> For the complete documentation index, see [llms.txt](https://docs.cherry-ai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherry-ai.com/docs/en-us/question-contact/questions.md). # FAQ ## Common error codes * **4xx (client error status codes)**: usually indicates a request syntax error, authentication failure, or authorization failure, etc., so the request cannot be completed. * **5xx (server error status codes)**: usually indicates a server-side error, such as the server being down or request processing timing out. | Error code | Possible cases | Solution | | ---------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **400** | Invalid request body format, etc. |

Check the error content returned by the conversation or Console\

\[Common case 1]: if it is a Gemini model, you may need to bind a card;
\[Common case 2]: data size exceeded the limit, commonly seen in vision models; this error code is returned when the image size exceeds the upstream single-request traffic limit;
\[Common case 3]: unsupported parameters were added or parameters were entered incorrectly. Try creating a new clean assistant to test whether it works normally;
\[Common case 4]:The context exceeds the limit; clear the context, start a new conversation, or reduce the number of context turns.

| | **401** | Authentication failed: the model is unsupported or the service provider account has been banned, etc. | Contact or check the account status with the corresponding service provider | | **403** | No permission for the requested operation | Based on the error information returned by the conversation or[Console](#kong-zhi-tai-bao-cuo-cha-kan-fang-fa)error message prompt, take the corresponding action | | **404** | Requested resource not found | Check the request path, etc. | | **422** | The request format is correct, but the semantics are wrong | This kind of error can be parsed by the server, but it cannot be processed. It is common with JSON semantic errors (for example: null values; a value is required to be a string, but a number or boolean is used instead). | | **429** | Request rate has reached the limit | The request rate (TPM or RPM) has reached the limit; wait a moment before trying again | | **500** | Internal server error, unable to complete the request | If it persists, contact the upstream service provider | | **501** | The server does not support the requested function and cannot complete the request | | | **502** | A server acting as a gateway or proxy received an invalid response from the remote server while attempting to process the request | | | **503** | Due to overload or system maintenance, the server is temporarily unable to handle the client's request. The length of the delay may be included in the server's Retry-After header information | | | **504** | The server acting as a gateway or proxy did not obtain the request from the remote server in time | | *** ## How to view console errors * After clicking the Cherry Studio client window, press the shortcut key Ctrl + Shift + I(Mac:Command + Option + I) {% hint style="info" %} * The currently active window must be the Cherry Studio client window to bring up the console; * You need to open the console first, and then click Test or initiate a conversation request before request information can be collected. {% endhint %} - In the popped-up console window, click `Network` → Click the last item marked red in ② `×` of `completions`*(when errors occur in conversations, translations, model connectivity checks, etc.)* or `generations`*(when errors occur in drawing)* → click`Response`View the full returned content (the area marked ④ in the image). > If you cannot determine the cause of the error, please send a screenshot of this interface to [the official discussion group](https://t.me/CherryStudioAI) for help.
This checking method can obtain error information not only during conversations, but also when testing models, adding knowledge bases, drawing, etc. In any case, you need to open the debugging window first, then perform the request operation to obtain request information. {% hint style="info" %} The name in the Name field (② in the image above) will vary depending on the scenario Conversation, translation, model check:`completions` Drawing:`generations` Knowledge base creation:`embeddings` {% endhint %} *** ## Formula not rendered / formula rendering error * If the formula is not rendered and the formula code is displayed directly, check whether the formula has delimiters > **Delimiter usage** > > *Inline formula* > > * Use a single dollar sign: `$formula$` > * or use`\(` and `\)`, for example:`\(formula\)` > > *Standalone formula block* > > * Use double dollar signs: `$$formula$$` > * or use `\[formula\]` > * Example: `$$\sum_{i=1}^n x_i$$`\ > $$\sum\_{i=1}^n x\_i$$ * Formula rendering error / garbled text; commonly occurs when Chinese content is included in the formula. Try switching the formula engine to KateX. *** ## Unable to create knowledge base / failed to obtain embedding dimensions 1. Model status unavailable > Confirm whether the service provider supports this model, or confirm whether the service status for this model is normal. 2\. A non-embedding model was used *** ## The model cannot process images / cannot upload or select images First, confirm whether the model supports image recognition. Cherry Studio categorizes popular models, and models with a small eye icon after the name support image recognition. Image-recognition models support uploading image files. If the model function is not matched correctly, you can find the model in the corresponding service provider's model list, click the settings button after its name, and check the image option. For specific model information, you can check the corresponding service provider's documentation. As with embedding models, models that do not support vision do not need to forcibly enable the image function; checking the image option will not have any effect. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.cherry-ai.com/docs/en-us/question-contact/questions.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.