Skip to main content

Summ provides intelligent question-answering and search capabilities across user interivew transcripts.

Project description

Summ

PyPI - Version PyPI - Python Version


Summ uses ChatGPT to provide intelligent question-answering and search capabilities across user transcripts!

Easily surface insights and summarize facts across various dimensions such as department, industry, and role. With the help of natural language processing, the tool can understand and respond to complex questions and queries, making it easy for users to find the information they need.

A tool by @markiewagner and @yasyf.

Installation

pip install summ

You'll need an instance of Redis Stack running. We've found that brew install redis-stack/redis-stack/redis-stack is the fastest way to get up and running.

You'll also need to set two environment variables: OPENAI_API_KEY, and PINECONE_API_KEY

Docs

TODO: Docs on how to customize

License

summ is distributed under the terms of the MIT license.

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

summ-0.0.2.tar.gz (419.9 kB view details)

Uploaded Source

Built Distribution

summ-0.0.2-py3-none-any.whl (17.4 kB view details)

Uploaded Python 3

File details

Details for the file summ-0.0.2.tar.gz.

File metadata

  • Download URL: summ-0.0.2.tar.gz
  • Upload date:
  • Size: 419.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.23.3

File hashes

Hashes for summ-0.0.2.tar.gz
Algorithm Hash digest
SHA256 8878995924a27481a53854ef53eaf7e3ee2e81402559bfa006cbbb5832765379
MD5 d28b689f8d4eb5766403a76eed795109
BLAKE2b-256 34402304e27b93c3e946d41fb9120549512c09d668879fde4a052588954464be

See more details on using hashes here.

File details

Details for the file summ-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: summ-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 17.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.23.3

File hashes

Hashes for summ-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 636665e018b50e65879c871af4c2bef9a8a4e95832a715bb8fbed1d34b61746a
MD5 f9f8c5153a98e8b4123228aef879c497
BLAKE2b-256 be8e650b6f85fadaf1d2a8ccd14a5c91a1b6d3c4e0b215021000c00adab4c121

See more details on using hashes here.

Supported by

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