diff --git a/api.py b/api.py index 006dadd..3b4221c 100644 --- a/api.py +++ b/api.py @@ -23,8 +23,8 @@ MODEL_CACHE = {} # --- Pydantic Models --- class PredictRequest(BaseModel): prompt: str - temperature: float = 0.7 - n: int = 3 + temperature: float = 1.6 + n: int = 4 length: int = 5 @@ -84,6 +84,14 @@ async def predict(request: PredictRequest): return PredictResponse(prediction=prediction) +@app.get("/api") +async def api_docs(): + """ + API documentation page. + """ + return FileResponse(os.path.join(UI_DIR, "api.html")) + + # --- Static Files and Root --- app.mount("/ui", StaticFiles(directory=UI_DIR), name="ui") diff --git a/ui/api.html b/ui/api.html new file mode 100644 index 0000000..42d9fa8 --- /dev/null +++ b/ui/api.html @@ -0,0 +1,395 @@ + + + + + + Kreatyw - API Documentation + + + + + +
+ + + + + + Back to Editor + + +
+

Kreatyw API

+

Text generation API powered by N-gram language models

+
+ +
+

Overview

+

+ The Kreatyw API provides a simple REST endpoint for + generating text continuations using N-gram language models. + The API uses Markov chains trained on source texts to + predict and generate coherent text sequences. +

+
+ +
+

Base URL

+
+ 
http://localhost:8000
+
+
+ +
+

Endpoints

+ +

POST /api/predict

+

Generate text continuation based on a given prompt.

+ +

Request Body

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ParameterTypeRequiredDescription
promptstring + Required + The starting text to continue from
ninteger + Optional + + N-gram size (2-5). Default: 4. Higher values + produce more coherent but less creative text. +
+ temperature + float + Optional + + Sampling temperature (0.1-2.0). Default: 1.6. + Higher values increase randomness. +
lengthinteger + Optional + + Number of words to generate (1-500). Default: 5. +
+ +

Response

+ + + + + + + + + + + + + + + +
FieldTypeDescription
predictionstringThe generated text continuation
+ +

Example Request

+
+ 
+curl -X POST http://localhost:8000/api/predict \
+  -H "Content-Type: application/json" \
+  -d '{
+    "prompt": "Once upon a time",
+    "n": 4,
+    "temperature": 1.2,
+    "length": 20
+  }'
+
+ +

Example Response

+
+ 
+{
+  "prediction": "in a kingdom far away there lived a brave knight who sought adventure..."
+}
+
+ +

JavaScript Example

+
+ 
+const response = await fetch('/api/predict', {
+  method: 'POST',
+  headers: {
+    'Content-Type': 'application/json'
+  },
+  body: JSON.stringify({
+    prompt: 'The old wizard',
+    n: 3,
+    temperature: 0.8,
+    length: 15
+  })
+});
+
+const data = await response.json();
+console.log(data.prediction);
+
+ +

Python Example

+
+ 
+import requests
+
+response = requests.post('http://localhost:8000/api/predict',
+    json={
+        'prompt': 'In the beginning',
+        'n': 4,
+        'temperature': 1.0,
+        'length': 25
+    }
+)
+
+result = response.json()
+print(result['prediction'])
+
+
+ +
+

Model Parameters

+ +

N-gram Size (n)

+

+ Controls the context window size. Higher values use more + context words to predict the next word: +

+ + +

Temperature

+

Controls the randomness of predictions:

+ +
+ +
+

Error Handling

+

The API returns standard HTTP status codes:

+ +
+ +
+

Rate Limits

+

+ Currently, there are no rate limits imposed on the API. For + production use, consider implementing appropriate rate + limiting. +

+
+
+ +