Skip to main content

Experimental libraries for conversational analysis with llms.

Project description

Conversational analysis based on communication with the OpenAI API (regardless of the API Base)

Implementation of several methods for communication with the OpenAI API, embedding-based retrieval and data preparation

Getting Started

Can be installed directly with pip (a setup.py file is provided, if needed).

Notably the module contains the ChatGPTMemory class, which enables communication with the OpenAI API (through the ChatCompletion endpoint) while managing conversation memory.

Data preparation modules

This project was not originally intended for production. A lot of the scripts contained here are mainly for data preparation (to demonstrate different use cases). However, some functions are being used by both the qualtop-llmapi and the QOPA-LLM demo sides of the project.

In the future, this module should be replaced by a communication module. Also, any existent calculation functions should be passed to the server.

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

qualtop-conversational-analysis-0.33.tar.gz (49.9 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file qualtop-conversational-analysis-0.33.tar.gz.

File metadata

File hashes

Hashes for qualtop-conversational-analysis-0.33.tar.gz
Algorithm Hash digest
SHA256 b24a977b573f285a476ae3648cf280f134110cecb2c780f637d131ecd7662126
MD5 8d309c2949a16806cc2b0a600bff3ad3
BLAKE2b-256 a09d7262539bf1655a1e7d547d6561dac7f4f5360ad673b532e5e153e2a508a2

See more details on using hashes here.

File details

Details for the file qualtop_conversational_analysis-0.33-py3-none-any.whl.

File metadata

File hashes

Hashes for qualtop_conversational_analysis-0.33-py3-none-any.whl
Algorithm Hash digest
SHA256 98006d7c1b3d7f53b3a9dcd95cd0b18ba620c2fbc5ebfdc840edab8d8212f763
MD5 61b412377fa5b48d548edb151add003e
BLAKE2b-256 50e8b3c475f0089c3f5e088bfa4d8ed91c12e3e14db363f5ff5f42fef5ab7b43

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