessary permissions to access the endpoint they are trying to use.

    3. Rate Limiting: OpenAI limits the number of requests that can be made to its API within a certain timeframe. If a developer exceeds this limit, the API will return an "unauthorized" response. Developers should ensure that they are not making too many requests within a short period of time.

    4. Account Suspension: In rare cases, OpenAI may suspend a developer's account for violating its terms of service or engaging in abusive behavior. If a developer's account is suspended, they will receive an "unauthorized" response when attempting to access the API.

    Q: If the user's computer requires a proxy configuration to connect to the internet, could this also be problematic when connecting to OpenAI API?

    A: Yes, if the user's computer requires a proxy configuration to connect to the internet, it could cause issues when connecting to the OpenAI API.

    A proxy server acts as an intermediary between a client (such as a user's computer) and a server (such as the OpenAI API). When a user's computer is configured to use a proxy server to connect to the internet, all traffic from the user's computer is routed through the proxy server. This can cause issues if the proxy server is not properly configured to allow connections to the OpenAI API.

    If the user's proxy server is not properly configured to allow connections to the OpenAI API, the API requests from the user's computer may be blocked by the proxy server. In this case, the developer would need to work with the user to properly configure the proxy server to allow connections to the OpenAI API.

    In addition, if the OpenAI API requires authentication via an API key, the developer would need to ensure that the API key is properly configured to work with the proxy server. This may require additional configuration on the user's part, such as configuring the proxy server to allow the API key to be passed through to the OpenAI API.

    Overall, connecting to the OpenAI API through a proxy server can add an extra layer of complexity to the integration process, but it is possible to work around these issues with proper configuration and troubleshooting.

    Q: Could it also be related to a country not having access to OpenAI API?

    A: Yes, it's possible that a country not having access to the OpenAI API could result in an "unauthorized" response for a developer trying to integrate with the API.
    emoji
Reply
  • 0 in reply to Rocío Valero

    Hi  ,

    There are several reasons why you are receiving this error, incorrect API key, rate limiting, account suspension, but also could be related to system requiring a proxy connection.

    I've used ChatGPT to help me articulate the response, underneath. Can you review these responses and lets see if we can narrorow down the cause?

    Q: Explain why a user would receive an unauthorized http response from a plugin integration with OpenAI API?

    A: There are several reasons why a user might receive an "unauthorized" response when attempting to integrate with the OpenAI API. Here are some possible explanations:

    1. Incorrect API Key: The most common reason for an "unauthorized" response is an incorrect API key. OpenAI requires an API key for authentication purposes, and if the key is incorrect, the API will reject the request. Developers should ensure that they are using the correct API key for their integration.

    2. Missing Permissions: OpenAI's API is divided into several endpoints, each with its own set of permissions. Developers should ensure that their API key has the necessary permissions to access the endpoint they are trying to use.

    3. Rate Limiting: OpenAI limits the number of requests that can be made to its API within a certain timeframe. If a developer exceeds this limit, the API will return an "unauthorized" response. Developers should ensure that they are not making too many requests within a short period of time.

    4. Account Suspension: In rare cases, OpenAI may suspend a developer's account for violating its terms of service or engaging in abusive behavior. If a developer's account is suspended, they will receive an "unauthorized" response when attempting to access the API.

    Q: If the user's computer requires a proxy configuration to connect to the internet, could this also be problematic when connecting to OpenAI API?

    A: Yes, if the user's computer requires a proxy configuration to connect to the internet, it could cause issues when connecting to the OpenAI API.

    A proxy server acts as an intermediary between a client (such as a user's computer) and a server (such as the OpenAI API). When a user's computer is configured to use a proxy server to connect to the internet, all traffic from the user's computer is routed through the proxy server. This can cause issues if the proxy server is not properly configured to allow connections to the OpenAI API.

    If the user's proxy server is not properly configured to allow connections to the OpenAI API, the API requests from the user's computer may be blocked by the proxy server. In this case, the developer would need to work with the user to properly configure the proxy server to allow connections to the OpenAI API.

    In addition, if the OpenAI API requires authentication via an API key, the developer would need to ensure that the API key is properly configured to work with the proxy server. This may require additional configuration on the user's part, such as configuring the proxy server to allow the API key to be passed through to the OpenAI API.

    Overall, connecting to the OpenAI API through a proxy server can add an extra layer of complexity to the integration process, but it is possible to work around these issues with proper configuration and troubleshooting.

    Q: Could it also be related to a country not having access to OpenAI API?

    A: Yes, it's possible that a country not having access to the OpenAI API could result in an "unauthorized" response for a developer trying to integrate with the API.
    emoji
Children