Skip to main content

Python SDK for Reservoir video querying system

Project description

Reservoir SDK

A simple Python client for the Reservoir video querying system.

Installation

pip install reservoir-sdk

Authentication

You must provide an API key to use the Reservoir SDK. The API key can be passed directly to the client or set via the RESERVOIR_API_KEY environment variable:

# Directly in code
client = ReservoirClient(api_key="your-api-key-here")

# Or via environment variable
# export RESERVOIR_API_KEY="your-api-key-here"
client = ReservoirClient()  # Will use RESERVOIR_API_KEY env var

Usage

from reservoir_sdk import ReservoirClient

# Initialize with API key
client = ReservoirClient(api_key="your-api-key-here")

# Simple query
result = client.query(
    query_text="People having a conversation",
    max_duration_minutes=5.0,
    min_confidence=0.7
)

print(f"Query submitted! Job ID: {result['job_id']}")
print(f"Check results at: {result['result_url']}")

# Get available models
models = client.get_available_models()
print(f"Available models: {models}")

# List creators
creators = client.list_creators()
print(f"Found {len(creators)} creators")

# Get a specific creator's ID
if creators:
    creator_id = creators[0]['id']
    
    # Query with a specific creator
    result = client.query(
        query_text="People laughing",
        creators_ids=[creator_id],
        max_duration_minutes=2.0
    )
    
    print(f"Creator-specific query submitted! Job ID: {result['job_id']}")

# Check status of a query
status = client.get_query_status(result['job_id'])
print(f"Query status: {status['status']}")

API Reference

Client Initialization

client = ReservoirClient(
    api_key="your-api-key-here",  # Required unless RESERVOIR_API_KEY env var is set
    base_url="http://localhost:8000"  # Optional, defaults to http://localhost:8000
)

Methods

query

Submit a query to search for video segments.

result = client.query(
    query_text="People having a conversation",  # Required
    max_duration_minutes=5.0,  # Optional, defaults to 10.0
    max_chunks=20,  # Optional, defaults to 20
    min_confidence=0.7,  # Optional, defaults to 0.5
    models=["active_speaker", "conversation_confidence"],  # Optional, defaults to all models
    creators_ids=["creator-id-1", "creator-id-2"]  # Optional, defaults to all creators
)

get_query_status

Check the status of a submitted query.

status = client.get_query_status(job_id)

list_creators

Get a list of all available creators.

creators = client.list_creators()

get_available_models

Get a dictionary of available models.

models = client.get_available_models()

Requirements

  • Python 3.7+
  • requests library

Development

To build and install the package locally for development:

git clone https://github.com/yourusername/reservoir-sdk.git
cd reservoir-sdk
pip install -e .

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

reservoir_sdk-0.1.0.tar.gz (6.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

reservoir_sdk-0.1.0-py3-none-any.whl (7.4 kB view details)

Uploaded Python 3

File details

Details for the file reservoir_sdk-0.1.0.tar.gz.

File metadata

  • Download URL: reservoir_sdk-0.1.0.tar.gz
  • Upload date:
  • Size: 6.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.2

File hashes

Hashes for reservoir_sdk-0.1.0.tar.gz
Algorithm Hash digest
SHA256 c43c1b9919a8febdc56c1159ef4b535bf5d125f494b44743fad49c61ad3ecd57
MD5 03e1995634bfd6a2d62f0b515528229e
BLAKE2b-256 84abfcff7f8313b3c3b13628aae3a1012a546e20e692d71f007c9b4f4a728071

See more details on using hashes here.

File details

Details for the file reservoir_sdk-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: reservoir_sdk-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.2

File hashes

Hashes for reservoir_sdk-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 769002385eb0d7db01727639e758e35cac90e41c7d6b726e6769f5991f220cc0
MD5 acaa215ac99cb65658d69b8854f24832
BLAKE2b-256 9e6c666cf9a05fef7fedb507449a3816ea548a9f4cf5319992f4314541a6379f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page