At present, I have built a vector search database of existing text using chroma vector database, which can quickly search the relevant content that has been converted into vectors.
But now I have 600 megabytes of text content in plain text stored in the elaesticsearch database. I hope to combine chorma and elaesticsearch data content to feedback llama_index related questions.
Specific ideas are as follows:

1. I want to search directly in plain text and retrieve the elaesticsearch database to return semantically relevant content.
2. Then vector search results based on chroma vector database, and then vectorization conversion based on the text search results of elaesticsearch.
3. Combine the results of the two searches.

How should it be done?

help I'm using llama_index on chroma ,but there is still a question.

According to the example：Chroma - LlamaIndex 🦙 0.7.22 (gpt-index.readthedocs.io)

Normally, we delete or modify a document based on our query, not based on the ID of a document, because the document id is an internal field that we cannot know in advance. But is now based on the code:
'''
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
'''

Now according to the sample code, we can only get the text result of the query, but cannot get the corresponding id of the text, so we cannot delete or update the query result. How to query the corresponding id of the result text based on prompt, so as to delete or modify the operation later?