fix(perplexity): address sjrl review comments

- embedders: fix api_base_url default to include /v1 (was hitting
  https://api.perplexity.ai/embeddings -> 404; correct endpoint is
  https://api.perplexity.ai/v1/embeddings). This is why the embedder
  integration tests failed for sjrl.
- embedders: add explicit from_dict classmethod on both
  PerplexityDocumentEmbedder and PerplexityTextEmbedder for correct
  typing (r3224097561, r3224106489).
- chat generator: use generate_qualified_class_name() instead of
  hardcoded class path in to_dict (r3224126336); drop redundant
  data['type'] override in from_dict (r3224130257); drop unused
  module-level path constants (r3224143875).
- websearch: drop unreachable 'client failed to initialize'
  RuntimeError branches in run / run_async — warm_up always runs first
  (r3224158183, r3224160907).
- websearch: tighten return-type hint on run / run_async to
  dict[str, list[Document] | list[str]] (r3224178510, r3224179725).
- tests: bump api_base_url assertions in embedder unit tests to /v1;
  drop obsolete 'raises_runtime_error_when_warm_up_fails' websearch
  tests; update chat-generator to_dict assertion to the
  fully-qualified module path produced by generate_qualified_class_name.

Author: jliounis

integrations/perplexity/src/haystack_integrations/components/embedders/perplexity/document_embedder.py

@@ -5,7 +5,7 @@
 import importlib.metadata
 from typing import Any, ClassVar
 
-from haystack import component, default_to_dict
+from haystack import component, default_from_dict, default_to_dict
 from haystack.components.embedders import OpenAIDocumentEmbedder
 from haystack.utils.auth import Secret
 
@@ -66,7 +66,7 @@ def __init__(
         *,
         api_key: Secret = Secret.from_env_var("PERPLEXITY_API_KEY"),
         model: str = "pplx-embed-v1-0.6b",
-        api_base_url: str | None = "https://api.perplexity.ai",
+        api_base_url: str | None = "https://api.perplexity.ai/v1",
         prefix: str = "",
         suffix: str = "",
         batch_size: int = 32,
@@ -151,3 +151,15 @@ def to_dict(self) -> dict[str, Any]:
             max_retries=self.max_retries,
             http_client_kwargs=self.http_client_kwargs,
         )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "PerplexityDocumentEmbedder":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            Dictionary to deserialize from.
+        :returns:
+            Deserialized component.
+        """
+        return default_from_dict(cls, data)

integrations/perplexity/src/haystack_integrations/components/embedders/perplexity/text_embedder.py

@@ -5,7 +5,7 @@
 import importlib.metadata
 from typing import Any, ClassVar
 
-from haystack import component, default_to_dict
+from haystack import component, default_from_dict, default_to_dict
 from haystack.components.embedders import OpenAITextEmbedder
 from haystack.utils.auth import Secret
 
@@ -61,7 +61,7 @@ def __init__(
         *,
         api_key: Secret = Secret.from_env_var("PERPLEXITY_API_KEY"),
         model: str = "pplx-embed-v1-0.6b",
-        api_base_url: str | None = "https://api.perplexity.ai",
+        api_base_url: str | None = "https://api.perplexity.ai/v1",
         prefix: str = "",
         suffix: str = "",
         timeout: float | None = None,
@@ -126,3 +126,15 @@ def to_dict(self) -> dict[str, Any]:
             max_retries=self.max_retries,
             http_client_kwargs=self.http_client_kwargs,
         )
+
+    @classmethod
+    def from_dict(cls, data: dict[str, Any]) -> "PerplexityTextEmbedder":
+        """
+        Deserializes the component from a dictionary.
+
+        :param data:
+            Dictionary to deserialize from.
+        :returns:
+            Deserialized component.
+        """
+        return default_from_dict(cls, data)

integrations/perplexity/src/haystack_integrations/components/generators/perplexity/chat/chat_generator.py

@@ -7,17 +7,14 @@
 
 from haystack import component, default_from_dict
 from haystack.components.generators.chat import OpenAIResponsesChatGenerator
+from haystack.core.serialization import generate_qualified_class_name
 from haystack.dataclasses import StreamingCallbackT
 from haystack.tools import ToolsType, deserialize_tools_or_toolset_inplace
 from haystack.utils import deserialize_callable
 from haystack.utils.auth import Secret
 
 _INTEGRATION_SLUG = "haystack"
 _PACKAGE_NAME = "perplexity-haystack"
-_PERPLEXITY_COMPONENT_PATH = "haystack_integrations.components.generators.perplexity.PerplexityChatGenerator"
-_PERPLEXITY_INTERNAL_COMPONENT_PATH = (
-    "haystack_integrations.components.generators.perplexity.chat.chat_generator.PerplexityChatGenerator"
-)
 
 
 def _attribution_header() -> str:
@@ -151,7 +148,7 @@ def to_dict(self) -> dict[str, Any]:
             The serialized component as a dictionary.
         """
         data = super(PerplexityChatGenerator, self).to_dict()  # noqa: UP008
-        data["type"] = _PERPLEXITY_COMPONENT_PATH
+        data["type"] = generate_qualified_class_name(type(self))
         data["init_parameters"]["extra_headers"] = self.extra_headers
         return data
 
@@ -175,5 +172,4 @@ def from_dict(cls, data: dict[str, Any]) -> "PerplexityChatGenerator":
         if serialized_callback_handler:
             data["init_parameters"]["streaming_callback"] = deserialize_callable(serialized_callback_handler)
 
-        data["type"] = _PERPLEXITY_INTERNAL_COMPONENT_PATH
         return default_from_dict(cls, data)

integrations/perplexity/src/haystack_integrations/components/websearch/perplexity/perplexity_websearch.py

@@ -113,7 +113,7 @@ def run(
         self,
         query: str,
         search_params: dict[str, Any] | None = None,
-    ) -> dict[str, Any]:
+    ) -> dict[str, list[Document] | list[str]]:
         """
         Search the web using Perplexity and return results as Documents.
 
@@ -127,9 +127,6 @@ def run(
         """
         if self._client is None:
             self.warm_up()
-        if self._client is None:
-            msg = "PerplexityWebSearch client failed to initialize."
-            raise RuntimeError(msg)
 
         response = self._client.post(
             PERPLEXITY_SEARCH_URL,
@@ -144,7 +141,7 @@ async def run_async(
         self,
         query: str,
         search_params: dict[str, Any] | None = None,
-    ) -> dict[str, Any]:
+    ) -> dict[str, list[Document] | list[str]]:
         """
         Asynchronously search the web using Perplexity and return results as Documents.
 
@@ -158,9 +155,6 @@ async def run_async(
         """
         if self._async_client is None:
             self.warm_up()
-        if self._async_client is None:
-            msg = "PerplexityWebSearch async client failed to initialize."
-            raise RuntimeError(msg)
 
         response = await self._async_client.post(
             PERPLEXITY_SEARCH_URL,

integrations/perplexity/tests/test_perplexity_chat_generator.py

@@ -104,7 +104,10 @@ def test_to_dict_default_round_trip(self, monkeypatch):
         component = PerplexityChatGenerator()
         data = component.to_dict()
 
-        assert data["type"] == "haystack_integrations.components.generators.perplexity.PerplexityChatGenerator"
+        assert (
+            data["type"]
+            == "haystack_integrations.components.generators.perplexity.chat.chat_generator.PerplexityChatGenerator"
+        )
         assert data["init_parameters"]["api_key"] == Secret.from_env_var("PERPLEXITY_API_KEY").to_dict()
         assert data["init_parameters"] == {
             "api_key": Secret.from_env_var("PERPLEXITY_API_KEY").to_dict(),

integrations/perplexity/tests/test_perplexity_document_embedder.py

@@ -70,7 +70,7 @@ def test_init_default(self, monkeypatch):
 
         assert embedder.api_key == Secret.from_env_var(["PERPLEXITY_API_KEY"])
         assert embedder.model == "pplx-embed-v1-0.6b"
-        assert embedder.api_base_url == "https://api.perplexity.ai"
+        assert embedder.api_base_url == "https://api.perplexity.ai/v1"
         assert embedder.prefix == ""
         assert embedder.suffix == ""
         assert embedder.batch_size == 32
@@ -115,7 +115,7 @@ def test_to_dict(self, monkeypatch):
             "init_parameters": {
                 "api_key": Secret.from_env_var("PERPLEXITY_API_KEY").to_dict(),
                 "model": "pplx-embed-v1-0.6b",
-                "api_base_url": "https://api.perplexity.ai",
+                "api_base_url": "https://api.perplexity.ai/v1",
                 "prefix": "",
                 "suffix": "",
                 "batch_size": 32,
@@ -176,7 +176,7 @@ def test_from_dict(self, monkeypatch):
             "init_parameters": {
                 "api_key": Secret.from_env_var("PERPLEXITY_API_KEY").to_dict(),
                 "model": "pplx-embed-v1-0.6b",
-                "api_base_url": "https://api.perplexity.ai",
+                "api_base_url": "https://api.perplexity.ai/v1",
                 "prefix": "",
                 "suffix": "",
                 "batch_size": 32,
@@ -193,7 +193,7 @@ def test_from_dict(self, monkeypatch):
 
         assert component.api_key == Secret.from_env_var(["PERPLEXITY_API_KEY"])
         assert component.model == "pplx-embed-v1-0.6b"
-        assert component.api_base_url == "https://api.perplexity.ai"
+        assert component.api_base_url == "https://api.perplexity.ai/v1"
         assert component.prefix == ""
         assert component.suffix == ""
         assert component.batch_size == 32

integrations/perplexity/tests/test_perplexity_text_embedder.py

@@ -63,7 +63,7 @@ def test_init_default(self, monkeypatch):
         embedder = PerplexityTextEmbedder()
 
         assert embedder.api_key == Secret.from_env_var(["PERPLEXITY_API_KEY"])
-        assert embedder.api_base_url == "https://api.perplexity.ai"
+        assert embedder.api_base_url == "https://api.perplexity.ai/v1"
         assert embedder.model == "pplx-embed-v1-0.6b"
         assert embedder.prefix == ""
         assert embedder.suffix == ""
@@ -77,7 +77,7 @@ def test_init_with_parameters(self):
         )
 
         assert embedder.api_key == Secret.from_token("test-api-key")
-        assert embedder.api_base_url == "https://api.perplexity.ai"
+        assert embedder.api_base_url == "https://api.perplexity.ai/v1"
         assert embedder.model == "pplx-embed-v1-4b"
         assert embedder.prefix == "START"
         assert embedder.suffix == "END"
@@ -94,7 +94,7 @@ def test_to_dict(self, monkeypatch):
             "init_parameters": {
                 "api_key": Secret.from_env_var("PERPLEXITY_API_KEY").to_dict(),
                 "model": "pplx-embed-v1-0.6b",
-                "api_base_url": "https://api.perplexity.ai",
+                "api_base_url": "https://api.perplexity.ai/v1",
                 "prefix": "",
                 "suffix": "",
                 "timeout": None,
@@ -139,7 +139,7 @@ def test_from_dict(self, monkeypatch):
             "init_parameters": {
                 "api_key": Secret.from_env_var("PERPLEXITY_API_KEY").to_dict(),
                 "model": "pplx-embed-v1-0.6b",
-                "api_base_url": "https://api.perplexity.ai",
+                "api_base_url": "https://api.perplexity.ai/v1",
                 "prefix": "",
                 "suffix": "",
                 "timeout": None,
@@ -151,7 +151,7 @@ def test_from_dict(self, monkeypatch):
         component = PerplexityTextEmbedder.from_dict(data)
 
         assert component.api_key == Secret.from_env_var(["PERPLEXITY_API_KEY"])
-        assert component.api_base_url == "https://api.perplexity.ai"
+        assert component.api_base_url == "https://api.perplexity.ai/v1"
         assert component.model == "pplx-embed-v1-0.6b"
         assert component.prefix == ""
         assert component.suffix == ""

integrations/perplexity/tests/test_perplexity_websearch.py

@@ -233,19 +233,6 @@ def test_run_empty_results(self):
         assert result["documents"] == []
         assert result["links"] == []
 
-    def test_run_raises_runtime_error_when_warm_up_fails_to_initialize_client(self, monkeypatch):
-        ws = PerplexityWebSearch(api_key=Secret.from_token("test-key"))
-        monkeypatch.setattr(ws, "warm_up", lambda: None)
-        with pytest.raises(RuntimeError, match="PerplexityWebSearch client failed to initialize"):
-            ws.run(query="test")
-
-    @pytest.mark.asyncio
-    async def test_run_async_raises_runtime_error_when_warm_up_fails_to_initialize_client(self, monkeypatch):
-        ws = PerplexityWebSearch(api_key=Secret.from_token("test-key"))
-        monkeypatch.setattr(ws, "warm_up", lambda: None)
-        with pytest.raises(RuntimeError, match="PerplexityWebSearch async client failed to initialize"):
-            await ws.run_async(query="test")
-
     def test_run_drops_none_valued_search_params(self):
         captured: list[httpx.Request] = []
         ws = PerplexityWebSearch(