Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-18 09:20:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

🪙 feat: Configure Max Context and Output Tokens (#2648)

Browse source 
* chore: make frequent 'error' log into 'debug' log

* feat: add maxContextTokens as a conversation field

* refactor(settings): increase popover height

* feat: add DynamicInputNumber and maxContextTokens to all endpoints that support it (frontend), fix schema

* feat: maxContextTokens handling (backend)

* style: revert popover height

* feat: max tokens

* fix: Ollama Vision firebase compatibility

* fix: Ollama Vision, use message_file_map to determine multimodal request

* refactor: bring back MobileNav and improve title styling
This commit is contained in:
Danny Avila 2024-05-09 13:27:13 -04:00 • committed by GitHub
parent 5293b73b6d
commit 6ba7f60eec
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 420 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

6
client/src/localization/languages/Eng.ts
View file

@ -280,6 +280,9 @@ export default {
com_endpoint_tone_style: 'Tone Style',
com_endpoint_token_count: 'Token count',
com_endpoint_output: 'Output',
com_endpoint_context_tokens: 'Max Context Tokens',
com_endpoint_context_info: `The maximum number of tokens that can be used for context. Use this for control of how many tokens are sent per request.
If unspecified, will use system defaults based on known models' context size. Setting higher values may result in errors and/or higher token cost.`,
com_endpoint_google_temp:
'Higher values = more random, while lower values = more focused and deterministic. We recommend altering this or Top P but not both.',
com_endpoint_google_topp:
@ -305,6 +308,9 @@ export default {
com_endpoint_max_output_tokens: 'Max Output Tokens',
com_endpoint_stop: 'Stop Sequences',
com_endpoint_stop_placeholder: 'Separate values by pressing `Enter`',
com_endpoint_openai_max_tokens: `Optional \`max_tokens\` field, representing the maximum number of tokens that can be generated in the chat completion.
The total length of input tokens and generated tokens is limited by the models context length. You may experience errors if this number exceeds the max context tokens.`,
com_endpoint_openai_temp:
'Higher values = more random, while lower values = more focused and deterministic. We recommend altering this or Top P but not both.',
com_endpoint_openai_max: