eai_answers_lib 0.2.0

Library to interact with Expert AI Answers engine

Answers Lib

Library to interact with Expert AI Answers engine.

Installation

pip install eai-answers-lib

Or install with dev dependencies for development:

pip install eai-answers-lib[dev]

Quick Start

from eai_answers_lib import Answers, QueryRequest

# Create Answers client
a = Answers(endpoint="https://your-api.example.com/api")

# Create query request using schema (recommended)
query = QueryRequest(question="What are the effects of dietary insect meal?")

# Execute query
result = a(query, pkg="my_knowledge_base", collection="my_collection")

Usage with Dict (Auto-converted)

from eai_answers_lib import Answers

a = Answers(endpoint="https://your-api.example.com/api")

# Pass as dict - automatically converted to QueryRequest
result = a(
    {"question": "Your question here"},
    pkg="my_knowledge_base",
    collection="my_collection"
)

Query Request Options

The QueryRequest schema supports all API options:

from eai_answers_lib import QueryRequest, QueryImage, QueryParams

query = QueryRequest(
    question="Your question",
    config_name="default",
    user="[e-mail]",
    images=[
        QueryImage(name="image1", data="base64...", mime_type="image/png")
    ],
    params=QueryParams(
        filters=["tag:important"],
        top_k_docs=10,
        debug=True
    ),
    neural={"score_ranges": {...}},
    generative={"generative_answer": True, "stream": False}
)

Authentication

a = Answers(
    endpoint="https://your-api.example.com/api",
    enable_auth=True,
    client_id="your-client-id",
    client_secret="your-client-secret",
    auth_url="https://auth.example.com",
    auth_path="auth",
    realm="your-realm"
)

Environment Variables

• ANSWERS_ENDPOINT - API endpoint URL (required)
• ANSWERS_OWNER_ACCOUNT - Default owner account (default: "default")
• ANSWERS_CLIENT_ID - Client ID for authentication
• ANSWERS_CLIENT_SECRET - Client secret for authentication

Knowledge Base Operations

from eai_answers_lib import Answers

a = Answers(endpoint="https://api.example.com", enable_auth=True)

# List user directories
dirs = a.get_user_dirs("[e-mail]")

# List collections in a directory
collections = a.get_dir_collections("root_dir_id")

# Check if KB exists
exists = a.kb_exists("my_kb")

# Create a new KB
a.add_kb("my_new_kb", "[e-mail]")

# Create collection
collection_id = a.create_collection("my_kb", "My Collection")

Documentation

Build Sphinx documentation:

pip install sphinx sphinx-rtd-theme
sphinx-build -b html docs docs/_build
open docs/_build/index.html