Refactor web retriever

[Spycsh]

Description

Refactor web retriever

Issues

#1010

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

na

Tests

UT

[eero-t]

PR could be described more in detail what it's refactoring, as commit descriptions are also missing.

This seems to be splitting retriever_chroma.py to:

• opea_google_search.py backend, and
• opea_web_retrievers_microservice.py frontend

I assume split is done to prepare for using other search engines than Google.

Frontend is still hard-coded to using Chroma vector-db and TEI embedding, but I assume vLLM embedding support will be addded in future.

On quick look at the new code, it seems to correspond to old one, and the text & script changes look OK (git grep does not return other matches for chroma).

PS. IMHO opea_ prefixes for the new files are redundant as this whole thing is OPEA project / repository.

[eero-t]

CI test "web_retrievers_opea_google_search, intel_cpu":

   File "/home/user/comps/web_retrievers/src/integrations/google_search.py", line 43, in get_urls
    result = self.search.results(query, num_search_result)
             ^^^^^^^^^^^
AttributeError: 'OpeaGoogleSearch' object has no attribute 'search'

There are also other 2 trivial CI failures.