DataTalksClub/llm-zoomcamp

10.2

Adjusted Score

10.2

Raw Score

100%

Time Factor

2026-07-13

Last Push

6.8K

Stars

Jupyter Notebook

Language

46.3K

Lines of Code

205

Files

175

Pattern Hits

2026-07-14

Scan Date

0.16

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 32MEDIUM 97LOW 46

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 175 distinct pattern matches across 15 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Modern AI Meta-Vocabulary72 hits · 211 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	README.md	83	### [Module 1: Agentic RAG](01-agentic-rag/)	COMMENT
MEDIUM⚡	README.md	83	### [Module 1: Agentic RAG](01-agentic-rag/)	COMMENT
MEDIUM⚡	README.md	93	### [Module 3: Orchestration](03-orchestration/)	COMMENT
MEDIUM	README.md	176	- [Timur Kamaliev](https://www.linkedin.com/in/timurkamaliev/) - AI engineer building production LLM systems, RAG pipeli	CODE
MEDIUM	06-best-practices/lessons/01-intro.md	1	# Best Practices for RAG	COMMENT
MEDIUM	06-best-practices/lessons/01-intro.md	8	## The RAG pipeline	COMMENT
MEDIUM	03-orchestration/README.md	28	## Part 3: RAG Workflows	COMMENT
MEDIUM	03-orchestration/lessons/05-rag.md	9	## What is RAG?	COMMENT
MEDIUM	03-orchestration/lessons/05-rag.md	15	## How RAG Works in Kestra	COMMENT
MEDIUM⚡	03-orchestration/lessons/05-rag.md	49	### Step 1: Without RAG	COMMENT
MEDIUM⚡	03-orchestration/lessons/05-rag.md	59	### Step 2: With RAG	COMMENT
MEDIUM	03-orchestration/lessons/05-rag.md	73	## Extending RAG with web search	COMMENT
MEDIUM	03-orchestration/lessons/05-rag.md	94	### Static RAG vs. web search RAG	COMMENT
MEDIUM	02-vector-search/lessons/09-onnx-embedder.md	133	wget https://raw.githubusercontent.com/DataTalksClub/llm-zoomcamp/main/01-agentic-rag/code/ingest.py	CODE
MEDIUM	02-vector-search/lessons/03-embeddings-dataset.md	17	wget https://raw.githubusercontent.com/DataTalksClub/llm-zoomcamp/main/01-agentic-rag/code/ingest.py	CODE
MEDIUM	02-vector-search/lessons/08-pgvector.md	241	## Using it in RAG	STRING
MEDIUM	02-vector-search/lessons/06-rag-vector.md	1	# RAG with Vector Search	COMMENT
MEDIUM	02-vector-search/lessons/06-rag-vector.md	29	wget https://raw.githubusercontent.com/DataTalksClub/llm-zoomcamp/main/01-agentic-rag/code/rag_helper.py	CODE
MEDIUM	02-vector-search/lessons/06-rag-vector.md	30	wget https://raw.githubusercontent.com/DataTalksClub/llm-zoomcamp/main/01-agentic-rag/code/ingest.py	CODE
MEDIUM	02-vector-search/lessons/07-sqlitesearch-vector.md	174	## Using sqlitesearch vector search in RAG	COMMENT
MEDIUM	04-evaluation/README.md	25	## Part 2: RAG and Agent Evaluation	COMMENT
MEDIUM	04-evaluation/lessons/12-rag-answers.md	1	# Generating RAG Answers	COMMENT
MEDIUM	04-evaluation/lessons/12-rag-answers.md	66	## Running RAG	COMMENT
MEDIUM	04-evaluation/lessons/11-evaluation-intro.md	1	# RAG and Agent Evaluation	COMMENT
MEDIUM	04-evaluation/lessons/13-llm-as-judge.md	40	## Loading the RAG answers	COMMENT
MEDIUM	etc/chunking.md	45	### Implementing Chunking for RAG	COMMENT
MEDIUM	07-project-example/lessons/01-intro.md	112	## The RAG flow	STRING
MEDIUM	07-project-example/lessons/04-interface.md	23	rag.py # RAG flow + search + LLM	CODE
MEDIUM	07-project-example/lessons/04-interface.md	71	## RAG module	COMMENT
MEDIUM	07-project-example/lessons/05-monitoring.md	11	## Adding evaluation to the RAG flow	COMMENT
MEDIUM	07-project-example/lessons/03-evaluating-rag.md	1	# Evaluating RAG	COMMENT
MEDIUM	07-project-example/lessons/03-evaluating-rag.md	11	## LLM-as-a-Judge for RAG	COMMENT
MEDIUM	cohorts/2025/pre-course-q-a-stream-summary.md	24	## 4. Will the course help me implement RAG from a live database?	COMMENT
MEDIUM	cohorts/2025/pre-course-q-a-stream-summary.md	28	## 5. Are we going to do any agentic AI development in this course?	COMMENT
MEDIUM	cohorts/2025/pre-course-q-a-stream-summary.md	47	## 9. Do we discuss evaluating LLM-based applications, generating metrics, and setting up guardrails?	COMMENT
MEDIUM	cohorts/2025/pre-course-q-a-stream-summary.md	58	## 11. Is the RAG pipeline included in the course?	COMMENT
MEDIUM	cohorts/2025/02-vector-search/README.md	51	## 2.5 RAG with Vector Search	COMMENT
MEDIUM	cohorts/2025/02-vector-search/homework.md	150	## Q5. Selecting the embedding model	COMMENT
MEDIUM	cohorts/2025/03-evaluation/README.md	1	# RAG and LLM Evaluation	COMMENT
MEDIUM	cohorts/2025/03-evaluation/README.md	78	## 3.5 Offline vs Online (RAG) evaluation	COMMENT
MEDIUM	cohorts/2025/03-evaluation/README.md	89	## 3.6 Generating data for offline RAG evaluation	COMMENT
MEDIUM	cohorts/2025/03-evaluation/README.md	108	## 3.7 Offline RAG evaluation: cosine similarity	COMMENT
MEDIUM	cohorts/2025/03-evaluation/README.md	130	## 3.8 Offline RAG evaluation: LLM as a judge	COMMENT
MEDIUM	cohorts/2025/01-intro/README.md	15	## 1.1 Introduction to LLM and RAG	COMMENT
MEDIUM	cohorts/2025/01-intro/README.md	85	## 1.5 Cleaned RAG flow	COMMENT
MEDIUM	cohorts/2024/04-monitoring/README.md	25	## 4.2 Offline vs Online (RAG) evaluation	COMMENT
MEDIUM	cohorts/2024/04-monitoring/README.md	36	## 4.3 Generating data for offline RAG evaluation	COMMENT
MEDIUM	cohorts/2024/04-monitoring/README.md	49	## 4.4 Offline RAG evaluation: cosine similarity	COMMENT
MEDIUM	cohorts/2024/04-monitoring/README.md	71	## 4.5 Offline RAG evaluation: LLM as a judge	COMMENT
MEDIUM	cohorts/2024/05-orchestration/README.md	1	# Data Preparation in RAG	COMMENT
MEDIUM	cohorts/2024/05-orchestration/homework.md	58	## Creating a RAG pipeline	COMMENT
MEDIUM	cohorts/2024/02-open-source/README.md	190	## 2.9 UI for RAG	COMMENT
MEDIUM	cohorts/2026/03-orchestration/homework.md	30	## Question 2: RAG vs No RAG	COMMENT
MEDIUM	cohorts/2026/01-agentic-rag/homework.md	1	## Homework: Agentic RAG	COMMENT
MEDIUM	cohorts/2026/01-agentic-rag/homework.md	118	## Q3. RAG	COMMENT
MEDIUM	cohorts/2026/01-agentic-rag/homework.md	124	wget https://raw.githubusercontent.com/DataTalksClub/llm-zoomcamp/main/01-agentic-rag/code/rag_helper.py	CODE
MEDIUM	cohorts/2026/01-agentic-rag/homework.md	199	## Q5. RAG with chunking	COMMENT
MEDIUM	05-monitoring/lessons/04-metrics.md	64	## Instrumented RAG	COMMENT
MEDIUM	05-monitoring/lessons/13-docker-compose.md	27	├── assistant.py # RAG pipeline + LLM	CODE
MEDIUM	01-agentic-rag/README.md	1	# Module 1: Agentic RAG	COMMENT
12 more matches not shown…

Cross-File Repetition24 hits · 120 pts

Severity	File	Snippet	Context
HIGH	04-evaluation/code/rag_helper.py	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	cohorts/2026/05-monitoring/rag_helper.py	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	05-monitoring/code/rag_helper.py	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	01-agentic-rag/code/rag_helper.py	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	01-agentic-rag/lessons/08-rag-helper.md	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	01-agentic-rag/lessons/06-building-prompt.md	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	01-agentic-rag/lessons/03-rag.md	your task is to answer questions from the course participants based on the provided context. use the context to find rel	STRING
HIGH	04-evaluation/lessons/14-agent-evaluation.md	search the faq database for entries matching the given query.	STRING
HIGH	cohorts/2026/workshops/dlt/homework/agent.py	search the faq database for entries matching the given query.	STRING
HIGH	01-agentic-rag/lessons/15-frameworks.md	search the faq database for entries matching the given query.	STRING
HIGH	07-project-example/lessons/05-monitoring.md	create table conversations ( id text primary key, question text not null, answer text not null, course text not null, mo	STRING
HIGH	cohorts/2024/04-monitoring/code.md	create table conversations ( id text primary key, question text not null, answer text not null, course text not null, mo	STRING
HIGH	cohorts/2024/04-monitoring/app/db.py	create table conversations ( id text primary key, question text not null, answer text not null, course text not null, mo	STRING
HIGH	07-project-example/lessons/05-monitoring.md	create table feedback ( id serial primary key, conversation_id text references conversations(id), feedback integer not n	STRING
HIGH	cohorts/2024/04-monitoring/code.md	create table feedback ( id serial primary key, conversation_id text references conversations(id), feedback integer not n	STRING
HIGH	cohorts/2024/04-monitoring/app/db.py	create table feedback ( id serial primary key, conversation_id text references conversations(id), feedback integer not n	STRING
HIGH	07-project-example/lessons/05-monitoring.md	insert into conversations (id, question, answer, course, model_used, response_time, relevance, relevance_explanation, pr	STRING
HIGH	cohorts/2024/04-monitoring/code.md	insert into conversations (id, question, answer, course, model_used, response_time, relevance, relevance_explanation, pr	STRING
HIGH	cohorts/2024/04-monitoring/app/db.py	insert into conversations (id, question, answer, course, model_used, response_time, relevance, relevance_explanation, pr	STRING
HIGH	cohorts/2025/01-intro/homework.md	you're a course teaching assistant. answer the question based on the context from the faq database. use only the facts f	STRING
HIGH	cohorts/2024/04-monitoring/code.md	you're a course teaching assistant. answer the question based on the context from the faq database. use only the facts f	STRING
HIGH	cohorts/2024/04-monitoring/app/assistant.py	you're a course teaching assistant. answer the question based on the context from the faq database. use only the facts f	STRING
HIGH	cohorts/2024/01-intro/homework.md	you're a course teaching assistant. answer the question based on the context from the faq database. use only the facts f	STRING
HIGH	cohorts/2024/02-open-source/qa_faq.py	you're a course teaching assistant. answer the question based on the context from the faq database. use only the facts f	STRING

Structural Annotation Overuse14 hits · 26 pts

Severity	File	Line	Snippet	Context
LOW⚡	03-orchestration/lessons/05-rag.md	49	### Step 1: Without RAG	COMMENT
LOW⚡	03-orchestration/lessons/05-rag.md	59	### Step 2: With RAG	COMMENT
LOW	03-orchestration/lessons/03-setup.md	11	## Step 1: Start Kestra	COMMENT
LOW	03-orchestration/lessons/03-setup.md	28	## Step 2: Obtain API Keys	COMMENT
LOW	03-orchestration/lessons/03-setup.md	51	## Step 3: Configure API Keys in Kestra	COMMENT
LOW	03-orchestration/lessons/03-setup.md	73	## Step 4: Import Example Flows	COMMENT
LOW	03-orchestration/lessons/03-setup.md	89	## Step 5: Run Your First Agent	COMMENT
LOW⚡	…rts/2024/02-open-source/serving-hugging-face-models.md	5	### Step 1: Authenticate and Accept the User Agreement	COMMENT
LOW⚡	…rts/2024/02-open-source/serving-hugging-face-models.md	12	### Step 2: Install Hugging Face Transformers and Other Dependencies	COMMENT
LOW⚡	…rts/2024/02-open-source/serving-hugging-face-models.md	20	### Step 3: Authenticate with Hugging Face CLI	COMMENT
LOW⚡	…rts/2024/02-open-source/serving-hugging-face-models.md	30	### Step 4: Download the Model	COMMENT
LOW	…rts/2024/02-open-source/serving-hugging-face-models.md	48	### Step 5: Load the Model Locally	COMMENT
LOW	…rts/2024/02-open-source/serving-hugging-face-models.md	63	### Step 6: Serve the Model	COMMENT
LOW	…rts/2024/02-open-source/serving-hugging-face-models.md	97	### Step 7: Deploy the Service	COMMENT

Magic Placeholder Names6 hits · 25 pts

Severity	File	Line	Snippet	Context
HIGH	06-best-practices/documents-with-ids.json	6212	"text": "Problem: when running the preprocess_data.py file you get the following error:\n\nwandb: ERROR api_key not	CODE
HIGH	…3-evaluation/search_evaluation/documents-with-ids.json	6212	"text": "Problem: when running the preprocess_data.py file you get the following error:\n\nwandb: ERROR api_key not	CODE
HIGH	cohorts/2025/01-intro/documents.json	4451	"text": "Problem: when running the preprocess_data.py file you get the following error:\n\nwandb: ERROR api_key	CODE
HIGH	cohorts/2024/04-monitoring/code.md	1485	OPENAI_API_KEY = os.getenv('OPENAI_API_KEY', 'your-api-key-here')	STRING
HIGH	cohorts/2024/04-monitoring/code.md	1893	OPENAI_API_KEY = os.getenv('OPENAI_API_KEY', 'your-api-key-here')	STRING
HIGH	cohorts/2024/04-monitoring/app/assistant.py	13	OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "your-api-key-here")	CODE

Self-Referential Comments9 hits · 18 pts

Severity	File	Line	Snippet	Context
MEDIUM	06-best-practices/documents-with-ids.json	549	"text": "error: could not change permissions of directory \"/var/lib/postgresql/data\": Operation not permitted vol	CODE
MEDIUM	06-best-practices/documents-with-ids.json	1529	"text": "There are multiple benefits of using Cloud Functions to automate tasks in Google Cloud.\nUse below Cloud Fu	CODE
MEDIUM	06-best-practices/documents-with-ids.json	3041	"text": "Docker Commands\n# Create a Docker Image from a base image\nDocker run -it ubuntu bash\n#List docker images	CODE
MEDIUM	…3-evaluation/search_evaluation/documents-with-ids.json	549	"text": "error: could not change permissions of directory \"/var/lib/postgresql/data\": Operation not permitted vol	CODE
MEDIUM	…3-evaluation/search_evaluation/documents-with-ids.json	1529	"text": "There are multiple benefits of using Cloud Functions to automate tasks in Google Cloud.\nUse below Cloud Fu	CODE
MEDIUM	…3-evaluation/search_evaluation/documents-with-ids.json	3041	"text": "Docker Commands\n# Create a Docker Image from a base image\nDocker run -it ubuntu bash\n#List docker images	CODE
MEDIUM	cohorts/2025/01-intro/documents.json	396	"text": "error: could not change permissions of directory \"/var/lib/postgresql/data\": Operation not permitted	CODE
MEDIUM	cohorts/2025/01-intro/documents.json	1096	"text": "There are multiple benefits of using Cloud Functions to automate tasks in Google Cloud.\nUse below Clou	CODE
MEDIUM	cohorts/2025/01-intro/documents.json	2176	"text": "Docker Commands\n# Create a Docker Image from a base image\nDocker run -it ubuntu bash\n#List docker im	CODE

Slop Phrases9 hits · 15 pts

Severity	File	Line	Snippet	Context
LOW	06-best-practices/documents-with-ids.json	724	"text": "ImportError: no pq wrapper available.\nAttempts made:\n- couldn't import \\dt\nopg 'c' implementation: No m	CODE
MEDIUM	06-best-practices/documents-with-ids.json	1277	"text": "It means your container consumed all available RAM allocated to it. It can happen in particular when workin	CODE
MEDIUM	06-best-practices/documents-with-ids.json	5008	"text": "Problem: When trying to install tflite_runtime with\n!pip install --extra-index-url https://google-coral.gi	CODE
LOW	…3-evaluation/search_evaluation/documents-with-ids.json	724	"text": "ImportError: no pq wrapper available.\nAttempts made:\n- couldn't import \\dt\nopg 'c' implementation: No m	CODE
MEDIUM	…3-evaluation/search_evaluation/documents-with-ids.json	1277	"text": "It means your container consumed all available RAM allocated to it. It can happen in particular when workin	CODE
MEDIUM	…3-evaluation/search_evaluation/documents-with-ids.json	5008	"text": "Problem: When trying to install tflite_runtime with\n!pip install --extra-index-url https://google-coral.gi	CODE
LOW	cohorts/2025/01-intro/documents.json	521	"text": "ImportError: no pq wrapper available.\nAttempts made:\n- couldn't import \\dt\nopg 'c' implementation:	CODE
MEDIUM	cohorts/2025/01-intro/documents.json	916	"text": "It means your container consumed all available RAM allocated to it. It can happen in particular when wo	CODE
MEDIUM	cohorts/2025/01-intro/documents.json	3586	"text": "Problem: When trying to install tflite_runtime with\n!pip install --extra-index-url https://google-cora	CODE

Synthetic Comment Markers2 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH	cohorts/2025/03-evaluation/README.md	55	* [queries generated by OpenAI (pickle)](search_evaluation/results.bin)	COMMENT
HIGH	cohorts/2024/03-vector-search/README.md	57	* [queries generated by OpenAI (pickle)](eval/results.bin)	COMMENT

Excessive Try-Catch Wrapping15 hits · 12 pts

Severity	File	Line	Snippet	Context
LOW	04-evaluation/code/evaluation_utils.py	64	except Exception:	CODE
LOW	cohorts/2024/04-monitoring/code.md	863	except Exception as e:	STRING
MEDIUM	cohorts/2024/04-monitoring/code.md	864	print(f"An error occurred during database initialization: {e}")	STRING
LOW	cohorts/2024/04-monitoring/code.md	879	except Exception as e:	STRING
MEDIUM	cohorts/2024/04-monitoring/code.md	880	print(f"An error occurred while saving the conversation: {e}")	STRING
LOW	cohorts/2024/04-monitoring/code.md	895	except Exception as e:	STRING
MEDIUM	cohorts/2024/04-monitoring/code.md	896	print(f"An error occurred while saving feedback: {e}")	STRING
LOW	cohorts/2024/04-monitoring/code.md	981	except Exception as e:	STRING
MEDIUM	cohorts/2024/04-monitoring/code.md	982	print(f"An error occurred during database initialization: {e}")	STRING
LOW	cohorts/2024/04-monitoring/code.md	997	except Exception as e:	STRING
MEDIUM	cohorts/2024/04-monitoring/code.md	998	print(f"An error occurred while saving the conversation: {e}")	STRING
LOW	cohorts/2024/04-monitoring/code.md	1013	except Exception as e:	STRING
MEDIUM	cohorts/2024/04-monitoring/code.md	1014	print(f"An error occurred while saving feedback: {e}")	STRING
LOW	cohorts/2024/05-orchestration/code/06_retrieval.py	64	except Exception as e:	CODE
LOW	05-monitoring/code/evaluation_utils.py	64	except Exception:	CODE

AI Slop Vocabulary4 hits · 8 pts

Severity	File	Line	Snippet	Context
MEDIUM	06-best-practices/documents-with-ids.json	3041	"text": "Docker Commands\n# Create a Docker Image from a base image\nDocker run -it ubuntu bash\n#List docker images	CODE
MEDIUM	…3-evaluation/search_evaluation/documents-with-ids.json	3041	"text": "Docker Commands\n# Create a Docker Image from a base image\nDocker run -it ubuntu bash\n#List docker images	CODE
MEDIUM	cohorts/2025/01-intro/documents.json	2176	"text": "Docker Commands\n# Create a Docker Image from a base image\nDocker run -it ubuntu bash\n#List docker im	CODE
MEDIUM	cohorts/2025/01-intro/documents-llm.json	176	"text": "You can limit the amount of memory used in the ElasticSearch container by adding the next line to the e	CODE

Redundant / Tautological Comments4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	06-best-practices/documents-with-ids.json	1501	"text": "Reference:\nhttps://cloud.google.com/bigquery/docs/external-data-cloud-storage\nSolution:\nfrom google.clou	CODE
LOW	…3-evaluation/search_evaluation/documents-with-ids.json	1501	"text": "Reference:\nhttps://cloud.google.com/bigquery/docs/external-data-cloud-storage\nSolution:\nfrom google.clou	CODE
LOW	cohorts/2025/01-intro/documents.json	1076	"text": "Reference:\nhttps://cloud.google.com/bigquery/docs/external-data-cloud-storage\nSolution:\nfrom google.	CODE
LOW	cohorts/2025/01-intro/documents-llm.json	116	"text": "You can store your different API keys in a yaml file that you will add in your .gitignore file. Be care	CODE

Hyper-Verbose Identifiers4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	06-best-practices/lessons/03-reranking.md	32	def elastic_search_hybrid_rrf(field, query, vector, course):	CODE
LOW	06-best-practices/lessons/03-reranking.md	93	def elastic_search_hybrid_rrf(field, query, vector, course, k=60):	CODE
LOW	04-evaluation/lessons/04-search-evaluation.md	158	def compute_relevance_total_text(ground_truth):	CODE
LOW	cohorts/2025/0a-agents/mcp_client.py	185	def convert_mcp_tool_to_function_format(mcp_tool):	CODE

Unused Imports4 hits · 4 pts

Severity	File	Line	Context
LOW	cohorts/2024/04-monitoring/app/generate_data.py	6	CODE
LOW	cohorts/2024/05-orchestration/code/06_retrieval.py	1	CODE
LOW	cohorts/2024/02-open-source/qa_faq.py	2	CODE
LOW	05-monitoring/code/judge.py	1	CODE

AI Structural Patterns3 hits · 3 pts

Severity	File	Line	Context
LOW	cohorts/2025/0a-agents/mcp_client.py	159	CODE
LOW	cohorts/2026/05-monitoring/rag_helper.py	64	CODE
LOW	05-monitoring/code/metrics.py	51	CODE

Over-Commented Block3 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	cohorts/2026/workshops/dlt/homework/agent.py	41	# In Module 1, the search function used a global `index` variable directly.	COMMENT
LOW	cohorts/2026/workshops/dlt/homework/agent.py	61	# Pydantic AI replaces all three:	COMMENT
LOW	cohorts/2026/workshops/dlt/homework/agent.py	81	#	COMMENT

Deep Nesting2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	cohorts/2026/workshops/dlt/code/filesystem_pipeline.py	47		CODE
LOW	cohorts/2026/workshops/dlt/code/filesystem_pipeline.py	51		CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings