Query

POST Generate AI Completion

Generate AI completions using relevant document context. The system will automatically retrieve relevant chunks from your documents based on semantic similarity to provide context for the AI model's response.

Parameters:

Field	Type	Required	Default	Description
query	string	Yes	-	The question or prompt
filters	object	No	null	Metadata filters to apply
k	integer	No	4	Number of context chunks to use
min_score	float	No	0.0	Minimum similarity score threshold
max_tokens	integer	No	null	Maximum tokens in completion
temperature	float	No	null	Sampling temperature for completion

Returns: CompletionResponse object with:

• completion: Generated text response

• usage: Token usage statistics (completion_tokens, prompt_tokens, total_tokens)

Python SDK

from databridge import DataBridge

db = DataBridge(uri="your-databridge-uri")

# Generate completion
response = db.query(
    query="What are the main applications of machine learning?",
    filters={"category": "tech"},
    k=3,
    max_tokens=150,
    temperature=0.7
)

print("Answer:", response.completion)
print(f"Total tokens used: {response.usage.total_tokens}")

REST API

curl -X POST "http://localhost:8000/query" \
  -H "Authorization: Bearer your_token" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are the main applications of machine learning?",
    "filters": {
        "category": "tech"
    },
    "k": 3,
    "max_tokens": 150,
    "temperature": 0.7
  }'

Response:

200 Success

{
    "completion": "Based on the retrieved context, machine learning has several key applications...",
    "usage": {
        "completion_tokens": 45,
        "prompt_tokens": 120,
        "total_tokens": 165
    }
}

401 Unauthorized

{
    "detail": "Invalid authentication credentials"
}

422 Validation Error

{
    "detail": [
        {
            "loc": ["body", "query"],
            "msg": "field required",
            "type": "value_error.missing"
        }
    ]
}