Skip to main content
POST
/
upload
/
upload_text
Upload Markdown
curl --request POST \
  --url https://api.usecortex.ai/upload/upload_text \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "content": "<content>",
  "file_id": "CortexDoc1234",
  "tenant_metadata": {},
  "document_metadata": {}
}'
{
  "file_id": "CortexDoc1234",
  "message": "<string>",
  "success": true
}
Hit the Try it button to try this API now in our playground. It’s the best way to check the full request and response in one place, customize your parameters, and generate ready-to-use code snippets.

Sample Request

curl --request POST \
  --url 'https://api.usecortex.ai/upload/upload_text?tenant_id=tenant_1234&sub_tenant_id=sub_tenant_4567' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "content": "<string>",
  "file_id": "text_doc_123456",
  "tenant_metadata": {},
  "document_metadata": {}
}'
Upload text content directly to your tenant’s knowledge base. The text will be processed, chunked, and indexed for search and retrieval.

Text Processing Pipeline

When you upload text content, it goes through a streamlined processing pipeline optimized for direct text input:

1. Immediate Upload & Queue

  • Your text content is immediately accepted and stored securely
  • It’s added to our processing queue for background processing
  • You receive a confirmation response with a file_id for tracking

2. Text Processing Phase

Our system automatically handles:
  • Content Validation: Ensuring text content is properly formatted and accessible
  • Format Detection: Identifying markdown, plain text, or structured content
  • Text Normalization: Cleaning and standardizing text formatting

3. Intelligent Chunking

  • Text is split into semantically meaningful chunks
  • Chunk size is optimized for both context preservation and search accuracy
  • Overlapping boundaries ensure no information is lost between chunks
  • Metadata is preserved and associated with each chunk

4. Embedding Generation

  • Each chunk is converted into high-dimensional vector embeddings
  • Embeddings capture semantic meaning and context
  • Vectors are optimized for similarity search and retrieval

5. Indexing & Database Updates

  • Embeddings are stored in our vector database for fast similarity search
  • Full-text search indexes are created for keyword-based queries
  • Metadata is indexed for filtering and faceted search
  • Cross-references are established for related content

6. Quality Assurance

  • Automated quality checks ensure processing accuracy
  • Content validation verifies text completeness
  • Embedding quality is assessed for optimal retrieval performance
Processing Time: Text content is typically processed and searchable within 1-3 minutes. Large text blocks (10,000+ words) may take up to 5 minutes. You can check processing status using the document ID returned in the response.
Default Sub-Tenant Behavior: If you don’t specify a sub_tenant_id, the text content will be uploaded to the default sub-tenant created when your tenant was set up. This is perfect for organization-wide content that should be accessible across all departments.
File ID Management: The system uses a priority-based approach for file ID assignment:
  1. First Priority: If you provide a file_id as a direct body parameter, that specific ID will be used
  2. Second Priority: If no direct file_id is provided, the system checks for a file_id in the document_metadata object
  3. Auto-Generation: If neither source provides a file_id, the system will automatically generate a unique identifier

Duplicate File ID Behavior

When you upload text content with a file_id that already exists in your tenant:
  • Overwrite Behavior: The existing text content with the same file_id will be completely replaced with the new content
  • Processing: The new text content will go through the full processing pipeline (validation, chunking, embedding generation, indexing)
  • Search Results: Previous search results and embeddings from the old content will be replaced with the new content
  • Idempotency: Uploading the same text content with the same file_id multiple times is safe and will result in the same final state
Important: When overwriting existing text content, all previous chunks, embeddings, and search indexes associated with that file_id will be permanently removed and replaced. This action cannot be undone.
Example Success Response for Duplicate File ID:
{
  "message": "Text content uploaded successfully. Existing content with file_id 'text_123456' has been overwritten.",
  "file_id": "text_123456",
  "status": "success"
}

Processing Status & Monitoring

After uploading, you can monitor your text content’s processing status:

Immediate Response

Upon successful upload, you’ll receive:
{
  "message": "Text content uploaded successfully",
  "file_id": "doc_123456"
}

Processing States

Your text content will progress through these states:
  • queued: Text content is in the processing queue, waiting to be processed
  • in_progress: Text content is actively being processed (includes validation, chunking, embedding generation, and indexing)
  • success: Text content is fully processed and searchable
  • errored: Processing encountered an error (rare occurrence)
In-Progress Details: While the status shows in_progress, the system is actually performing multiple steps: content validation, format detection, intelligent chunking, embedding generation, and database indexing. These happen sequentially but are all part of the single in_progress state.

When Your Text is Ready

Once processing is complete, your text content will be:
  • Searchable via semantic search and Q&A endpoints
  • Retrievable through our retrieval APIs
  • Available for AI-powered applications
  • Indexed for fast query performance
Important: Don’t attempt to search or retrieve your text content immediately after upload. Wait for processing to complete (typically 1-3 minutes) to ensure optimal results.

Error Responses

All endpoints return consistent error responses following the standard format. For detailed error information, see our Error Responses documentation.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

tenant_id
string
required

Unique identifier for the tenant/organization

Example:

"tenant_1234"

sub_tenant_id
string
default:""

Optional sub-tenant identifier used to organize data within a tenant. If omitted, the default sub-tenant created during tenant setup will be used.

Example:

"sub_tenant_4567"

Body

application/json
content
string
required

The text or markdown content to upload

Example:

"<content>"

file_id
string | null
default:""

Optional file ID for the uploaded content. If not provided, will be generated automatically.

Example:

"CortexDoc1234"

tenant_metadata
object | null

JSON string containing tenant-level document metadata (e.g., department, compliance_tag)

Example: > "{"department":"Finance","compliance_tag":"GDPR"}"

document_metadata
object | null

JSON string containing document-specific metadata (e.g., title, author, file_id). If file_id is not provided, the system will generate an ID automatically.

Example: > "{"title":"Q1 Report.pdf","author":"Alice Smith","file_id":"custom_file_123"}"

Response

Successful Response

file_id
string
required

Unique identifier for the file being processed

Example:

"CortexDoc1234"

message
string
required

Status message indicating document parsing scheduled or update completed

success
boolean
default:true
Example:

true

I