Logo
  • Documentation
  • Blogs
  • Processors
Sparkflows Logo
  • 01-Data-Connectors
    • 01-Input
      • 01-Database
        • Execute BigQuery
        • Execute CRUD Stmt In Snowflake
        • Execute Query In Snowflake
        • Execute Stored Procedure In Snowflake
        • Hive Incremental
        • Read JDBC
        • JDBC Incremental Load
        • Netsuite AutoIncrement
        • Read Netsuite
        • AutoIncrement
        • DB Incremental Ingestion
        • Read JDBC
        • Query JDBC
        • Read Incorta
        • Read BigQuery
        • Read Cassandra
        • Read Databricks Table
        • Read DynamoDB
        • Read Elastic Search
        • Read From Snowflake
        • Read HIVE Table
        • Read Iceberg
        • Read MongoDB
      • 02-Structured-Files
        • Read Avro
        • Create Dataset
        • Read CSV
        • Read Delta
        • Empty Dataset
        • Read Excel
        • Read Excel Advanced
        • ReadFlatFile
        • Read HANA CSV
        • InMemoryDataset
        • Read JSON
        • Read LIBSVM
        • Read Parquet
        • Read Shape File
        • Dataset Structured
        • URL Text File Reader
        • URL Single Record JSON Reader
        • Read XML
      • 03-Unstructured-Files
        • Binary Files
        • PDF
        • PDF Image OCR
        • Text Files
        • Tika
        • Whole Text Files
      • 05-SFTP
        • SFTP Read
        • SFTP
      • 06-Enterprise-Applications
        • Read Marketo
        • Read Salesforce
    • 02-Output
      • 01-Database
        • Insert Into HIVE Table
        • Save JDBC
        • Write To BigQuery
        • Save Incorta
        • Save As HIVE Table
        • Save Cassandra
        • Save Databricks Table
        • Save DynamoDB
        • Save ElasticSearch
        • Save Iceberg
        • Save MongoDB
        • Update JDBC
        • Upsert JDBC
        • Write To Snowflake
      • 02-Structured-Files
        • Save DOCX
        • Save Excel
        • Save Excel Advanced
        • Save HTML
        • Save PDF
        • Save Text
        • Save Avro
        • Save CSV
        • Save Delta
        • Save JDBC
        • Save JSON
        • Save ORC
        • Save Parquet
      • 04-Streaming
        • Kafka Producer
      • 05-SFTP
        • SFTP Write
    • 03-Streaming
      • 01-Real-Time-Streaming
        • Streaming Kafka
        • Streaming Socket Text Stream
        • Streaming Text File Stream
      • 02-Structured-Streaming
        • Structured Streaming Console Sink
        • Structured Streaming CSV
        • Structured Streaming File Sink
        • Structured Streaming JSON
        • Structured Streaming Kafka Read
        • Structured Streaming Kafka Save
        • Structured Streaming Kinesis
        • Structured Streaming Socket
        • Structured Streaming Hive Sink
        • Structured Streaming Hive Sink2
  • 02-Data-Profiling
    • Columns Cardinality
    • Correlation
    • Correlation
    • Cross Tab
    • Distinct Values In Column
    • Flag Outlier
    • Graph Week Day Distribution
    • Graph Year Distribution
    • Histogram
    • Graph Month Distribution
    • MultiFlagOutliers
    • MultiFlagOutliers
    • Null Values In Column
    • Skewness And Kurtosis
    • Summary Statistics
    • WhatIf Summary Statistics
  • 03-Data-Preparation
    • 01-DateTime
      • Date Time Field Extract
      • Date To Age
      • Date Difference
      • Date To String
      • String To Date
      • String To Unix Time
      • Time Functions
      • Unix Time To String
    • 02-Math
      • Math Expression
      • Math Functions
    • 03-String
      • String Functions
      • Text Case Transformer
    • 04-Parsing
      • Apache Logs
      • Field Splitter
      • Fixed Length Fields
      • Multi Regex Extractor
      • OCR
      • Paragraph Splitter
      • Parse JSON Col
      • Parse XML Col
      • Regex Tokenizer
    • 05-Cleaning
      • Count rows columns
      • Data Cleansing
      • Data Cleansing Advanced
      • Data Wrangling
      • Dedup
      • Drop Duplicate Rows
      • Drop Rows With Null
      • Drop Null Rows for Selected Columns
      • Find And Replace Using Regex
      • Find And Replace Using Regex Advanced
      • Impute Advanced
      • Imputing With Constant
      • Imputing With Mean Value
      • Imputing With Median
      • Imputing With Mode Value
      • Lookup
      • Count Null Values
      • Remove Duplicate Rows
      • Remove Unwanted Characters
      • Remove Unwanted Characters Advanced
      • Standard Deviation
      • Value count
    • 06-Add-Column
      • Add Columns
      • Add Column Advanced
      • Case When
      • Case When Advanced
      • Concat Columns
      • Expressions
      • Record ID
      • Generate UID
      • Generate UUID
      • Data Masking
      • Row Numbering
      • Zip With Index
    • 06-Control-Structures
      • Execute In Loop
      • Execute Workflow
      • Read Parameters
      • Specify Parameters
    • 07-Split
      • Compare All Columns
      • Compare All Columns Single Output
      • Compare Specific Columns
      • Compare Specific Columns Single Output
      • Split By Expression
      • Split By Multiple Expressions
    • 08-Condition
      • Assert
      • Decision
    • 09-Cast-DataType
      • Cast To Single Type
      • Cast To Different Types-1
      • Cast To Different Types-2
    • 10-Filter
      • Select Columns
      • Drop Columns
      • Filter Advanced
      • Filter By Date Range
      • Filter By String Length
      • Limit
      • Filter By Number Range
      • Regex Advanced
      • Row Filter
      • Node Row Filter By Index
      • Select
      • FindDuplicate
    • 11-Join-Union
      • Append Fields
      • Join On Columns
      • Join On Common Column
      • Join On Common Columns
      • Join Using SQL
      • Join Advanced
      • Union Advanced
      • Union All
      • Union Distinct
    • 12-Group
      • Aggregate
      • Cube
      • Group By
      • Melt
      • Pivot By
      • Pivot By Advanced
      • Pivot By
      • Rollup
    • 13-Code
      • Scala
      • Jython
      • MultiInputPySpark
      • Multi Input To Multi Output PySpark
      • Pipe Python
      • Pipe Python2
      • PySpark
      • Run Python Code
      • Run Python File
      • Run HIVEQL
      • Spark
      • Scala UDF
      • SQL
      • SQL Executer
      • Unix Shell Commands
    • 16-Others
      • CDC Using Full Table Merge
      • Columns Rename
      • Count
      • Dynamic Rename
      • Explode
      • Flatten
      • Formula
      • JsonToEDI
      • Linear Programming Optimisation
      • Multi Window Analytics
      • Multi Window Ranking
      • DeltaMerge
      • Recover Hive Partitions
      • Register TempTable
      • Round Value
      • Sample
      • SaveWaterMark
      • SCDType2DeltaMerge
      • Scheduling Optimization
      • Sort By
      • Sort Columns
      • Supplier Optimization
      • Transpose
      • Transpose Advanced
      • Window Aggregation
      • Window Analytics
      • Window Function
      • Window Ranking
      • Word Count
  • 04-Data-Validation
    • Validate Address
    • Compare Datasets
    • Node Schema Validation
    • Validate Fields Simple
    • Validate Fields Advanced
  • 06-Data-Quality
    • 01-Great-Expectations
      • Create CSV from GE Results
      • ExpectColumnToExist
      • ExpectColumnValueLengthToBeInBetween
      • ExpectColumnValueLengthsToEqual
      • ExpectColumnValueToMatchStrftimeFormat
      • ExpectColumnValuesToBeInBetween
      • ExpectColumnValuesToBeInSet
      • ExpectColumnValuesToBeNull
      • ExpectColumnValuesToBeUnique
      • ExpectColumnValuesToMatchRegex
      • ExpectColumnValuesToNotBeNull
      • ExpectTableRowCountToBeBetween
      • GE Decision
      • Split Into Good And Bad Records
    • HasDataSize
    • HasMax
    • HasMin
    • PatternMatch
    • IsNonNegative
    • Is Not Null
    • IsPositive
    • Is Primary Key
    • Is Value In
    • NodeDataQualityCheckAndAlert
    • CheckOutliers
    • ColumnValuesToBeBetween
  • 07-Data-Visualization
    • 01-SPC
      • C Chart
      • EWMA Chart
      • I-MR Chart
      • IMR-R Chart
      • IMR-S Chart
      • NP Chart
      • P Chart
      • Process Capability Index
      • Run Chart
      • U Chart
      • Xbar-R Chart
      • Xbar-S Chart
    • Box Plot
    • Bubble Chart
    • Gauge Chart
    • Graph Group By Column
    • Geo Chart
    • Graph Values
    • Hierarchy Chart
    • Bar Chart
    • Bar Group Chart
    • Print Rich Text
    • Print N Rows
    • Scatter Chart
    • Scatter Cluster Chart
    • Graph Subplots
    • Word Cloud Chart
  • 08-Machine-Learning
    • 01-ML-Feature-Selection
      • Data Drift
      • Feature Selection
      • Feature Selection With Importance
      • Feature Selection With Correlation
      • Group By RFM Features
      • Moving Average Features
      • Time Series Features
    • 02-ML-SparkML
      • 02-FeatureScaler
        • Min Max Scaler
        • Min Max Scaler
        • Min Max Scaler Transform
        • Min Max Scaler Transform
        • Standard Scaler
        • Standard Scaler Transform
      • 03-FeatureExtraction
        • Count Vectorizer
        • Hashing TF
        • Markov Chain
        • R Formula
        • Word2 Vec
      • 04-FeatureTransformers
        • Binarizer
        • Bucketizer
        • Bucketizer Transform
        • IDF
        • Imputer
        • Imputer
        • Imputer Transform
        • Imputer Transform
        • Index To String
        • Index To String Transform
        • Index String
        • Interaction
        • Interaction Transform
        • MaxAbs Scaler
        • MaxAbs Scaler
        • MaxAbs Scaler Transform
        • MaxAbs Scaler Transform
        • N Gram Transformer
        • Normalizer
        • Normalizer
        • Normalizer Transform
        • One Hot Encoder
        • One Hot Encoder Advanced
        • One Hot Encoder Advanced Transform
        • One Hot Encoder
        • One Hot Encoder Transform
        • Polynominal Expansion
        • Quantile Discretizer
        • Quantile Discretizer Transform
        • Robust Scaler
        • Robust Scaler
        • Robust Scaler Transform
        • Robust Scaler Transform
        • Signal Processing
        • SMOTE
        • SQL Transformer
        • Stop Words Remover
        • String Indexer
        • String Indexer Advanced
        • String Indexer
        • String Indexer Transform
        • String Indexer Advanced Transform
        • Tokenizer
        • Vector Assembler
        • Vector Functions
        • Vector Indexer
        • Vector Indexer
        • Vector Indexer Transform
        • Vector Indexer Transform
        • Word To Score Mapping
      • 05-DimensionalityReduction
        • PCA
        • SVD
      • 06-FeatureSelection
        • ChiSq Selector
        • Vector Slicer
      • 07-SplitDataset
        • Split
        • Split Probability Column
        • Split With Stratified Sampling
      • 08-Clustering
        • Gaussian Mixture
        • K-Means
        • LDA
      • 09-Regression
        • AFT Survival Regression
        • Decision Tree Regression
        • GBT Regression
        • Linear Regression
        • Random Forest Regression
        • XGBoost Regressor
      • 10-Classification
        • Decision Tree Classifier
        • Decision Tree Classifier
        • GBT Classifier
        • GBT Classifier
        • Logistic Regression
        • Logistic Regression
        • MultiLayer Perceptron
        • Naive Bayes
        • Random Forest Classifier
        • Random Forest Classifier
        • XGBoost Classifier
      • 11-CollaborativeFiltering
        • ALS
      • 12-FreqPatternMining
        • FP Growth
      • 13-Modeling
        • Binary Classification Evaluator
        • Binary Classification Evaluator
        • Clustering Evaluator
        • Cross Validator
        • Load MLeap
        • Spark ML Model Load
        • Spark ML Model Load
        • Spark ML Model Save
        • Multiclass Classification Evaluator
        • Multiclass Classification Evaluator
        • Spark Pipeline
        • Spark Predict
        • Regression Evaluator
        • Spark ML ROC
        • Save MLeap
        • Train Validation Split
    • 03-ML-H2O
      • Extract Probabilities
      • H2O Auto ML
      • H2O Auto ML
      • H2O Clustering Evaluator
      • H2O Clustering Evaluator
      • H2O Distributed Random Forest
      • H2O Distributed Random Forest
      • H2O Gradient Boosting Machine
      • H2O Gradient Boosting Machine
      • H2O Generalized Linear Models
      • H2O Generalized Linear Models
      • H2O Generalized Low Rank Models
      • H2O Generalized Low Rank Models
      • H2O Isolation Forest
      • H2O Isolation Forest
      • H2O K-Means
      • H2O K-Means
      • H2O ML Model Load
      • H2O ML Model Load
      • H2O ML Model Save
      • H2O ML Model Save
      • H2O Neural Network
      • H2O PCA
      • H2O PCA
      • H2O Score
      • H2O Score
      • H2O Word to Vec
      • H2O Word to Vec
      • H2O XGBoost
      • H2O XGBoost
    • 05-ML-DeepLearning
      • Dense Layer
      • Keras Preprocessor
      • Keras Model Compile
      • Keras Model Fit
      • Keras Model Sequential
      • Keras Predict
      • ImageSegmentation
    • 06-ML-Sklearn
      • Classification
        • Sklearn Gradient Boosting Classifier
        • Sklearn Logistic Regression
        • Sklearn Random Forest Classifier
        • Sklearn XGBoost Classifier
      • Clustering
        • Sklearn K-Means
      • Data
        • Sklearn Polynomial
      • Modeling
        • Custom Metrics
        • Sklearn Classification Evaluator
        • Sklearn Model Load From S3
        • Sklearn Model Load
        • Sklearn Predict
        • Sklearn Regression Evaluator
        • Sklearn Model Save To S3
        • Sklearn Model Save
      • Optimization
        • Optimization
        • Optimization Model Load And Score
      • PreProcessing
        • Sklearn Binarizer
        • Sklearn Binarizer Transform
        • Sklearn Label Encoder
        • Sklearn MinMaxScaler
        • Sklearn MinMax Scaler Transform
        • MinMax Scaler Inverse Transform
        • Sklearn Normalizer
        • Sklearn Normalizer Transform
        • Sklearn OneHotEncoder
        • Sklearn Quantile Fit Transform
        • Sklearn Quantile Transform
        • Sklearn StandardScalar
        • Sklearn StandardScalar Transform
        • Standard Scaler Inverse Transform
        • Sklearn TF-IDF Vectorizer
      • Regression
        • Sklearn Bayesian Ridge Regression
        • Sklearn Gradient Boosting Regression
        • SkLearn Lasso Regression
        • Sklearn Random Forest Regression
        • Sklearn Ridge Regression
        • Sklearn XGBoost Regressor
    • 07-ML-Pycaret
      • PyCaret AutoML Classification
      • PyCaret AutoML Regression
    • 08-ML-TimeSeries
      • Arima
      • Arima Forecast
      • Arima Model Load
      • Arima Model Save
      • LSTM
      • Prophet
      • Prophet Cross Validator
      • Prophet Model Load
      • Prophet Make Future Dataframe
      • Prophet Predict
      • Prophet Model Save
      • Sarimax
      • Sarimax Forecast
      • Sarimax Model Load
      • Sarimax Model Save
      • TS Decompose
      • VAR
      • VarForecast
      • VAR Model Load
      • VAR Model Save
    • 10-OpenNLP
      • Open NLP Document Categorizer
      • Open NLP Name Finder
      • Open NLP Sentence Detector
  • 09-Utilities
    • 01-Spark-Performance
      • Cache Data Frame
      • Print Spark Configuration
      • Unpersist DataFrame
    • 02-Data-Partition
      • Coalesce
      • Number Of Partitions
      • Repartition
    • CodeLibrary
    • Pdf Attachments from Emails
    • EmailNotification
    • InlineDQ_Validation
    • ML Data Metrics
    • Generate Dynamic Parameters
    • Rest API Client
    • PGPDecrypt
    • ExecuteRedshiftStatement
  • 10-Documentation
    • Notes
    • Sticky Note
  • 11-Custom-Processors
    • pyspark
      • ScoreCard_Binning
  • 12-Deprecated
    • String To Date
  • 13-Generative-AI
    • 01-Hugging-Face
      • Hugging Face Custom Category Sentiment Analysis
      • Hugging Face Grammatical Correctness
      • Hugging Face Natural Language Inference
      • Hugging Face Question Natural Language Inference
      • Hugging Face Sentiment Analysis
      • Hugging Face Summarization
      • Hugging Face Tone Analysis
    • 02-Ingestion
      • Confluence Reader
      • Document To Text
      • Service Now Data Extraction
      • Sharepoint Data Extraction
      • Audio Diarization
      • Video Summarization
      • Web Scraper
    • 03-Vectorization
      • Save Chroma DB
      • Save Faiss DB
      • Save to Pinecone
      • Create Text Embedding
    • 04-Retrieval
      • Read Chroma DB
      • Read Faiss DB
      • Read Pinecone DB
    • 05-LLM-Inference
      • Interactive LLM Agent
      • Invoice Extraction
      • Multi LLM Query
      • Output Formatter
      • SerperAI Search
      • Text Analysis
Sparkflows
  • »
  • 13-Generative-AI »
  • 05-LLM-Inference »
  • SerperAI Search
  • View page source

SerperAI Search¶

The SerperAI Search node fetches real-time search results from Google services (Web, News, Images, Shopping, Places) using the SerperAI API. It processes user queries and returns results as a structured DataFrame or raw JSON, ideal for retrieval-augmented generation (RAG) workflows.

Input¶

No input DataFrame required

Output¶

Returns search results as a DataFrame

Type¶

pyspark

Class¶

fire.nodes.gai.NodeSerperAISearch

Fields¶

Name

Title

Description

serperConnection

Select Connection

The serper api connection to connect

query

Query

Search query to send to the SerperAI API (e.g., ‘latest AI tools’).

userQueryCol

User Query Column

Column name for user query, (if the query is in a column)

Advanced

Advanced

search_type

Search Type

Type of search to perform: web, news, images, shopping, places, youtube, scholar, patents, autocomplete, etc.

num_results

Number of Results

Number of search results to fetch (default: 10).

country

Country Code (gl)

Two-letter country code (e.g., ‘us’ for United States, ‘in’ for India). Used to localize results.

language

Language Code (hl)

Two-letter language code (e.g., ‘en’ for English, ‘fr’ for French). Used to return results in a specific language.

date_range

Date Range Filter

Restrict search results to a specific time range.

additional_params

Additional Parameters

Optional JSON object for advanced search parameters (e.g., {“gl”: “us”, “hl”: “en”}).

output_format

Output Format

Output format: Parsed DataFrame (structured columns) or Raw JSON (full response).

Details¶

SerperAI Search Node Details¶

The SerperAI Search node fetches real-time search results from Google services (Web, News, Images, Shopping, Places) using the SerperAI API. It processes user queries and returns results as a structured DataFrame or raw JSON, ideal for retrieval-augmented generation (RAG) workflows.

General:¶

API Key:¶

Specifies the SerperAI API key obtained from serper.ai. This field is required to authenticate requests to the SerperAI API.

Query:¶

Defines the search query to send to the SerperAI API (e.g., ‘latest AI tools’). This is required unless a User Query Column is specified.

User Query Column:¶

Specifies a DataFrame column containing search queries. This is optional and used when queries are stored in an input DataFrame column instead of the Query field.

Search Type:¶

Selects the type of search to perform. Options include:

  • search: Standard web search results.

  • news: News articles related to the query.

  • images: Image search results.

  • shopping: Product listings from shopping searches.

  • places: Local business or place information.

  • autocomplete: Search query suggestions.

  • webpage: Webpage-specific search results (treated as standard search).

If not specified, defaults to search.

Number of Results:¶

Sets the number of search results to fetch. Default is 10. Must be a positive integer.

Country Code (gl):¶

Specifies a two-letter country code (e.g., ‘us’ for United States, ‘in’ for India) to localize search results. Optional.

Language Code (hl):¶

Specifies a two-letter language code (e.g., ‘en’ for English, ‘fr’ for French) to return results in a specific language. Optional.

Date Range Filter:¶

Restricts search results to a specific time range. Options are:

  • Any Time: No time restriction (default).

  • Past Hour: Results from the last hour.

  • Past 24 Hours: Results from the last day.

  • Past Week: Results from the last week.

  • Past Month: Results from the last month.

  • Past Year: Results from the last year.

Additional Parameters:¶

Allows advanced search parameters as a JSON object (e.g., {“gl”: “us”, “hl”: “en”}). Optional and overrides Country Code and Language Code if provided.

Output Format:¶

Determines the output format of the search results. Options are:

  • Parsed DataFrame: Structured columns specific to the search type (e.g., title, link, snippet for web search).

  • Raw JSON: Full API response as a JSON string.

Defaults to Parsed DataFrame.

Input:¶

No input DataFrame is required unless User Query Column is used, in which case an input DataFrame with the specified query column is needed.

Output:¶

The node outputs a DataFrame with columns depending on the Search Type and Output Format:

  • For Parsed DataFrame:

  • Web search: title, link, snippet, query.

  • News: title, link, source, date, query.

  • Images: title, imageUrl, source, query.

  • Shopping: title, link, price, query.

  • Places: title, address, rating (float), query.

  • Autocomplete: suggestion, query.

  • For Raw JSON: search_results (JSON string), query.

Examples¶

Example: SerperAI Search Node¶

Input:¶

The SerperAI Search node is configured as follows:

  • API Key: abc123xyz (valid SerperAI API key).

  • Query: “latest AI tools 2025”.

  • User Query Column: Empty (uses Query field).

  • Search Type: search (web search).

  • Number of Results: 5.

  • Country Code (gl): us.

  • Language Code (hl): en.

  • Date Range Filter: Past Month.

  • Additional Parameters: {} (empty).

  • Output Format: Parsed DataFrame.

No input DataFrame is provided since User Query Column is empty.

Output:¶

The node processes the query and produces a DataFrame with the following structure:

title                          | link                                      | snippet                                   | query
-------------------------------|-------------------------------------------|-------------------------------------------|--------------------
Top AI Tools for 2025          | https://example.com/ai-tools-2025         | Best AI tools for productivity...         | latest AI tools 2025
AI Innovations in 2025         | https://techsite.com/ai-2025              | Discover the latest AI advancements...    | latest AI tools 2025
2025 AI Software Guide         | https://reviews.com/ai-guide              | Comprehensive guide to AI tools...       | latest AI tools 2025
New AI Tools Released          | https://news.com/ai-releases             | Latest AI tool announcements...          | latest AI tools 2025
AI Trends for 2025             | https://insights.com/ai-trends           | Emerging AI technologies for 2025...     | latest AI tools 2025

Explanation:¶

  • The node sends the query “latest AI tools 2025” to the SerperAI API with the search type, requesting 5 results.

  • The Country Code (gl) is set to ‘us’ and Language Code (hl) to ‘en’, localizing results to the United States in English.

  • The Date Range Filter is set to Past Month, restricting results to content from the last 30 days.

  • Since Output Format is Parsed DataFrame, the results are structured into columns: title, link, snippet, and query.

  • Each row corresponds to a search result, with the query column reflecting the input query.

  • If Output Format were Raw JSON, the output would include a search_results column with the full JSON response and a query column.

  • The API key authenticates the request, and no input DataFrame is needed since User Query Column is empty.

Next Previous

© 2026 Sparkflows, Inc. All rights reserved.

Privacy Policy | Terms and Conditions

Built with Sphinx using a theme provided by Read the Docs.