
* feat: update PaLM icons * feat: add additional google models * POC: formatting inputs for Vertex AI streaming * refactor: move endpoints services outside of /routes dir to /services/Endpoints * refactor: shorten schemas import * refactor: rename PALM to GOOGLE * feat: make Google editable endpoint * feat: reusable Ask and Edit controllers based off Anthropic * chore: organize imports/logic * fix(parseConvo): include examples in googleSchema * fix: google only allows odd number of messages to be sent * fix: pass proxy to AnthropicClient * refactor: change `google` altName to `Google` * refactor: update getModelMaxTokens and related functions to handle maxTokensMap with nested endpoint model key/values * refactor: google Icon and response sender changes (Codey and Google logo instead of PaLM in all cases) * feat: google support for maxTokensMap * feat: google updated endpoints with Ask/Edit controllers, buildOptions, and initializeClient * feat(GoogleClient): now builds prompt for text models and supports real streaming from Vertex AI through langchain * chore(GoogleClient): remove comments, left before for reference in git history * docs: update google instructions (WIP) * docs(apis_and_tokens.md): add images to google instructions * docs: remove typo apis_and_tokens.md * Update apis_and_tokens.md * feat(Google): use default settings map, fully support context for both text and chat models, fully support examples for chat models * chore: update more PaLM references to Google * chore: move playwright out of workflows to avoid failing tests
4.7 KiB
Render Deployment
Note:
Some features will not work:
- Bing/Sydney: success may vary
- Meilisearch: additional configuration is needed, see guide here.
Also:
- You need to create an online MongoDB Atlas Database to be able to properly deploy
Create an account
1. visit https://render.com/ and click on 'Get Started for Free` to create an account and Login
2. Go into your dashboard
3. Select New
then Web Service
4. Add https://github.com/danny-avila/LibreChat
in the public repositories section and click continue
5. Give it a unique name and continue with the free tier and click on the create web service
button in the bottom of the page
6. At that point it will try to automatically deploy, you should cancel the deployment as it is not properly configured yet.
Add Environement Variables
1. Next you want to go in the Environement
section of the menu to manually add the Environement Variables
- You need to use the
Add Environement Variables
and add them one by one as adding a secret file will not work in our case.
2. You will need to copy and paste all of these:
Key | Value |
---|---|
ALLOW_REGISTRATION | true |
ANTHROPIC_API_KEY | user_provided |
BINGAI_TOKEN | |
CHATGPT_TOKEN | user_provided |
CREDS_IV | e2341419ec3dd3d19b13a1a87fafcbfb |
CREDS_KEY | f34be427ebb29de8d88c107a71546019685ed8b241d8f2ed00c3df97ad2566f0 |
HOST | 0.0.0.0 |
JWT_REFRESH_SECRET | secret |
JWT_SECRET | secret |
OPENAI_API_KEY | user_provided |
GOOGLE_KEY | user_provided |
PORT | 3080 |
SESSION_EXPIRY | (1000 * 60 * 60 * 24) * 7 |
⬆️ Add a single space in the value field for any endpoints that you wish to disable.
DO NOT FORGET TO SAVE YOUR CHANGES
3. Also add DOMAIN_CLIENT
DOMAIN_SERVER
and use the custom render address you were attributed in the value fields
Key | Value |
---|---|
DOMAIN_CLIENT | add your custom onrender.com address here |
DOMAIN_SERVER | add your custom onrender.com address here |
Create and Configure your Database
The last thing you need is to create a MongoDB Atlas Database and get your connection string.
Follow the instructions in this document: Online MongoDB Database
Complete the Environment Variables configuration
1. Go back to render.com and enter one last key / value in your Environment Variables
Key | Value |
---|---|
MONGO_URI | mongodb+srv://USERNAME:PASSWORD@render-librechat.fgycwpi.mongodb.net/?retryWrites=true&w=majority |
2. Important: Remember to replace <password>
with the database password you created earlier (when you did step 6 of the database creation (do not leave the <
>
each side of the password)
3. Save Changes
4. You should now have all these variables
Deployment
1. Now click on Manual Deploy
and select Deploy latest commit
2. It will take a couple of minutes
3. When it's ready you will see your service is live 🎉
in the console and the green Live
icon on top
Conclusion
You can now access it by clicking the link, congrattulation, you've sucessfully deployed LibreChat on render.com