Feat/qdrant docs reconstruct

[ThomasRochefortB]

This PR adds a Docs.load_docs_from_qdrant() function in order to rebuild a Docs() object from a QdrantVectorStore.

Assuming you have built a QdrantVectorStore using something like:

from paperqa import QdrantVectorStore, Docs
from qdrant_client import QdrantClient
import nest_asyncio
import os 

nest_asyncio.apply()

client = QdrantClient(url="localhost", port=6333)
vectorstore = QdrantVectorStore(client=client,
                                collection_name="test-collection")

# Loop through the ./downloaded_papers/ directory and run docs.add() on each file:
for file in os.listdir("downloaded_papers"):
    docs = Docs(texts_index=vectorstore)

    docs.add("./downloaded_papers/"+file)

    docs.texts_index.add_texts_and_embeddings(docs.texts)

Then you can rebuild the Docs object using:

import asyncio
from qdrant_client import AsyncQdrantClient
from paperqa import Docs

async def test_load_docs_from_qdrant():
    client = AsyncQdrantClient(url="http://localhost:6333")
    docs = await Docs.load_docs_from_qdrant(
        client=client,
        collection_name="test-collection",
        vector_name=None,
        batch_size=100,
        max_concurrent_requests=5
    )
    print(docs)
    assert len(docs.texts) > 0
    for text in docs.texts:
        assert text.text is not None
        assert text.doc is not None
    return docs

if __name__ == "__main__":
    # Run the async test
    docs = asyncio.run(test_load_docs_from_qdrant())

[jamesbraza]

So we want to keep Docs as a lightweight and general object. Let's keep DB provider stuff out of Docs.

Can you perhaps:

• Make this a classmethod or staticmethod on the Qdrant entity
• Make a free function that in that module

[ThomasRochefortB]

Hey @jamesbraza , thank you so much for your time on the review!

• I have committed all of your suggestions and asks. Let me know what you think.
• I have not touched the quirky if asyncio.iscoroutinefunction(... code as I will open a quick PR for this first.
• I am also expecting some linting issues.

[ThomasRochefortB]

#778 includes the async changes @jamesbraza