Add PostgreSQL vector store support with pgvector and Add config to Setting

[mlavaei3]

This pull request introduces PostgreSQL vector store integration for RAGLight.
It allows storing and retrieving embeddings directly from a PostgreSQL database using the pgvector extension.
"pip install langchain-postgres "

[Bessouat40]

Thank you for this PR and for your interest in RAGLight

You’re definitely on the right track to add PostgreSQL vector store support, but a few key pieces are still missing :

• You only created the vector store class, it still needs to be connected to the builder,
• Please update the README.md accordingly,
• Update pyproject.toml with new packages,
• Add an example script showing how to use PostgreSQL with RAGLight.

You can check how existing vector stores are registered and used throughout the repo to guide you.

[duranbe]

I'd argue that PostgreSQL is more often referred as Postgres

[mlavaei3]

I’ve updated the PR based on your feedback. Let me know if anything else needs adjustment.

[Bessouat40]

Hello, sorry for the delay.
When I try your code with this example file :

from raglight.rag.simple_rag_api import RAGPipeline
from raglight.models.data_source_model import FolderSource, GitHubSource
from raglight.config.settings import Settings
from raglight.config.rag_config import RAGConfig
from raglight.config.vector_store_config import VectorStoreConfig

Settings.setup_logging()

knowledge_base=[
    FolderSource(path="<path to your folder with pdf>/knowledge_base"),
    GitHubSource(url="https://github.com/Bessouat40/RAGLight")
    ]

vector_store_config = VectorStoreConfig(
    embedding_model = Settings.DEFAULT_EMBEDDINGS_MODEL,
    provider=Settings.HUGGINGFACE,
    # api_base = ... # If you have a custom client URL
    database=Settings.POSTGRES,
    persist_directory = './defaultDb',
    password = "mysecretpassword"
)

config = RAGConfig(
        llm = Settings.DEFAULT_LLM,
        provider = Settings.OLLAMA,
        # api_base = ... # If you have a custom client URL
        # k = Settings.DEFAULT_K,
        # cross_encoder_model = Settings.DEFAULT_CROSS_ENCODER_MODEL,
        # system_prompt = Settings.DEFAULT_SYSTEM_PROMPT,
        # knowledge_base = knowledge_base
    )

pipeline = RAGPipeline(config, vector_store_config)

pipeline.build()

response = pipeline.generate("How can I create an easy RAGPipeline using raglight framework ? Give me python implementation")
print(response)

I've got this error :
vector_store_config = VectorStoreConfig( ^^^^^^^^^^^^^^^^^^ TypeError: VectorStoreConfig.__init__() got an unexpected keyword argument 'password'

I've you tried your code before creating this PR ?

I think it does'nt works.
Furthermore, the parameter database from your constructor is already used for the database type in VectorStoreConfig.

[Bessouat40]

And you need to implement similarity_search_class.