test.py

# Colab: https://colab.research.google.com/drive/1YpDetI8BRbObPDEVdfqUcwhEX9UUXP-m?usp=sharing
import os
from pathlib import Path

from haystack import Pipeline
from haystack.components.converters import HTMLToDocument
from haystack.components.writers import DocumentWriter

from haystack_integrations.document_stores.chroma import ChromaDocumentStore
from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever
from itertools import islice

def all_xml_files():
    return tuple(
        islice(
            (
                entry.path
                for entry in os.scandir(os.path.expanduser("~/Downloads/xmlsall/"))
            ),
            100
        )
    )


# Chroma is used in-memory so we use the same instances in the two pipelines below
document_store = ChromaDocumentStore()

indexing = Pipeline()
indexing.add_component("converter", HTMLToDocument())
indexing.add_component("writer", DocumentWriter(document_store))
indexing.connect("converter", "writer")
indexing.run({"converter": {"sources": all_xml_files()}})

querying = Pipeline()
querying.add_component("retriever", ChromaQueryTextRetriever(document_store))
results = querying.run({"retriever": {"query": "Variable declarations", "top_k": 3}})

for d in results["retriever"]["documents"]:
    print(d.meta, d.score)