What is the endpoint for [AI50]Patent Large Model(Pat GPT)?

The [AI50]Patent Large Model(Pat GPT) endpoint is POST https://connect.patsnap.com/chat/pat-gpt-stream.

Where can I find the OpenAPI schema for [AI50]Patent Large Model(Pat GPT)?

The OpenAPI schema is available at /openapi.json#/paths/~1chat~1pat-gpt-stream/post. You can also browse the full specification at /openapi.json.

[AI50]Patent Large Model(Pat GPT)

Q: What data can [AI50]Patent Large Model(Pat GPT) return?

[AI50]Patent Large Model(Pat GPT) It supports inputting technical questions or questions related to patents. The Patent Large Model (Pat GPT) aims to intelligently retrieve, analyze, and mine data in response to the posed questions, providing relevant patent information, trend analysis, and technical evaluations. See the Response Schema and Success Response Example on this page for the full structure.

post

https://connect.patsnap.com/chat/pat-gpt-stream

Try in Sandbox

It supports inputting technical questions or questions related to patents. The Patent Large Model (Pat GPT) aims to intelligently retrieve, analyze, and mine data in response to the posed questions, providing relevant patent information, trend analysis, and technical evaluations.

The interface charges based on the total length of tokens consumed after the model invocation is complete, and the token count is calculated using tiktoken.

Request Parameters

List of parameters supported by this API endpoint

Name	Type	Example	Description
`query` Required	`string`	`What is the technology method of the patent with publication number CN109213437A?`	User question Note: No more than 30000 character.
`stream`	`boolean`	`true`	When the interface returns results, whether to require streaming response: true: Represents needed false: Represents not needed Default value is true.

Response Schema

Structure of the API response data

Field Name	Type	Example	Description
`data`	`object`	-	response data
`output`	`object`	`Please check the form: AiPatGptOutPut`	The invocation result information for the patent large model includes the conversation result text
`usage`	`object`	`Please check the form: AiPatGptUsage`	Measurement information indicating the consumption of metered data for this request
`input_tokens`	`integer<int32>`	`20`	The length of the user's question after tokenization.
`total_tokens`	`integer<int32>`	`1520`	The total length of tokens consumed after the model invocation is complete.
`output_tokens`	`integer<int32>`	`1500`	The length of the text generated by the model after tokenization.
`status`	`string`	`finished`	Model Return Status Note: When status = "running", the system is outputting via SSE, When status = "finished", the request has ended, When status = "length", the generated content exceeds the model's maximum length.
`content`	`string`	`根据公开号为CN109213437A的`	Conversation result
`references`	`array`	`Please check the form: AiPatGptReference`	Reference materials for model output results.
`text`	`string`	`text`	Introduction to reference materials
`type`	`string`	`patent`	Types of reference materials include patent (专利), paper (文献), and website (网页).
`value`	`string`	`72fbb693-366a-4e50-bcd4-56d699f6c316`	Reference material associated ID, 1) When type is 'patent', the value is 'patent_id' 2) When type is 'paper', the value is 'paper_id' 3) When type is 'website', the value is the 'url-link'
`status` Required	`boolean`	`false`	Status
`error_msg`	`string`	`The request parameter format is incorrect！`	Error Message
`error_code` Required	`integer`	`0`	Error Code

Success Response Example

Example of a successful API response

JSON

{
  "data": {
    "output": {
      "usage": {
        "input_tokens": 20,
        "total_tokens": 1520,
        "output_tokens": 1500
      },
      "status": "finished",
      "content": "根据公开号为CN109213437A的"
    },
    "references": [
      {
        "text": "text",
        "type": "patent",
        "value": "72fbb693-366a-4e50-bcd4-56d699f6c316"
      }
    ]
  },
  "status": true,
  "error_code": 0
}

Error Codes

List of possible error codes returned by this endpoint

Business Errors

Error Code	Description
`68300004`	Invalid parameter!
`68300005`	Search api failure!
`68300006`	Analytic basic access error!
`68300007`	Bad request!
`68300008`	Service error, please try again later!
`68300010`	The file does not comply with upload specifications!

Platform Errors

Error Code	Description
`67200000`	API call exceeds the total limit set by the platform!
`67200001`	API call exceeds the total limit set by the platform!
`67200002`	The current call rate is too fast, exceeding the current configuration limit QPS!
`67200003`	The key and secret parameters for applying for the token are incorrect or the client has been disabled!
`67200004`	The requested api does not have permission. Please contact our support personnel!
`67200005`	Insufficient account balance/number of calls!
`67200006`	The client has exceeded the activation validity period!
`67200007`	The current call exceeds the configured usage limit of the day!
`67200008`	Please check if the required apikey in the query parameter has been transmitted!
`67200009`	The apikey does not match the passed bearerToken. Please check if a valid token is being used!
`67200012`	The request is illegal!
`67200100`	The current server status is busy, request response timeout!
`67200101`	The API requested currently does not exist. Please check the request path!

HTTP Status Codes

Status Code	Description
`0`	Success
`33610400`	Illegal content in user input
`33610500`	Illegal content in the returned results of the model
`33610600`	Internal system exception

Performance Metrics

Expected performance characteristics for this endpoint

Normal Response Time

5000 ms

Max Response Time

10000 ms