Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-01-30 22:35:18 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add Option to Disable Titling, Config Titling Model, and Title Prompt Improvements (#977)

Browse source 
* feat: add option to disable titling as well as decide what model to use for OpenAI titling
refactor: truncate conversation text so it caps around 200 tokens for titling requests, optimize some of the title prompts

* feat: disable bing titling with TITLE_CONVO as well
This commit is contained in:
Danny Avila 2023-09-20 18:45:56 -04:00 • committed by GitHub
parent d13a7b1a74
commit 1d3e336e1c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 43 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
.env.example
View file

@ -73,6 +73,16 @@ OPENAI_API_KEY=user_provided
# Leave it blank to use internal settings.
# OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-16k,gpt-3.5-turbo-0301,text-davinci-003,gpt-4,gpt-4-0314,gpt-4-0613
# Titling is enabled by default when initiating a conversation.
# Uncomment the following variable to disable this feature.
# TITLE_CONVO=false
# The model used for titling by default is gpt-3.5-turbo-0613 to assure it works with the default method.
# gpt-3.5-turbo should also work when using the official API (and not a reverse proxy).
# You can change the model used by uncommenting the following and setting it to the model you want
# Must be compatible with the OpenAI Endpoint.
# OPENAI_TITLE_MODEL=gpt-3.5-turbo
# Reverse proxy settings for OpenAI:
# https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy
# OPENAI_REVERSE_PROXY=