Scribd
Upload
33 views2 pages

Deploying To Render

Before deploying your app to Render, it's recommended to remove unused dependencies from the pyproject.toml file based on your chosen vector database provider to enhance performance. The document provides a list of packages to remove for various providers such as Pinecone, Weaviate, and others. Deployment can be initiated easily via a button that connects to Render's maintained repository, and further guidance is available in the linked documentation.

Uploaded by

officialvasquez
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
33 views2 pages

Deploying To Render

Before deploying your app to Render, it's recommended to remove unused dependencies from the pyproject.toml file based on your chosen vector database provider to enhance performance. The document provides a list of packages to remove for various providers such as Pinecone, Weaviate, and others. Deployment can be initiated easily via a button that connects to Render's maintained repository, and further guidance is available in the linked documentation.

Uploaded by

officialvasquez
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

# Deploying to Render

## Removing Unused Dependencies

Before deploying your app, you might want to remove unused dependencies from your
[pyproject.toml](/pyproject.toml) file to reduce the size of your app and improve
its performance. Depending on the vector database provider you choose, you can
remove the packages that are not needed for your specific provider.

Find the packages you can remove for each vector database provider [here](removing-
unused-dependencies.md).

After removing the unnecessary packages from the `pyproject.toml` file, you don't
need to run `poetry lock` and `poetry install` manually. The provided Dockerfile
takes care of installing the required dependencies using the `requirements.txt`
file generated by the `poetry export` command.

## Deployment

Render maintains a [fork](https://github.com/render-examples/chatgpt-retrieval-


plugin/) of this repository with a few small changes that facilitate easy
deployment. The source code is unchanged. To deploy both the Docker container from
this repository and a self-hosted Weaviate database to back it, just click the
button below. Enter your OpenAI API key when prompted.

[<img src="https://render.com/images/deploy-to-render-button.svg" alt="Deploy to


Render" />](https://render.com/deploy?repo=https://github.com/render-examples/
chatgpt-retrieval-plugin/tree/main)

The bearer token will be randomly generated for you. You can view it in in the
"Environment" tab on the [Render dashboard](https://dashboard.render.com) page for
your server. For more guidance, consult the [README in Render's
fork](https://github.com/render-examples/chatgpt-retrieval-plugin/blob/main/
README.md), [Render's documentation](https://render.com/docs), or the screen
recording linked below.

[![Deploy to Render screen


recording](render-thumbnail.png)](https://vimeo.com/823610578)

Removing Unused Dependencies


Before deploying your app, you might want to remove unused dependencies from your
pyproject.toml file to reduce the size of your app and improve its performance.
Depending on the vector database provider you choose, you can remove the packages
that are not needed for your specific provider.

Here are the packages you can remove for each vector database provider:

Pinecone: Remove weaviate-client, pymilvus, qdrant-client, redis, chromadb, llama-


index, azure-identity, azure-search-documents, supabase, psycopg2+pgvector, and
psycopg2cffi.
Weaviate: Remove pinecone-client, pymilvus, qdrant-client, redis, chromadb, llama-
index, azure-identity and azure-search-documents, supabase, psycopg2+pgvector,
psycopg2cffi.
Zilliz: Remove pinecone-client, weaviate-client, qdrant-client, redis, chromadb,
llama-index, azure-identity and azure-search-documents, supabase,
psycopg2+pgvector, and psycopg2cffi.
Milvus: Remove pinecone-client, weaviate-client, qdrant-client, redis, chromadb,
llama-index, azure-identity and azure-search-documents, supabase,
psycopg2+pgvector, and psycopg2cffi.
Qdrant: Remove pinecone-client, weaviate-client, pymilvus, redis, chromadb, llama-
index, azure-identity and azure-search-documents, supabase, psycopg2+pgvector, and
psycopg2cffi.
Redis: Remove pinecone-client, weaviate-client, pymilvus, qdrant-client, chromadb,
llama-index, azure-identity and azure-search-documents, supabase,
psycopg2+pgvector, and psycopg2cffi.
LlamaIndex: Remove pinecone-client, weaviate-client, pymilvus, qdrant-client,
chromadb, redis, azure-identity and azure-search-documents, supabase,
psycopg2+pgvector, and psycopg2cffi.
Chroma:: Remove pinecone-client, weaviate-client, pymilvus, qdrant-client, llama-
index, redis, azure-identity and azure-search-documents, supabase,
psycopg2+pgvector, and psycopg2cffi.
Azure Cognitive Search: Remove pinecone-client, weaviate-client, pymilvus, qdrant-
client, llama-index, redis and chromadb, supabase, psycopg2+pgvector, and
psycopg2cffi.
Supabase: Remove pinecone-client, weaviate-client, pymilvus, qdrant-client, redis,
llama-index, azure-identity and azure-search-documents, psycopg2+pgvector, and
psycopg2cffi.
Postgres: Remove pinecone-client, weaviate-client, pymilvus, qdrant-client, redis,
llama-index, azure-identity and azure-search-documents, supabase, and psycopg2cffi.
AnalyticDB: Remove pinecone-client, weaviate-client, pymilvus, qdrant-client,
redis, llama-index, azure-identity and azure-search-documents, supabase, and
psycopg2+pgvector.
After removing the unnecessary packages from the pyproject.toml file, you don't
need to run poetry lock and poetry install manually. The provided Dockerfile takes
care of installing the required dependencies using the requirements.txt file
generated by the poetry export command.

```

You might also like