refactor: Address review feedback for FirecrawlWebSearch

- Remove warm_up() from docstring example (auto-called on first run)
- Remove custom to_dict()/from_dict() in favor of default serialization
- Update top_k docstring to note it can be overridden by limit in search_params
- Remove client-side top_k truncation (Firecrawl respects limit server-side)
- Use SearchData type instead of Any for _parse_search_response
- Remove redundant or "" from getattr() calls
- Use search_response.web directly instead of getattr()
- Remove corresponding tests for removed functionality

Author: saakshigupta2002

integrations/firecrawl/src/haystack_integrations/components/websearch/firecrawl/firecrawl_websearch.py

@@ -5,7 +5,8 @@
 from typing import Any
 
 from firecrawl import AsyncFirecrawl, Firecrawl  # type: ignore[import-untyped]
-from haystack import Document, component, default_from_dict, default_to_dict, logging
+from firecrawl.types import SearchData  # type: ignore[import-untyped]
+from haystack import Document, component, logging
 from haystack.utils import Secret
 
 logger = logging.getLogger(__name__)
@@ -33,8 +34,6 @@ class FirecrawlWebSearch:
         api_key=Secret.from_env_var("FIRECRAWL_API_KEY"),
         top_k=5,
     )
-    websearch.warm_up()
-
     result = websearch.run(query="What is Haystack by deepset?")
     documents = result["documents"]
     links = result["links"]
@@ -55,7 +54,7 @@ def __init__(
             Defaults to the `FIRECRAWL_API_KEY` environment variable.
         :param top_k:
             Maximum number of documents to return.
-            Defaults to 10.
+            Defaults to 10. This can be overridden by the `"limit"` parameter in `search_params`.
         :param search_params:
             Additional parameters passed to the Firecrawl search API.
             See the [Firecrawl API reference](https://docs.firecrawl.dev/api-reference/endpoint/search)
@@ -79,20 +78,6 @@ def warm_up(self) -> None:
         if self._async_firecrawl_client is None:
             self._async_firecrawl_client = AsyncFirecrawl(api_key=self.api_key.resolve_value())
 
-    def to_dict(self) -> dict[str, Any]:
-        """Serializes the component to a dictionary."""
-        return default_to_dict(
-            self,
-            api_key=self.api_key.to_dict(),
-            top_k=self.top_k,
-            search_params=self.search_params,
-        )
-
-    @classmethod
-    def from_dict(cls, data: dict[str, Any]) -> "FirecrawlWebSearch":
-        """Deserializes the component from a dictionary."""
-        return default_from_dict(cls, data)
-
     @component.output_types(documents=list[Document], links=list[str])
     def run(
         self,
@@ -128,11 +113,6 @@ def run(
             return {"documents": [], "links": []}
 
         documents, links = self._parse_search_response(search_response)
-
-        if self.top_k is not None:
-            documents = documents[: self.top_k]
-            links = links[: self.top_k]
-
         return {"documents": documents, "links": links}
 
     @component.output_types(documents=list[Document], links=list[str])
@@ -170,15 +150,10 @@ async def run_async(
             return {"documents": [], "links": []}
 
         documents, links = self._parse_search_response(search_response)
-
-        if self.top_k is not None:
-            documents = documents[: self.top_k]
-            links = links[: self.top_k]
-
         return {"documents": documents, "links": links}
 
     @staticmethod
-    def _parse_search_response(search_response: Any) -> tuple[list[Document], list[str]]:
+    def _parse_search_response(search_response: SearchData) -> tuple[list[Document], list[str]]:
         """
         Convert a Firecrawl search response to Haystack Documents and links.
 
@@ -188,7 +163,7 @@ def _parse_search_response(search_response: Any) -> tuple[list[Document], list[s
         documents: list[Document] = []
         links: list[str] = []
 
-        web_results = getattr(search_response, "web", None) or []
+        web_results = search_response.web or []
         for result in web_results:
             url = ""
             title = ""
@@ -200,9 +175,9 @@ def _parse_search_response(search_response: Any) -> tuple[list[Document], list[s
                 url = metadata.get("url", getattr(result, "url", ""))
                 title = metadata.get("title", "")
             else:
-                url = getattr(result, "url", "") or ""
-                title = getattr(result, "title", "") or ""
-                content = getattr(result, "description", "") or ""
+                url = getattr(result, "url", "")
+                title = getattr(result, "title", "")
+                content = getattr(result, "description", "")
 
             doc = Document(
                 content=content,

integrations/firecrawl/tests/test_firecrawl_websearch.py

@@ -7,7 +7,6 @@
 
 import pytest
 from haystack import Document
-from haystack.core.serialization import component_from_dict, component_to_dict
 from haystack.utils import Secret
 
 from haystack_integrations.components.websearch.firecrawl import FirecrawlWebSearch
@@ -68,32 +67,6 @@ def test_init_with_params(self) -> None:
         assert ws._search_params == {"tbs": "qdr:d", "location": "US"}
         assert ws.api_key.resolve_value() == "custom-key"
 
-    def test_to_dict(self, monkeypatch: pytest.MonkeyPatch) -> None:
-        monkeypatch.setenv("FIRECRAWL_API_KEY", "test-key")
-        ws = FirecrawlWebSearch(top_k=5, search_params={"tbs": "qdr:d"})
-        data = component_to_dict(ws, "FirecrawlWebSearch")
-        assert (
-            data["type"]
-            == "haystack_integrations.components.websearch.firecrawl.firecrawl_websearch.FirecrawlWebSearch"
-        )
-        assert data["init_parameters"]["top_k"] == 5
-        assert data["init_parameters"]["search_params"] == {"tbs": "qdr:d"}
-
-    def test_from_dict(self, monkeypatch: pytest.MonkeyPatch) -> None:
-        monkeypatch.setenv("FIRECRAWL_API_KEY", "test-key")
-        data = {
-            "type": ("haystack_integrations.components.websearch.firecrawl.firecrawl_websearch.FirecrawlWebSearch"),
-            "init_parameters": {
-                "top_k": 3,
-                "search_params": {"location": "UK"},
-                "api_key": {"env_vars": ["FIRECRAWL_API_KEY"], "strict": True, "type": "env_var"},
-            },
-        }
-        ws = component_from_dict(FirecrawlWebSearch, data, "FirecrawlWebSearch")
-        assert ws.top_k == 3
-        assert ws.search_params == {"location": "UK"}
-        assert ws.api_key.resolve_value() == "test-key"
-
     def test_run_returns_documents_and_links(self, mock_client) -> None:
         ws = FirecrawlWebSearch(api_key=Secret.from_token("test-key"), top_k=10)
         ws._firecrawl_client = mock_client
@@ -141,26 +114,6 @@ def test_run_overrides_init_params_with_runtime_params(self, mock_client) -> Non
             limit=5,
         )
 
-    def test_run_respects_top_k(self, mock_client) -> None:
-        results = []
-        for i in range(5):
-            r = MagicMock(spec=["url", "title", "description"])
-            r.url = f"https://example.com/{i}"
-            r.title = f"Title {i}"
-            r.description = f"Description {i}"
-            results.append(r)
-        response = MagicMock()
-        response.web = results
-        mock_client.search.return_value = response
-
-        ws = FirecrawlWebSearch(api_key=Secret.from_token("test-key"), top_k=3)
-        ws._firecrawl_client = mock_client
-
-        result = ws.run(query="test")
-
-        assert len(result["documents"]) == 3
-        assert len(result["links"]) == 3
-
     @pytest.mark.asyncio
     async def test_run_async(self, mock_async_client) -> None:
         ws = FirecrawlWebSearch(api_key=Secret.from_token("test-key"), top_k=10)