Enforce Ruff B905

Author: joshmarkovic

contrib/docs/compile_docs.py

@@ -344,7 +344,7 @@ def _create_commit_file(df_path, single_df):
     os.makedirs(commit_path, exist_ok=True)
     with open(os.path.join(commit_path, "commit.txt"), "w") as f:
         for commit, ts in zip(
-            single_df["__init__.py"]["commit"], single_df["__init__.py"]["timestamp"]
+            single_df["__init__.py"]["commit"], single_df["__init__.py"]["timestamp"], strict=False
         ):
             f.write(f"[commit::{commit}][ts::{ts}]\n")
 

contrib/hamilton/contrib/user/skrawcz/customize_embeddings/__init__.py

@@ -409,7 +409,7 @@ def _accuracy_and_se(
         threshold = threshold_thousandths / 1000
         total = 0
         correct = 0
-        for cs, ls in zip(cosine_similarity, labeled_similarity):
+        for cs, ls in zip(cosine_similarity, labeled_similarity, strict=False):
             total += 1
             if cs > threshold:
                 prediction = 1

contrib/hamilton/contrib/user/skrawcz/fine_tuning/__init__.py

@@ -657,7 +657,7 @@ def hold_out_set_predictions(
             )
             predictions.append(prediction)
             questions.append(tokenizer.decode(sample["input_ids"], skip_special_tokens=True))
-    return list(zip(questions, predictions))
+    return list(zip(questions, predictions, strict=False))
 
 
 if __name__ == "__main__":

examples/LLM_Workflows/modular_llm_stack/lancedb_module.py

@@ -68,7 +68,9 @@ def data_objects(
     assert len(ids) == len(titles) == len(text_contents) == len(embeddings)
     return [
         dict(squad_id=id_, title=title, context=context, vector=embedding, **metadata)
-        for id_, title, context, embedding in zip(ids, titles, text_contents, embeddings)
+        for id_, title, context, embedding in zip(
+            ids, titles, text_contents, embeddings, strict=False
+        )
     ]
 
 

examples/LLM_Workflows/modular_llm_stack/marqo_module.py

@@ -58,7 +58,7 @@ def data_objects(
     assert len(ids) == len(titles) == len(text_contents)
     return [
         dict(_id=id, title=title, Description=text_content)
-        for id, title, text_content in zip(ids, titles, text_contents)
+        for id, title, text_content in zip(ids, titles, text_contents, strict=False)
         if id is not None and title is not None or text_content is not None
     ]
 

examples/LLM_Workflows/modular_llm_stack/pinecone_module.py

@@ -62,7 +62,7 @@ def data_objects(
     assert len(ids) == len(titles) == len(embeddings)
     properties = [dict(title=title, **metadata) for title in titles]
     embeddings = [x.tolist() for x in embeddings]
-    return list(zip(ids, embeddings, properties))
+    return list(zip(ids, embeddings, properties, strict=False))
 
 
 def push_to_vector_db(

examples/LLM_Workflows/modular_llm_stack/qdrant_module.py

@@ -59,7 +59,7 @@ def data_objects(
     ids = list(range(len(ids)))
     payloads = [
         dict(id=_id, text_content=text_content, title=title, **metadata)
-        for _id, title, text_content in zip(ids, titles, text_contents)
+        for _id, title, text_content in zip(ids, titles, text_contents, strict=False)
     ]
     embeddings = [x.tolist() for x in embeddings]
     return dict(ids=ids, vectors=embeddings, payload=payloads)

examples/LLM_Workflows/modular_llm_stack/weaviate_module.py

@@ -86,7 +86,7 @@ def data_objects(
     assert len(ids) == len(titles) == len(text_contents)
     return [
         dict(squad_id=id_, title=title, context=context, **metadata)
-        for id_, title, context in zip(ids, titles, text_contents)
+        for id_, title, context in zip(ids, titles, text_contents, strict=False)
     ]
 
 

examples/LLM_Workflows/retrieval_augmented_generation/backend/ingestion.py

@@ -212,7 +212,9 @@ def store_documents(
                 uuid=document_uuid,
             )
 
-            chunk_iterator = zip(pdf_obj["chunked_text"], pdf_obj["chunked_embeddings"])
+            chunk_iterator = zip(
+                pdf_obj["chunked_text"], pdf_obj["chunked_embeddings"], strict=False
+            )
             for chunk_idx, (chunk_text, chunk_embedding) in enumerate(chunk_iterator):
                 chunk_object = dict(content=chunk_text, chunk_index=chunk_idx)
                 chunk_uuid = generate_uuid5(chunk_object, "Chunk")

examples/due_date_probabilities/probability_estimation.py

@@ -133,7 +133,8 @@ def raw_probabilities(raw_data: str) -> pd.DataFrame:
     days = [int(item.split(", ")[1].split()[0]) for item in raw_data]
     probability = [float(item.split()[5].replace("%", "")) / 100 for item in raw_data]
     probabilities_data = [
-        (week * 7 + day, probability) for week, day, probability in zip(weeks, days, probability)
+        (week * 7 + day, probability)
+        for week, day, probability in zip(weeks, days, probability, strict=False)
     ]
     probabilities_df = pd.DataFrame(probabilities_data)
     probabilities_df.columns = ["days", "probability"]