tencent cloud

File Dialogue (Real-Time Document Parsing + Dialogue)
Download PDF
Last updated: 2025-08-27 15:16:10
File Dialogue (Real-Time Document Parsing + Dialogue)
Last updated: 2025-08-27 15:16:10
Download PDF

Overall Introduction

During the dialogue, you can also upload documents to summarize files and perform content extraction.

File Q&A:

Note:
With product capability iteration, limits on file type and file size will gradually open. Refer to the Intelligent Agent development platform page for restrictions.
Document QA requires document parsing, parameter population, and uses WebSocket or HTTP SSE for dialogue.

3 Document QA Implementation Steps

For knowledge QA, if you need to upload documents for real-time QA, you must first connect to the real-time document parsing API. The process is as follows:
1. Call the DescribeStorageCredential API to get temporary key.
2. Upload to COS using the SDK with a temporary key.
Note:
The method of operating COS on the Tencent Cloud Agent Development Platform (Tencent Cloud ADP) may not be the same as the direct method of using a fixed key. For detailed steps, please refer to the Tencent Cloud Agent Development Platform COS Operation Guide.
3. Call the real-time document parsing docParse API to get the doc_id.
4. Fill parameters and use WebSocket or HTTP SSE for dialogue.

3.1 Real-Time Document Parsing

Real-time document parsing API address: https://wss.lke.tencentcloud.com/v1/qbot/chat/docParse
Request Method: POST.
3.1.1 Request Parameter
Place it in the HTTP Body and send it in the form of JSON, as follows:
Name
Type
Required or Not
Description
session_id
string(64)
Yes
Session ID, used to identify a session (provided by an external system, it is advisable for different user clients to import different session IDs, otherwise messages from different users within the same application may get mixed up).
Parameter length: 2-64 characters
Verification rule: ^[a-zA-Z0-9_-]{2,64}$. You can use uuid to generate this value.
uuid example: 1b9c0b03-dc83-47ac-8394-b366e3ea67ef
Note:
The session_id for document parsing should be consistent with the session. If a multi-round session involves multiple document uploads, the session_id must remain the same and will be validated during the session.
bot_app_key
string(8)
Yes
Application key (provided by operations)
request_id
string(255)
Yes
Unique request ID. Recommend using UUID to ensure uniqueness.
cos_bucket
string
Yes
Get the cos bucket from the API response for obtaining a temporary key.
file_type
string
Yes
File type (txt|doc|docx|pdf|ppt|pptx) Example: txt|doc|docx|pdf|ppt|pptx
file_name
string
Yes
File Name
Example: test.docx
cos_url
string
Yes
Platform cos path, maintain parameter consistency with the UploadPath parameter in the DescribeStorageCredential API query
Example: /corp/1750375931926544384/1750376442139246592/doc/AaCIYEATBTYUQXDfXOTN-1807688648286535680.txt
cos_hash
string
Yes
cos_hash x-cos-hash-crc64ecma Verify the consistency between the file uploaded to the cloud and the local file by checking the CRC64 code in the header. After successful upload to COS, obtain from the return header.
e_tag
string
Yes
ETag, short for Entity Tag, is an information Tag that identifies the object content when the object is created. It can be used to check whether the content of the object has changed. After successful upload to cos, obtain it from the return header.

Example value: "6886efe263f34c9f9401c2d910b02635".
size
string
Yes
File size
Note:
This field is of string type.
3.1.2 Calling the API Using Curl
curl --location 'https://wss.lke.tencentcloud.com/v1/qbot/chat/docParse' \\
--header 'Content-Type: application/json' \\
--data '{
  "session_id": "<your session_id>",
  "request_id": "<random uuid>",
  "cos_bucket": "lke-realtime-intl-1251316161",
  "file_type": "docx",
  "file_name": "test.docx",
  "cos_url": "/corp/1750375931926544384/1750376442139246592/doc/AaCIYEATBTYUQXDfXOTN-1807688648286535680.txt",
  "e_tag": "\\"6886efe263f34c9f9401c2d910b02635\\"",
  "cos_hash": "6138891591882964610",
  "size": "355",
  "bot_app_key": "<your appkey>"
}'
3.1.3 Postman Call Example


3.1.4 Response Parameter
SSE streaming return
Name
Type
Description
session_id
string(64)
Session ID, same as the session_id when making a request
trace_id
string
Unique ID returned
is_final
bool
Message output completed
doc_id
string
Document parsing API response doc_id
process
int32
Current progress, integer, value 100 means Successfully Ended
status
string
Status: PARSING, SUCCESS, FAILED
timestamp
int64
timestamp, unit: seconds
error_message
string
error information return on error
3.1.5 Response Example
{"type":"parsing","payload":{"doc_id":"0","error_message":"","is_final":false,"process":0,"session_id":"c7852s9d-aba8-4ee8-9c88-d65f28ddbc47","status":"PARSING","timestamp":1719821535,"trace_id":"1f1e5bfc9a3588d3abc62b9729fc6f62"},"message_id":"1b28b359-203e-4dbc-a103-6d92629cb1e0"}

{"type":"parsing","payload":{"doc_id":"0","error_message":"","is_final":false,"process":2,"session_id":"c7852s9d-aba8-4ee8-9c88-d65f28ddbc47","status":"PARSING","timestamp":1719821535,"trace_id":"1f1e5bfc9a3588d3abc62b9729fc6f62"},"message_id":"60c2a29a-7658-4186-90a9-d81c8c0b14b4"}

{"type":"parsing","payload":{"doc_id":"0","error_message":"","is_final":false,"process":85,"session_id":"c7852s9d-aba8-4ee8-9c88-d65f28ddbc47","status":"PARSING","timestamp":1719821536,"trace_id":"1f1e5bfc9a3588d3abc62b9729fc6f62"},"message_id":"65ca6da3-8909-42c4-9ea1-4a09be299a7b"}

{"type":"parsing","payload":{"doc_id":"1807688654434383264","error_message":"","is_final":true,"process":100,"session_id":"c7852s9d-aba8-4ee8-9c88-d65f28ddbc47","status":"SUCCESS","timestamp":1719821536,"trace_id":"1f1e5bfc9a3588d3abc62b9729fc6f62"},"message_id":"43046854-c596-45f5-9195-3df4f82a67ff"}

3.2 Document Dialogue Parameter Example

To concatenate a file COS address, follow these steps: 
  https:// +
   {DescribeStorageCredential.Response.Bucket} + 
   "." + 
   {DescribeStorageCredential.Response.Type} +
   "." + 
   {DescribeStorageCredential.Response.Region} + 
   ".myqcloud.com" + 
   {DescribeStorageCredential.Response.UploadPath}
Real-time document without content:
{
    "payload": {
        "request_id": "LkfnMf5IrS-4486169698",
        "session_id": "c60f0463-0176-4c15-a236-e4cbb6c21f97",
        "file_infos": [
            {
                "doc_id": "1833044072669409152",
                "file_name": "Riverside Scenery",
                "file_type": "docx",
                "file_size": "34859",
                "file_url": "https://lke-realtime-intl-1251316161.cos.ap-jakarta.myqcloud.com/corp/1753030485940633600/1781229014471147520/doc/xxxxxxx.docx"
            }
        ],
        "content": ""
    }
}
Real-time document with content:
{
    "payload": {
        "request_id": "XCBLyiWwYV-9639940128",
        "session_id": "c60f0463-0176-4c15-a236-e4cbb6c21f97",
        "file_infos": [
            {
                "doc_id": "1833044598014003968",
                "file_name": "test",
                "file_type": "docx",
                "file_size": "34859",
            }
        ],
        "content": "Extract the main points from the document"
    }
}

3.3 Special Note

After parsing the document is completed, assemble it into the file_infos field for WebSocket or HTTP SSE dialogue, then call the dialogue to use it. Here are some simple file_infos field examples.
Note:
1. doc_id and file_size are of string type. If the input is int, it will return a parameter error.
2. file_name do not include the file suffix.
3. Keep the session_id in the dialogue consistent with the session_id passed in the docParse API call, otherwise it will be unable to retrieve the passed-in file.
4. Real-time document parsing has session round limits for uploaded documents. Session rounds should be consistent with the context rounds set in page configuration. The default timeliness is 24h. If there is a new dialog based on the document within 24h, it will renew for another 24h. Do not repeatedly use the same document id for QA.

4 Image QA and Document QA Demo

Note:
Other programming languages have no Demo. See document and existing demos to implement your own.
The purpose of Demo is rapid verification. It uses HTTP SSE dialogue method. Users can select Websocket dialogue method based on actual business need.

Was this page helpful?
You can also Contact Sales or Submit a Ticket for help.
Yes
No

Feedback