Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-12-24 04:10:15 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

🎉 feat: Optimizations and Anthropic Title Generation (#2184)

Browse source 
* feat: add claude-3-haiku-20240307 to default anthropic list

* refactor: optimize `saveMessage` calls mid-stream via throttling

* chore: remove addMetadata operations and consolidate in BaseClient

* fix(listAssistantsForAzure): attempt to specify correct model mapping as accurately as possible (#2177)

* refactor(client): update last conversation setup with current assistant model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model

* refactor(cache): explicitly add TTL of 2 minutes when setting titleCache and add default TTL of 10 minutes to abortKeys cache

* feat(AnthropicClient): conversation titling using Anthropic Function Calling

* chore: remove extraneous token usage logging

* fix(convos): unhandled edge case for conversation grouping (undefined conversation)

* style: Improved style of Search Bar after recent UI update

* chore: remove unused code, content part helpers

* feat: always show code option
This commit is contained in:
Danny Avila 2024-03-23 20:21:40 -04:00 • committed by GitHub
parent 8e7816468d
commit 1f0fb497f8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 426 additions and 188 deletions
Download patch file Download diff file Expand all files Collapse all files

28
docs/install/configuration/dotenv.md
View file

@ -129,6 +129,15 @@ ENDPOINTS=openAI,assistants,azureOpenAI,bingAI,chatGPTBrowser,google,gptPlugins,
PROXY=
```
- Titling is enabled by default for all Endpoints when initiating a conversation (proceeding the first AI response).
- Set to `false` to disable this feature.
- Not all endpoints support titling.
- You can configure this feature on an Endpoint-level using [the `librechat.yaml` config file](./custom_config.md)
```bash
TITLE_CONVO=true
```
### Known Endpoints - librechat.yaml
- see: [AI Endpoints](./ai_endpoints.md)
- see also: [Custom Configuration](./custom_config.md)
@ -158,6 +167,15 @@ ANTHROPIC_MODELS=claude-3-opus-20240229,claude-3-sonnet-20240229,claude-2.1,clau
ANTHROPIC_REVERSE_PROXY=
```
- Titling is enabled by default but is configured with the environment variable
`TITLE_CONVO` for all Endpoints. The default model used for Anthropic titling is "claude-3-haiku-20240307". You can change it by uncommenting the following and setting the desired model. **(Optional)**
> **Note:** Must be compatible with the Anthropic Endpoint. Also, Claude 2 and Claude 3 models perform best at this task, with `claude-3-haiku` models being the cheapest.
```bash
ANTHROPIC_TITLE_MODEL=claude-3-haiku-20240307
```
### Azure
**Important:** See [the complete Azure OpenAI setup guide](./ai_setup.md#azure-openai) for thorough instructions on enabling Azure OpenAI
@ -325,14 +343,8 @@ DEBUG_OPENAI=false
OPENAI_MODELS=gpt-3.5-turbo-0125,gpt-3.5-turbo-0301,gpt-3.5-turbo,gpt-4,gpt-4-0613,gpt-4-vision-preview,gpt-3.5-turbo-0613,gpt-3.5-turbo-16k-0613,gpt-4-0125-preview,gpt-4-turbo-preview,gpt-4-1106-preview,gpt-3.5-turbo-1106,gpt-3.5-turbo-instruct,gpt-3.5-turbo-instruct-0914,gpt-3.5-turbo-16k
```
- Titling is enabled by default when initiating a conversation.
- Set to false to disable this feature.
```bash
TITLE_CONVO=true
```
- The default model used for titling by is gpt-3.5-turbo. You can change it by uncommenting the following and setting the desired model. **(Optional)**
- Titling is enabled by default but is configured with the environment variable
`TITLE_CONVO` for all Endpoints. The default model used for OpenAI titling is gpt-3.5-turbo. You can change it by uncommenting the following and setting the desired model. **(Optional)**
> **Note:** Must be compatible with the OpenAI Endpoint.