ChatX

Frequently Asked

  1. Missing API Mode config entry

    2. Please click on tab-3 [Settings] > [Refresh Server] and then kill ChatX App and then re-open, it will be fixed.

  2. Chat reply HTTP 403 / 503 error code

    3. This was a network congestion error caused by too many users. The server has now been repaired and will not appear again in the future, please enjoy your chat with AI.

  3. No network connection error? Please click [Settings] - [Advanced Settings] - [Permission Management] and select [Wireless and Cellular Data] to fix the problem.

What is Word Mode?

This is the default mode of ChatX, no need to have API Key, directly based on ChatX's high speed server for requesting, calculated by usage, you can top up word count balance on demand.

  • Word count consumption includes: number of words sent + number of words received
  • Words sent in a single session = Message sent + Prompt content + History (number of entries can be set)
  • Consumption rate for 4.0 is 10x times higher than for 3.5

What is the use of Chat Memory?

By sending a portion of the history to the AI with each chat, the AI has contextual memory to better process the generated content. Since an extra history is sent each time, an extra word count is consumed.

The number of memory bars can be set, or you can clear the memory and start a new conversation at any time by clicking 1/10 on the toolbar.

How to write great prompts?

  1. Clear and concise language: Use simple and straightforward language when writing prompts, avoiding jargon or complex sentence structures. Make sure the meaning of the prompts is clear and easy to understand for users to respond to.
  2. Specific questions: Ensure your prompts are specific and guide users to provide specific information. Avoid using overly broad or vague questions, such as "What do you like?", which can be confusing and leave users unsure of what to answer.
  3. Casual tone: Use a friendly and relaxed tone when writing prompts, making users feel comfortable and more likely to build a good relationship with your model. Avoid using language that is challenging or aggressive, which can make users feel uncomfortable or hostile.
  4. Constant experimentation: Writing prompts is a skill that requires constant experimentation and improvement. Use different types of prompts to understand different response patterns and reactions to improve the flow and effectiveness of the conversation.
  5. Personalization: Write prompts based on the user's needs and interests, making them feel that you care about their questions and feelings. By understanding the user's situation and goals, you can create more personalized prompts to improve the user experience and satisfaction.
‣
Examples:
  1. You will play the role of [character name], a [profession]. Can you tell me some basic information about [the profession/role]?
  2. You will play the role of [character name], a [nationality]. Can you share with me some cultural and customary information about yourself?
  3. You will play the role of [character name], a [historical era] figure. Can you share with me some historical events from your time?
  4. You will play the role of [character name], an [animal]. Can you tell me some information about your habits and natural environment?
  5. You will play the role of [character name], a [fictional character]. Can you tell me some of your story and background?
  6. You will play the role of [character name], a [superhero]. Can you share with me some of your superpowers and skills?
  7. You will play the role of [character name], a [historical figure]. Can you share with me some of your achievements and influences?
  8. You will play the role of [character name], a [scientist]. Can you share with me some of your inventions and research?

Other Features Docs

‣
Error Code：401 / 404 / 429
‣
401 - Invalid Authentication

This error message indicates that your authentication credentials are invalid. This could happen for several reasons, such as:

  • You are using a revoked API key.
  • You are using a different API key than one under the requesting organization.
  • You are using an API key that does not have the required permissions for the endpoint you are calling.

To resolve this error, please follow these steps:

  • Check that you are using the correct API key and organization ID in your request header. You can find your API key and organization ID in your account settings here.
  • If you are unsure whether your API key is valid, you can generate a new one here. Make sure to replace your old API key with the new one in your requests and follow our best practices.
‣
401 - Incorrect API key provided

This error message indicates that the API key you are using in your request is not correct. This could happen for several reasons, such as:

  • You are using a typo or an extra space in your API key.
  • You are using an API key that belongs to a different organization.
  • You are using an API key that has been deleted or deactivated
  • Your API key might be cached.

To resolve this error, please follow these steps:

  • Try clearing your browser's cache and cookies then try again.
  • Check that you are using the correct API key in your request header. Follow the instructions in our Authentication section to ensure your key is correctly formatted (i.e. 'Bearer <API_KEY>')
  • If you are unsure whether your API key is correct, you can generate a new one here. Make sure to replace your old API key in your codebase and follow our best practices.
‣
404 - You must be a member of an organization to use the API

This error message indicates that your account is not part of an organization. This could happen for several reasons, such as:

  • You have left or been removed from your previous organization.
  • Your organization has been deleted.

To resolve this error, please follow these steps:

  • If you have left or been removed from your previous organization, you can either request a new organization or get invited to an existing one.
  • To request a new organization, reach out to us via help.openai.com
  • Existing organization owners can invite you to join their organization via the Members Panel.
‣
429 - Rate limit reached for requests

This error message indicates that you have hit your assigned rate limit for the API. This means that you have submitted too many tokens or requests in a short period of time and have exceeded the number of requests allowed. This could happen for several reasons, such as:

  • You are using a loop or a script that makes frequent or concurrent requests.
  • You are sharing your API key with other users or applications.
  • You are using a free plan that has a low rate limit.

To resolve this error, please follow these steps:

  • Pace your requests and avoid making unnecessary or redundant calls.
  • If you are using a loop or a script, make sure to implement a backoff mechanism or a retry logic that respects the rate limit and the response headers. You can read more about our rate limiting policy and best practices here.
  • If you are sharing your organization with other users, note that limits are applied per organization and not per user. It is worth checking the usage of the rest of your team as this will contribute to this limit.
  • If you are using a free or low-tier plan, consider upgrading to a pay-as-you-go plan that offers a higher rate limit.
‣
429 - You exceeded your current quota, please check your plan and billing details.

This error message indicates that you have hit your maximum monthly spend (hard limit) for the API. This means that you have consumed all the credits or units allocated to your plan and have reached the limit of your billing cycle. This could happen for several reasons, such as:

  • You are using a high-volume or complex service that consumes a lot of credits or units per request.
  • You are using a large or diverse data set that requires a lot of requests to process.
  • Your limit is set too low for your organization’s usage.

To resolve this error, please follow these steps:

  • Check your current quota in your account settings here. You can see how many tokens your requests have consumed here.
  • If you are using a free plan, consider upgrading to a pay-as-you-go plan that offers a higher quota.
  • If you need a quota increase, you can apply for one here. We will review your request and get back to you as soon as possible.
‣
429 - The engine is currently overloaded. Please try again later.

This error message indicates that our servers are experiencing high traffic and are unable to process your request at the moment. This could happen for several reasons, such as:

  • There is a sudden spike or surge in demand for our services.
  • There is scheduled or unscheduled maintenance or update on our servers.
  • There is an unexpected or unavoidable outage or incident on our servers.

To resolve this error, please follow these steps:

  • Retry your request after a brief wait. We recommend using an exponential backoff strategy or a retry logic that respects the response headers and the rate limit. You can read more about our best practices here.
  • Check our status page for any updates or announcements regarding our services and servers.
  • If you are still getting this error after a reasonable amount of time, please contact us for further assistance. We apologize for any inconvenience and appreciate your patience and understanding.

Contact