Add difficulty meta to notebooks (#98)

* Add difficulty meta to notebooks

Author: anarafaelaferro

CONTRIBUTING.md

@@ -4,6 +4,7 @@ description="""\
     Run your MongoDB queries on SingleStore Kai with no code change. \
     """
 icon="database"
+difficulty="beginner"
 tags=["starter", "mongo", "kai"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/atlas-and-kai/meta.toml

@@ -4,6 +4,7 @@ description = """\
     Performs backup either single or multiple databases to AWS S3. \
     """
 icon = "database"
+difficulty="beginner"
 tags = ["starter", "backup"]
 destinations = ["spaces"]
 minimum_tier="standard"

notebooks/backup-database-s3/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Learn how to build a multi-agent group chat with RAG using Autogen and SingleStore   \
     """
 icon="vector-circle"
+difficulty="beginner"
 tags=["starter", "autogen", "rag", "multiagent", "groupchat"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/building-a-multi-agent-ai-app-with-autogen/meta.toml

@@ -3,6 +3,7 @@ title = "Ingest data from MONGODB® to SingleStore using SQL commands"
 description = """
     Setup CDC Replication from MongoDB® to SingleStore using SQL commands. """
 icon = "database"
+difficulty="intermediate"
 tags =  ["mongo", "pipeline", "cdc", "ingest", "kai"]
 destinations = ["spaces"]
 minimum_tier="standard"

notebooks/cdc-mongodb-sql-commands/meta.toml

@@ -3,6 +3,7 @@ title = "Ingest data from Confluent Cloud (Kafka)"
 description = """
     A step-by-step guide on seamlessly ingesting data from Confluent Cloud (Kafka) into your SingleStoreDB database using a robust pipeline. """
 icon = "confluent-logo"
+difficulty="advanced"
 tags = ["advanced", "confluent", "kafka", "pipeline", "realtime"]
 destinations = ["spaces"]
 minimum_tier="standard"

notebooks/confluent-cloud-integration/meta.toml

@@ -3,6 +3,7 @@ title="Evaluating LLMs with Uptrain"
 description="""\
 Using Uptrain to evaluate LLMs built with SingleStore as the contextual store. This notebook uses OpenAI embedding models and Langchain as a development framework.
     """
+difficulty="intermediate"
 tags=["openai", "llm", "vectordb", "langchain"]
 icon="vector-circle"
 destinations=["spaces"]

notebooks/evaluating-llms-with-uptrain/meta.toml

@@ -5,6 +5,7 @@ description="""\
     familiar DataFrame syntax in addition to SQL.
     """
 icon="browser"
+difficulty="beginner"
 tags=["starter", "dataframe", "python"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/getting-started-with-dataframes/meta.toml

@@ -6,6 +6,7 @@ description="""\
     Stage files all from SQL.
     """
 icon="browser"
+difficulty="beginner"
 tags=["starter", "fusion", "python"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/getting-started-with-fusion-sql/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Setup Zero ETL data replication from MongoDB to SingleStore \
     """
 icon="pipeline"
+difficulty="intermediate"
 tags=["cdc", "mongo", "kai"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/getting-started-with-mongocdc/meta.toml

@@ -5,6 +5,7 @@ description="""\
     visualization and analysis. \
     """
 icon="notes"
+difficulty="beginner"
 tags=["starter", "python", "sqrl"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/getting-started-with-notebooks/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Using OpenAI to build an app that can take images, audio, and text data to generate output
     """
 icon="chart-network"
+difficulty="advanced"
 tags=["advanced", "openai", "genai", "vectordb"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/how-to-build-llm-apps-that-can-see-hear-speak/meta.toml

@@ -1,6 +1,7 @@
 [meta]
 title="Hybrid Full-text and Vector Search"
 description="Example of similarity search over vector data and a hybrid search that combines full-text search with an indexed vector search."
+difficulty="beginner"
 tags=["starter", "openai", "genai", "vectordb"]
 destinations=["spaces"]
 icon="vector-circle"

notebooks/hybrid-full-text-vector-search/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Hybrid search combines keyword search with semantic search,
     aiming to provide more accurate results.
     """
+difficulty="beginner"
 tags=["starter", "openai", "genai", "vectordb"]
 icon="vector-circle"
 destinations=["spaces"]

notebooks/hybrid-search/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Facial recognition using dot_product function on vectors stored in SingleStoreDB. \
     """
 icon="face-viewfinder"
+difficulty="beginner"
 tags=["starter", "vectordb", "genai", "facenet"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/image-matching-with-sql/meta.toml

@@ -2,6 +2,7 @@
 title="Ask questions of your PDFs with Unstructured"
 description="Ask questions of your unstructured PDFs. In this notebook, Unstructured.io ingests pdfs accurately, then Open AI is used to create embeddings, the vector data is stored in SingleStore and finally ask questions of your PDF data"
 icon="file-export"
+difficulty="intermediate"
 tags=["ingest", "pdf","vector","unstructured"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/ingest-pdfs-with-unstructured/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Discover the power of SingleStoreDB's external functions to dynamically fetch and store vector embeddings from leading AI models into your database. This demo highlights leveraging SingleStore's robust vector data type and external functions for efficient management and analysis of machine learning embeddings.\
     """
 icon="vector-circle"
+difficulty="intermediate"
 tags=["vectordb", "genai", "openai", "rag", "huggingface"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/inserting-embeddings-from-multiple-models-into-singlestore-using-external-functions/meta.toml

@@ -1,6 +1,7 @@
 [meta]
 title="InsureGPT: OpenAI and SingleStore for Insurance"
 description="Creating an insurance analysis with OpenAI and vectorizing the results into SingleStore."
+difficulty="intermediate"
 tags=["openai", "langchain"]
 icon="database"
 minimum_tier="standard"

notebooks/insure-gpt-demo/meta.toml

@@ -5,6 +5,7 @@ description="""\
     the SingleStoreDB Python library, SQLAlchemy, and Ibis.
     """
 icon="database"
+difficulty="beginner"
 tags=["starter", "dataframe", "python"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/integrating-with-pandas/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Runs through the queries to bring data residing in object storage onto disk for a specified database. \
     """
 icon="database"
+difficulty="advanced"
 tags=["advanced", "automation", "tuning"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/kebab-case/meta.toml

@@ -4,6 +4,7 @@ description="""\
     LangChain connector to use SingleStoreDB as your vector database for your apps. \
     """
 icon="vector-circle"
+difficulty="intermediate"
 tags=["vectordb", "genai", "langchain"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/launch-open-source-apps-with-langchain/meta.toml

@@ -4,6 +4,7 @@ description="""\
     This notebook will help you load JSON files from a public open AWS S3 bucket.
     """
 icon="chart-network"
+difficulty="advanced"
 tags=["advanced", "pipeline", "json", "s3"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/load-json-files-s3/meta.toml

@@ -4,6 +4,7 @@ description="""\
     This notebook guides you through data ingestion of CSV files from an AWS S3 location into your shared tier workspace. \
     """
 icon="chart-network"
+difficulty="intermediate"
 tags=["pipeline", "s3"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/load-s3-files-into-shared-tier/meta.toml

@@ -5,6 +5,7 @@ description="""\
     Cloud using Fusion SQL.
     """
 icon="files"
+difficulty="beginner"
 tags=["starter", "fusion", "python"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/managing-stage-files-with-fusion-sql/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Movie recommendation engine using vectors stored in SingleStore to find your next watch. \
     """
 icon="camera-movie"
+difficulty="advanced"
 tags=["advanced", "vectordb", "genai", "openai"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/movie-recommendation/meta.toml

@@ -6,6 +6,7 @@ description="""
     for identifying infrequent occurrences, a common requirement in fields such as cybersecurity
     and fraud detection where only a small percentage of events are potentially malicious."""
 icon="browser"
+difficulty="advanced"
 tags=["advanced", "cybersecurity", "vectordb", "iot", "ai"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/network-intrusion-detection-part-1/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Part 2 or Real-time threat Detection - Validate the accuracy of the
     threat detection model with a test dataset"""
 icon="browser"
+difficulty="advanced"
 tags=["advanced", "cybersecurity", "vectordb", "iot", "ai"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/network-intrusion-detection-part-2/meta.toml

@@ -5,6 +5,7 @@ description="""
     and visualize Threat Detection on incoming logs.
     This notebook requires adjustments to work out of the box."""
 icon="browser"
+difficulty="advanced"
 tags=["advanced", "cybersecurity", "vectordb", "iot", "ai"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/network-intrusion-detection-part-3/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Foundational guide to notebooks with essential tips and tricks. \
     """
 icon="notes"
+difficulty="beginner"
 tags=["starter", "python", "dataframes"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/notebook-basics/meta.toml

@@ -4,6 +4,7 @@ description="""\
     This notebook will help you understand how you can take advantage of SingleStoreDB distributed capability using TPCH-100.
 """
 icon="database"
+difficulty="advanced"
 tags=["advanced", "performance", "turning", "shardkey", "ingest", "tpch"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/optimize-performance-with-tpch-100/meta.toml

@@ -4,6 +4,7 @@ description="""\
     This notebook will help you perform database performance troubleshoot
 """
 icon="database"
+difficulty="beginner"
 tags=["troubleshoot", "performance", "tuning", "starter"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/performance-troubleshooting/meta.toml

@@ -3,6 +3,7 @@ title="Kafka Pipelines and Query Tuning"
 description="""\
     Create a SingleStore pipeline to track the International Space Station and adjust queries & schema to optimize performance.
     """
+difficulty="intermediate"
 tags=["beginner", "kafka", "pipeline", "querytuning"]
 icon="database"
 destinations=["spaces"]

notebooks/pipelines-query-tuning/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Infuse domain-specific knowledge from SingleStoreDB into generative AI models on Amazon Bedrock to showcase Question & Answering using RAG (retrieval-agumented generation) to improve the quality of responses.\
     """
 icon="crystal-ball"
+difficulty="beginner"
 tags=["vectordb", "genai", "bedrock", "rag", "starter"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/rag-with-bedrock/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Real-time anomaly detection in IoT sensor data, harnessing the robust capabilities of SingleStoreDB and advanced analytical techniques. \
     """
 icon="chart-scatter"
+difficulty="intermediate"
 tags=["vectordb", "realtime"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/real-time-anomaly-detection/meta.toml

@@ -4,6 +4,7 @@ description="""\
 We demonstrate how to build and host a real-time recommendation engine for free with SingleStore. The notebook also leverages our new SingleStore Job Service to ensure that the latest data is ingested and used in providing recommendations.\
     """
 icon="crystal-ball"
+difficulty="beginner"
 tags=["starter", "openai", "vercel", "realtime", "vectordb"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/real-time-recommendation-engine/meta.toml

@@ -1,6 +1,7 @@
 [meta]
 title="Representing Unstructured Data as Vectors"
 description="Transforming unstructured data into vectors and representing them in a 3-dimensional space to find the distance between them using various techniques"
+difficulty="intermediate"
 tags=["vectors", "unstructureddata"]
 icon="vector-circle"
 minimum_tier="standard"

notebooks/representing-unstructured-data-as-vectors/meta.toml

@@ -4,6 +4,7 @@ description = """\
     This notebook will help you perform database restore from AWS S3.
 """
 icon = "database"
+difficulty="beginner"
 tags = ["starter", "admin", "restore"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/restore-database-from-s3/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Resume Evaluator using vectors stored in SingleStore to find sutiable resume for your job description, with Indexed ANN search.\
     """
 icon="arrows-spin"
+difficulty="intermediate"
 tags=["vectordb", "genai", "openai", "rag"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/resume-evaluator-ANN-index-search/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Resume Evaluator using vectors stored in SingleStore to find sutiable resume for your job description. \
     """
 icon="arrows-spin"
-tags=["stater", "vectordb", "genai", "openai"]
+difficulty="beginner"
+tags=["starter", "vectordb", "genai", "openai"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/resume-evaluator/meta.toml

@@ -4,6 +4,7 @@ description = """\
     Simulate searching through 10 million paragraphs in Wikipedia for information about video games, and generate answers using RAG! \
     """
 icon = "book-open-cover"
+difficulty="advanced"
 tags = ["vector", "advanced", "vectordb", "hybridsearch", "rag", "ann"]
 destinations = ["spaces"]
 minimum_tier="standard"

notebooks/searching-all-of-wikipedia/meta.toml

@@ -5,6 +5,7 @@ description="""\
     using dot product in SingleStoreDB. \
     """
 icon="chart-network"
+difficulty="beginner"
 tags=["starter", "vectordb", "huggingface"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/semantic-search-with-hugging-face/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Generate embeddings and run semantic search in your database in SQL. \
     """
 icon="chart-network"
+difficulty="beginner"
 tags=["starter", "openai", "vectordb", "genai"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/semantic-search-with-openai-embedding-creation/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Provide context to chatGPT using data stored in SingleStoreDB. \
     """
 icon="crystal-ball"
+difficulty="beginner"
 tags=["starter", "openai", "vectordb", "genai"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/semantic-search-with-openai-qa/meta.toml

@@ -4,6 +4,7 @@ description="""\
     SingleStoreDB leverages vector database processing to enable storage and search of vector data, allowing for semantic similarity-based searches to find content based on meaning rather than exact matches, such as locating related words like "happy" and "joyful." \
     """
 icon="chart-network"
-tags=["stater", "vectordb", "genai", "huggingface", "semanticsearch"]
+difficulty="beginner"
+tags=["starter", "vectordb", "genai", "huggingface", "semanticsearch"]
 destinations=["spaces"]
 minimum_tier="free-shared"

notebooks/semantic-visualization-and-vector-datatype/meta.toml

@@ -1,6 +1,7 @@
 [meta]
 title="Similarity Search on Vector Data"
 description="Example of similarity searches over vector data."
+difficulty="beginner"
 tags=["starter", "openai", "genai", "vectordb"]
 destinations=["spaces"]
 icon="vector-circle"

notebooks/similarity-search-on-vector-data/meta.toml

@@ -4,6 +4,7 @@ description="""\
     SingleStore is hosting a challenge inviting participants to craft a unique Haiku or create captivating ASCII art using SingleStore Notebooks. The most creative masterpiece wins a set of Meta RayBan Smart sunglasses and a $500 AWS gift card!" \
     """
 icon="chart-network"
+difficulty="intermediate"
 tags=["challenge", "haiku", "ascii"]
 destinations=["spaces"]
 minimum_tier="standard"

notebooks/singlestore-april-challenge-haiku-ascii/meta.toml

@@ -4,6 +4,7 @@ description="""\
     Perform both SQL and NoSQL queries on multi-modal relational and JSON data \
     """
 icon="database"
+difficulty="intermediate"
 tags=["cdc", "mongo", "sql", "nosql", "kai"]
 destinations=["spaces"]
 minimum_tier="standard"