Skip to main content
POST
/
chat
/
v1
/
api
/
document
/
pdf
Chat with a PDF file
curl --request POST \
  --url https://app.skimming.ai/back/chat/v1/api/document/pdf \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "file_id": "abc123-def456-ghi789",
  "question": "What are the main points in this PDF?",
  "streaming": false,
  "model": "gpt-4",
  "model_type": "openai"
}
'
"<string>"

Authorizations

​
Authorization
string
header
required

Bearer token authentication using an API key

Body

application/json
​
file_id
string
required

The file_id returned from ingest endpoint

Example:

"abc123-def456-ghi789"

​
question
string
required

Your question about the content

Example:

"What are the main points discussed in this document?"

​
streaming
boolean
default:true

Whether to stream the response (SSE format)

​
model
enum<string>
default:gpt-4

AI model to use

Available options:
gpt-4,
gpt-4o,
gpt-4o-mini,
gpt-3.5-turbo,
claude-3-opus,
claude-3-sonnet,
claude-3.5-sonnet,
gemini-1.5-pro,
gemini-1.5-flash
Example:

"gpt-4"

​
model_type
enum<string>
default:openai

Model provider

Available options:
openai,
anthropic,
gemini
Example:

"openai"

​
conversation_type
enum<string>
default:single

Type of conversation

Available options:
single,
group
​
max_output
integer

Maximum output tokens

Example:

2000

Response

Successful response

Server-Sent Events stream (when streaming=true)