Easy GPT utils include 1. chat completion 2. embedding and 3. vector database
Project description
easy_gpt_utils
Easy GPT Utils include 1. chat completion 2. embedding and 3. vector database and others to help create app based on GPT and vector search (vector database is not implemented yet)
gpt
gpt is a simple util to use OpenAI's chat modles such as gpt-3.5-terbo gpt-4 etc. It has functions:
- calculate token of a string
- split string by paragraph and sentences within maximum token limit
- set model, temprature
- set system prompt and post prompt
- add context infomation to query
- remember talking history(buggy, will exceed token limit)
embedding
embedding is a simple util to create embedding (1536 dimension victor) for strings and paragraphs, It has functions:
- create embedding from string ,paragrahp and file
- save embeddings to file
vector_base
not implemented yet
In summary, easy_gpt_utils is now on early stage and hope it could help to create more powerful AI Apps in the future
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file easy_gpt_utils-0.1.10.tar.gz.
File metadata
- Download URL: easy_gpt_utils-0.1.10.tar.gz
- Upload date:
- Size: 14.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dc39e0cddde81bf7922e2a7d1915da2de2bff57cc0bde89d3157c7fcefbb0078
|
|
| MD5 |
145e394734777c0d4e8cacae7c953ae1
|
|
| BLAKE2b-256 |
8598845cd1555e6c0b8c371f6b345370f05fffeab6711dc22eeb813aafb3a39f
|
File details
Details for the file easy_gpt_utils-0.1.10-py3-none-any.whl.
File metadata
- Download URL: easy_gpt_utils-0.1.10-py3-none-any.whl
- Upload date:
- Size: 24.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
05bbd2d51f2f3bca3cc9c7153dfb2891cc1dfb84f179465c9d822d2059aeb411
|
|
| MD5 |
b27ea637178d8a302a04594a6a7d2f95
|
|
| BLAKE2b-256 |
fa070bf075a22be82a6e50adb9eadd03015c110be5a0a63723d4fe04aa690915
|
