Document db metadata filtering

[kartiksonaghela]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

agronomy_name_space='test.agronomy_product'
client = MongoClient(connection_string)
collection = client['test']['agronomy_product']
#collection=client['chatbot-service-qa']['agronomy_product']
agronomy_collection = DocumentDBVectorSearch.from_connection_string(
connection_string=connection_string,
namespace = agronomy_name_space, 
index_name = "vector",
embedding = embeddings
)

# Create retriever with filtering
agronomy_retriever = agronomy_collection.as_retriever(
    search_type="similarity",
    search_kwargs={"filter": {"crop name": "corn"}},
    
)

# Perform semantic matching with filter applied
query = 'how to use this for farming'
semantic_matches = agronomy_retriever.invoke(query)

Description

My metadata filtering is not working do you have any solution for this when i perform normal text search using query in that case it is working
text_search_results = collection.find({"$text": {"$search": "corn"}})
but while perfomring metadatafiltering with langchain there is a problem
so how do is solve this problem please help thanks

This are my search indexes
{'id': {'v': 4, 'key': [('_id', 1)], 'ns': 'test.agronomy_product'},
'vector': {'v': 4,
'key': [('vectorContent', 'vector')],
'vectorOptions': SON([('type', 'hnsw'), ('dimensions', 1536), ('similarity', 'cosine'), ('m', 16), ('efConstruction', 64)]),
'ns': 'test.agronomy_product'},
'text_index': {'v': 1,
'key': [('_fts', 'text'), ('_ftsx', 1)],
'ns': 'test.agronomy_product',
'default_language': 'english',
'weights': SON([('crop name', 1.0), ('product name', 1.0), ('seed product name', 1.0), ('product category', 1.0)]),
'textIndexVersion': 1}}

System Info

langchain==0.1.14
langchain_community==0.0.31
langchain_openai==0.1.1
langcodes==3.3.0
openai python-dotenv==1.0.1
language_data==1.1
pymongo==4.7.3