First try app packaging : librechat - issue with postgresql extention (pgvector)

[LoudLemur]

@robi @girish there is an option to add cloudron's docs here, if they are on github

https://context7.com/add-library?tab=github

[Valexico]

I think building a RAG-like knowledge base is not the best approach for this use case.
It would be much mode efficient an agent with

• General knowledge about cloudron packaging
• Toolset (sub agent) to retrieve relevant files from repositories (dockerfile, docker-compose...)
• Toolset to retrieve additional context for each addon needed
• Toolset to retrieve relevant example (existing cloudron packaged apps)

The process is complex but quite straightforward and I see no need for a RAG knowledge base

[firmansi]

But without RAG API, somehow we can nor "chat" with files, that's from understanding about how important to have RAG API packaged with core Librechat. Pleaset let us know if we can upload files to Librechat without RAG API, maybe I miss something

[Valexico]

We should split in 2 different thread
Yes Librechat needs RAG API to have all its feature

No a cloudron packaging agent does not need a RAG knowledge bases to be efficient (I think)

Those are 2 totally different subjects

[firmansi]

@Valexico Sure, to make it more efficient,but somehow RAG knowledgebase deem necessary for business usage as RAG can enhance model to understand the business context of the company using tool like librechat, without RAG knowledgebase, the model will only have vast general knowledge

[Valexico]

I agree with you @firmansi
the problem is there are 2 topics discussed in this thread :

• Topic #1: Packaging of librechat
• Topic #2: How to build an AI agent to automate the process of packaging Cloudron app

I think that lead to our misunderstanding

[marcusquinn]

@LoudLemur said in First try app packaging : librechat - issue with postgresql extention (pgvector):

@robi @girish there is an option to add cloudron's docs here, if they are on github

https://context7.com/add-library?tab=github

Great suggestion! Might need it's own post to make sure it doesn't get lost in this thread.

[LoudLemur]

@marcusquinn Thanks! I have checked and context7 can also ingest from websites, which I shall try instead. That website is very busy ingesting and it keeps saying, "Try again in a few minutes..." Eventually it said "failed to find project name" from cloudron's:
https://docs.cloudron.io/

so it is still not working and now it is rate limiting me. perhaps somebody else could try?

[LoudLemur]

We have Cloudron docs in context7, now.
Thanks to whomever sorted that!

https://context7.com/context7/cloudron_io

[marcusquinn]

@LoudLemur Awesome!