wauldo 0.1.1

Official Python SDK for Wauldo — Verified AI answers from your documents

Wauldo Python SDK

Verified AI answers from your documents. Every response includes source citations, confidence scores, and an audit trail — or we don't answer at all.

Official Python SDK for the Wauldo API — the AI inference layer with smart model routing and zero hallucinations.

Why Wauldo?

• Zero hallucinations — every answer is verified against source documents
• Smart model routing — auto-selects the cheapest model that meets quality (save 40-80% on AI costs)
• One API, 7+ providers — OpenAI, Anthropic, Google, Qwen, Meta, Mistral, DeepSeek with automatic fallback
• OpenAI-compatible — swap your base_url, keep your existing code
• Full audit trail — confidence score, grounded status, model used, latency on every response

Quick Start

from wauldo import HttpClient

client = HttpClient(base_url="https://api.wauldo.com", api_key="YOUR_API_KEY")

reply = client.chat_simple("auto", "What is Python?")
print(reply)

Installation

pip install wauldo

Requirements: Python 3.9+

Features

Chat Completions

from wauldo import HttpClient, ChatRequest, HttpChatMessage

client = HttpClient(base_url="https://api.wauldo.com", api_key="YOUR_API_KEY")

request = ChatRequest(
    model="auto",
    messages=[
        HttpChatMessage.system("You are a helpful assistant."),
        HttpChatMessage.user("Explain Python decorators"),
    ],
)
response = client.chat(request)
print(response.choices[0].message.content)

RAG — Upload & Query

# Upload a document
upload = client.rag_upload(content="Contract text here...", filename="contract.txt")
print(f"Indexed {upload.chunks_count} chunks")

# Query with verified answer
result = client.rag_query("What are the payment terms?")
print(f"Answer: {result.answer}")
print(f"Confidence: {result.get_confidence():.0%}")
print(f"Grounded: {result.audit.grounded}")
for source in result.sources:
    print(f"  Source ({source.score:.0%}): {source.content[:80]}")

Streaming (SSE)

from wauldo import ChatRequest, HttpChatMessage

request = ChatRequest(model="auto", messages=[HttpChatMessage.user("Hello!")])
for chunk in client.chat_stream(request):
    print(chunk, end="", flush=True)

Conversation Helper

conv = client.conversation(system="You are an expert on Python.", model="auto")
reply = conv.say("What are list comprehensions?")
follow_up = conv.say("Give me a nested example")

Error Handling

from wauldo import WauldoError, ServerError, AgentTimeoutError

try:
    response = client.chat(ChatRequest.quick("auto", "Hello"))
except ServerError as e:
    print(f"Server error: {e}")
except AgentTimeoutError:
    print("Request timed out")
except WauldoError as e:
    print(f"SDK error: {e}")

RapidAPI

client = HttpClient(
    base_url="https://api.wauldo.com",
    headers={
        "X-RapidAPI-Key": "YOUR_RAPIDAPI_KEY",
        "X-RapidAPI-Host": "smart-rag-api.p.rapidapi.com",
    },
)

Get your free API key (300 req/month): RapidAPI

Links

• Website
• Documentation
• Live Demo
• Cost Calculator
• Status

Contributing

Found a bug? Have a feature request? Open an issue.

License

MIT — see LICENSE