* feat(PluginsClient.js): add conversationId to options object in the constructor feat(PluginsClient.js): add support for Code Interpreter plugin feat(PluginsClient.js): add support for Code Interpreter plugin in the availableTools manifest feat(CodeInterpreter.js): add CodeInterpreterTools module feat(CodeInterpreter.js): add RunCommand class feat(CodeInterpreter.js): add ReadFile class feat(CodeInterpreter.js): add WriteFile class feat(handleTools.js): add support for loading Code Interpreter plugin * chore(api): update langchain dependency to version 0.0.123 * fix(CodeInterpreter.js): add support for extracting environment from code fix(WriteFile.js): add support for extracting environment from data fix(extractionChain.js): add utility functions for creating extraction chain from Zod schema fix(handleTools.js): refactor getOpenAIKey function to handle user-provided API key fix(handleTools.js): pass model and openAIApiKey to CodeInterpreter constructor * fix(tools): rename CodeInterpreterTools to E2BTools fix(tools): rename code_interpreter pluginKey to e2b_code_interpreter * chore(PluginsClient.js): comment out unused import and function findMessageContent feat(PluginsClient.js): add support for CodeSherpa plugin feat(PluginsClient.js): add CodeSherpaTools to available tools feat(PluginsClient.js): update manifest.json to include CodeSherpa plugin feat(CodeSherpaTools.js): create RunCode and RunCommand classes for CodeSherpa plugin feat(E2BTools.js): Add E2BTools module for extracting environment from code and running commands, reading and writing files fix(codesherpa.js): Remove codesherpa module as it is no longer needed feat(handleTools.js): add support for CodeSherpaTools in loadTools function feat(loadToolSuite.js): create loadToolSuite utility function to load a suite of tools * feat(PluginsClient.js): add support for CodeSherpa v2 plugin feat(PluginsClient.js): add CodeSherpa v1 plugin to available tools feat(PluginsClient.js): add CodeSherpa v2 plugin to available tools feat(PluginsClient.js): update manifest.json for CodeSherpa v1 plugin feat(PluginsClient.js): update manifest.json for CodeSherpa v2 plugin feat(CodeSherpa.js): implement CodeSherpa plugin for interactive code and shell command execution feat(CodeSherpaTools.js): implement RunCode and RunCommand plugins for CodeSherpa v1 feat(CodeSherpaTools.js): update RunCode and RunCommand plugins for CodeSherpa v2 fix(handleTools.js): add CodeSherpa import statement fix(handleTools.js): change pluginKey from 'codesherpa' to 'codesherpa_tools' fix(handleTools.js): remove model and openAIApiKey from options object in e2b_code_interpreter tool fix(handleTools.js): remove openAIApiKey from options object in codesherpa_tools tool fix(loadToolSuite.js): remove model and openAIApiKey parameters from loadToolSuite function * feat(initializeFunctionsAgent.js): add prefix to agentArgs in initializeFunctionsAgent function The prefix is added to the agentArgs in the initializeFunctionsAgent function. This prefix is used to provide instructions to the agent when it receives any instructions from a webpage, plugin, or other tool. The agent will notify the user immediately and ask them if they wish to carry out or ignore the instructions. * feat(PluginsClient.js): add ChatTool to the list of tools if it meets the conditions feat(tools/index.js): import and export ChatTool feat(ChatTool.js): create ChatTool class with necessary properties and methods * fix(initializeFunctionsAgent.js): update PREFIX message to include sharing all output from the tool fix(E2BTools.js): update descriptions for RunCommand, ReadFile, and WriteFile plugins to provide more clarity and context * chore: rebuild package-lock after rebase * chore: remove deleted file from rebase * wip: refactor plugin message handling to mirror chat.openai.com, handle incoming stream for plugin use * wip: new plugin handling * wip: show multiple plugins handling * feat(plugins): save new plugins array * chore: bump langchain * feat(experimental): support streaming in between plugins * refactor(PluginsClient): factor out helper methods to avoid bloating the class, refactor(gptPlugins): use agent action for mapping the name of action * fix(handleTools): fix tests by adding condition to return original toolFunctions map * refactor(MessageContent): Allow the last index to be last in case it has text (may change with streaming) * feat(Plugins): add handleParsingErrors, useful when LLM does not invoke function params * chore: edit out experimental codesherpa integration * refactor(OpenAPIPlugin): rework tool to be 'function-first', as the spec functions are explicitly passed to agent model * refactor(initializeFunctionsAgent): improve error handling and system message * refactor(CodeSherpa, Wolfram): optimize token usage by delegating bulk of instructions to system message * style(Plugins): match official style with input/outputs * chore: remove unnecessary console logs used for testing * fix(abortMiddleware): render markdown when message is aborted * feat(plugins): add BrowserOp * refactor(OpenAPIPlugin): improve prompt handling * fix(useGenerations): hide edit button when message is submitting/streaming * refactor(loadSpecs): optimize OpenAPI spec loading by only loading requested specs instead of all of them * fix(loadSpecs): will retain original behavior when no tools are passed to the function * fix(MessageContent): ensure cursor only shows up for last message and last display index fix(Message): show legacy plugin and pass isLast to Content * chore: remove console.logs * docs: update docs based on breaking changes and new features refactor(structured/SD): use description_for_model for detailed prompting * docs(azure): make plugins section more clear * refactor(structured/SD): change default payload to SD-WebUI to prefer realism and config for SDXL * refactor(structured/SD): further improve system message prompt * docs: update breaking changes after rebase * refactor(MessageContent): factor out EditMessage, types, Container to separate files, rename Content -> Markdown * fix(CodeInterpreter): linting errors * chore: reduce browser console logs from message streams * chore: re-enable debug logs for plugins/langchain to help with user troubleshooting * chore(manifest.json): add [Experimental] tag to CodeInterpreter plugins, which are not intended as the end-all be-all implementation of this feature for Librechat
6.5 KiB
⚠️ Breaking Changes ⚠️
Note: If you experience any issues after updating, we recommend clearing your browser cache and cookies. Certain changes in the updates may impact cookies, leading to unexpected behaviors if not cleared properly.
v0.5.8
If you have issues after updating, please try to clear your browser cache and cookies!
- It's now required to name manifest JSON files (for ChatGPT Plugins) in the
api\app\clients\tools\.well-knowndirectory after theirname_for_modelproperty should you add one yourself.- This was a recommended convention before, but is now required.
v0.5.7
Now, we have an easier and safer way to update LibreChat. You can simply run npm run update from the project directory for a clean update.
If you want to skip the prompt you can use
for a docker install:
npm run update:docker
for a local install:
npm run update:local
v0.5.5
Some users have reported an error after updating their docker containers.
- To fix this error, you need to:
v0.5.4
Some changes were made in the .env file
Look at the .env.example for reference.
- If you previously used social login, you need to:
- Add this to your .env file: 👇
##########################
# User System:
##########################
# Allow Public Registration
ALLOW_REGISTRATION=true
# Allow Social Registration
ALLOW_SOCIAL_LOGIN=false
-
Set ALLOW_SOCIAL_LOGIN to true if you want to enable social login 🔥
-
If you want to enable the Anthropic Endpoint (Claude), you need to:
- Add this part in your .env file: 👇
##########################
# Anthropic Endpoint:
##########################
# Access key from https://console.anthropic.com/
# Leave it blank to disable this feature.
# Set to "user_provided" to allow the user to provide their API key from the UI.
# Note that access to claude-1 may potentially become unavailable with the release of claude-2.
ANTHROPIC_API_KEY="user_provided"
ANTHROPIC_MODELS=claude-1,claude-instant-1,claude-2
- Choose from ANTHROPIC_MODELS which models you want to enable 🤖
v0.5.3
Changed AZURE_OPENAI_API_KEY to AZURE_API_KEY:
I had to change the environment variable from AZURE_OPENAI_API_KEY to AZURE_API_KEY, because the former would be read by langchain and cause issues when a user has both Azure and OpenAI keys set. This is a known issue in the langchain library
v0.5.0
Note: These changes only apply to users who are updating from a previous version of the app.
Summary
- In this version, we have simplified the configuration process, improved the security of your credentials, and updated the docker instructions. 🚀
- Please read the following sections carefully to learn how to upgrade your app and avoid any issues. 🙏
- Note: If you're having trouble, before creating a new issue, please search for similar ones on our #issues thread on our discord or our troubleshooting discussion on our Discussions page. If you don't find a relevant issue, feel free to create a new one and provide as much detail as possible.
Configuration
- We have simplified the configuration process by using a single
.envfile in the root folder instead of separate/api/.envand/client/.envfiles. - We have renamed the
OPENAI_KEYvariable toOPENAI_API_KEYto match the official documentation. The upgrade script should do this automatically for you, but please double-check that your key is correct in the new.envfile. - We have removed the
VITE_SHOW_GOOGLE_LOGIN_OPTIONvariable, since it is no longer needed. The app will automatically enable Google Login if you provide theGOOGLE_CLIENT_IDandGOOGLE_CLIENT_SECRETvariables. 🔑 - We have changed the variable name for setting the app title from
VITE_APP_TITLEtoAPP_TITLE. If you had set a custom app title before, you need to update the variable name in the.envfile to keep it. Otherwise, the app might revert to the default title. - For enhanced security, we are now asking for crypto keys for securely storing credentials in the
.envfile. Crypto keys are used to encrypt and decrypt sensitive data such as passwords and access keys. If you don't set them, the app will crash on startup. 🔒 - You need to fill the following variables in the
.envfile with 32-byte (64 characters in hex) or 16-byte (32 characters in hex) values:CREDS_KEY(32-byte)CREDS_IV(16-byte)JWT_SECRET(32-byte) optional but recommended
- The upgrade script will do it for you, otherwise you can use this replit to generate some crypto keys quickly: https://replit.com/@daavila/crypto#index.js
- Make sure you keep your crypto keys safe and don't share them with anyone. 🙊
Docker
- The docker-compose file had some change. Review the new docker instructions to make sure you are setup properly. This is still the simplest and most effective method.
Local Install
- If you had installed a previous version, you can run
npm run upgradeto automatically copy the content of both files to the new.envfile and backup the old ones in the root dir. - If you are installing the project for the first time, it's recommend you run the installation script
npm run cito guide your local setup (otherwise continue to use docker) - The upgrade script requires both
/api/.envand/client/.envfiles to run properly. If you get an error about a missing client env file, just rename the/client/.env.examplefile to/client/.envand run the script again. - After running the upgrade script, the
OPENAI_API_KEYvariable might be placed in a different section in the new.envfile than before. This does not affect the functionality of the app, but if you want to keep it organized, you can look for it near the bottom of the file and move it to its usual section.
We apologize for any inconvenience caused by these changes. We hope you enjoy the new and improved version of our app!