chore: telemetry for rankers, readers, retrievers, writers (#6075)

* add telemetry to pipelines 2.0

* only collect data if telemetry is on

* reno

* add downsampling

* typing

* manual tests

* pylint

* simplify code

* Update haystack/preview/telemetry/__init__.py

* look for _telemetry_data

* rather index by component type

* black

* mypy

* error handling

* comment

* review feedback & small improvements

* defaultdict

* stray changes

* try-catch

* method instead of attribute

* fixes

* remove print statements

* lint

* invert condition

* always send the first event of the day

* collect specs

* track 2nd and 3rd events too

* send first event and then max 1 event a minute

* rename constant

* black

* add test

* add telemetry for rankers readers and retrievers

* get only the type of docstore, not the whole object

haystack/preview/components/rankers/similarity.py

@@ -56,6 +56,12 @@ class SimilarityRanker:
         self.model = None
         self.tokenizer = None
 
+    def _get_telemetry_data(self) -> Dict[str, Any]:
+        """
+        Data that is sent to Posthog for usage analytics.
+        """
+        return {"model": str(self.model_name_or_path)}
+
     def warm_up(self):
         """
         Warm up the model and tokenizer used in scoring the documents.

haystack/preview/components/readers/extractive.py

@@ -67,6 +67,12 @@ class ExtractiveReader:
         self.no_answer = no_answer
         self.calibration_factor = calibration_factor
 
+    def _get_telemetry_data(self) -> Dict[str, Any]:
+        """
+        Data that is sent to Posthog for usage analytics.
+        """
+        return {"model": self.model_name_or_path}
+
     def to_dict(self) -> Dict[str, Any]:
         """
         Serialize this component to a dictionary.

haystack/preview/components/retrievers/memory_bm25_retriever.py

@@ -41,6 +41,12 @@ class MemoryBM25Retriever:
         self.top_k = top_k
         self.scale_score = scale_score
 
+    def _get_telemetry_data(self) -> Dict[str, Any]:
+        """
+        Data that is sent to Posthog for usage analytics.
+        """
+        return {"document_store": type(self.document_store).__name__}
+
     def to_dict(self) -> Dict[str, Any]:
         """
         Serialize this component to a dictionary.

haystack/preview/components/retrievers/memory_embedding_retriever.py

@@ -44,6 +44,12 @@ class MemoryEmbeddingRetriever:
         self.scale_score = scale_score
         self.return_embedding = return_embedding
 
+    def _get_telemetry_data(self) -> Dict[str, Any]:
+        """
+        Data that is sent to Posthog for usage analytics.
+        """
+        return {"document_store": type(self.document_store).__name__}
+
     def to_dict(self) -> Dict[str, Any]:
         """
         Serialize this component to a dictionary.

haystack/preview/components/writers/document_writer.py

@@ -19,6 +19,12 @@ class DocumentWriter:
         self.document_store = document_store
         self.policy = policy
 
+    def _get_telemetry_data(self) -> Dict[str, Any]:
+        """
+        Data that is sent to Posthog for usage analytics.
+        """
+        return {"document_store": type(self.document_store).__name__}
+
     def to_dict(self) -> Dict[str, Any]:
         """
         Serialize this component to a dictionary.