Merge branch 'main' of github.com:Dtenwolde/community-extensions

.github/workflows/build_all.yml

@@ -0,0 +1,42 @@
+name: Build all extensions
+on:
+  workflow_dispatch:
+    inputs:
+      duckdb_version:
+        type: string
+      duckdb_tag:
+        type: string
+      deploy:
+        type: string
+
+jobs:
+  collect_extensions:
+    outputs:
+      COMMUNITY_EXTENSION_LIST: ${{ steps.generate_list.outputs.EXTENSION_LIST }}
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+
+    - name: Generate extension list
+      id: generate_list
+      run: |
+        ./scripts/get_extension_list.sh
+        cat extension_list
+        cat extension_list >> $GITHUB_OUTPUT
+      
+  build_all:
+    needs:
+      - collect_extensions
+    strategy:
+      fail-fast: false
+      matrix:
+        extension_name: ${{ fromJson(needs.collect_extensions.outputs.COMMUNITY_EXTENSION_LIST) }}
+    uses: ./.github/workflows/build.yml 
+    secrets: inherit
+    with:
+      extension_name: ${{ matrix.extension_name }}
+      duckdb_version: ${{ inputs.duckdb_version }}
+      duckdb_tag: ${{ inputs.duckdb_tag }}
+      deploy: ${{ inputs.deploy }}

.gitignore

@@ -0,0 +1,2 @@
+build/
+downloads-last-week.json

README.md

@@ -2,6 +2,8 @@
 
 This repository collects third-party extensions created for [DuckDB](https://www.duckdb.org).
 
-Visit the [DuckDB community extensions website](https://community-extensions.duckdb.org) to learn more about the available extensions.
+View the [list of Community Extensions](https://duckdb.org/community_extensions/list_of_extensions).
+
+Visit the [DuckDB Community Extensions website](https://duckdb.org/community_extensions) to learn more about the available extensions.
 
 [Learn about the official extensions and community extensions.](https://duckdb.org/2024/07/05/community-extensions)

extensions/bigquery/description.yml

@@ -1,7 +1,7 @@
 extension:
   name: bigquery
   description: Integrates DuckDB with Google BigQuery, allowing direct querying and management of BigQuery datasets
-  version: 1.0.0
+  version: 0.1.0
   language: C++
   build: cmake
   license: MIT
@@ -13,12 +13,12 @@ extension:
 
 repo:
   github: hafenkran/duckdb-bigquery
-  ref: 656055570493d26de86c4ab3a81f0c1b718835d2
+  ref: e5cd4a9ac32ce3380559bc63869c442c14e1fb75
 
 docs:
   hello_world: |
     -- Attach to your BigQuery Project
-    D ATTACH 'project=my_gcp_project' as bq (TYPE bigquery, READ_ONLY);
+    D ATTACH 'project=my_gcp_project' AS bq (TYPE bigquery, READ_ONLY);
 
     -- Show all tables in all datasets in the attached BigQuery project
     D SHOW ALL TABLES;

extensions/bigquery/docs/function_descriptions.csv

@@ -0,0 +1,7 @@
+function,description,comment,example
+bigquery_attach,"Attach to a BigQuery project.","","ATTACH 'project=my_gcp_project' as bq (TYPE bigquery);"
+bigquery_scan,"Scan a single table directly from BigQuery.",,"SELECT * FROM bigquery_scan('my_gcp_project.quacking_dataset.duck_tbl');"
+bigquery_query,"Run a custom GoogleSQL query in BigQuery and read the results.",,"SELECT * FROM bigquery_query('bq', 'SELECT * FROM quacking_dataset.duck_tbl WHERE duck_id = 123');"
+bigquery_execute,"Execute an arbitrary GoogleSQL query in BigQuery.",,"CALL bigquery_execute('bq', 'CREATE SCHEMA deluxe_dataset OPTIONS(location=""us"", default_table_expiration_days=3.75);')"
+bigquery_jobs,"List jobs in a BigQuery project.","","SELECT * FROM bigquery_jobs('bq');"
+bigquery_clear_cache,"Clear the internal caches to refetch the most current project information from BigQuery.","","CALL bigquery_clear_cache();"

extensions/chsql/description.yml

@@ -9,13 +9,13 @@ extension:
     - lmangani
 
 repo:
-  github: lmangani/duckdb-extension-clickhouse-sql
-  ref: 89e1c2fd68c18e018f5afb7ef81b3454abb46dfc
+  github: quackscience/duckdb-extension-clickhouse-sql
+  ref: a000d4f2a5f9e1c13cddcd75ea2d3351466f1706
 
 docs:
   hello_world: |
     -- Use ClickHouse SQL function macros in DuckDB SQL queries
-    SELECT toString('world') as hello, toInt8OrZero('world') as zero;
+    SELECT toString('world') AS hello, toInt8OrZero('world') AS zero;
 
     ┌─────────┬───────┐
     │  hello  │ zero  │
@@ -45,4 +45,4 @@ docs:
 
     
   extended_description: |
-    This extension implements a growing number of [ClickHouse SQL Macros](https://community-extensions.duckdb.org/extensions/chsql.html#added-functions) and functions for DuckDB. 
+    This extension implements a growing number of [ClickHouse SQL Macros](https://duckdb.org/community_extensions/extensions/chsql#added-functions) and functions for DuckDB.

extensions/duckpgq/description.yml

@@ -14,8 +14,8 @@ repo:
 
 docs:
   hello_world: |
-    CREATE TABLE Person as select * from 'https://gist.githubusercontent.com/Dtenwolde/2b02aebbed3c9638a06fda8ee0088a36/raw/8c4dc551f7344b12eaff2d1438c9da08649d00ec/person-sf0.003.csv';
-    CREATE TABLE Person_knows_person as select * from 'https://gist.githubusercontent.com/Dtenwolde/81c32c9002d4059c2c3073dbca155275/raw/8b440e810a48dcaa08c07086e493ec0e2ec6b3cb/person_knows_person-sf0.003.csv';
+    CREATE TABLE Person AS SELECT * FROM 'https://gist.githubusercontent.com/Dtenwolde/2b02aebbed3c9638a06fda8ee0088a36/raw/8c4dc551f7344b12eaff2d1438c9da08649d00ec/person-sf0.003.csv';
+    CREATE TABLE Person_knows_person AS SELECT * FROM 'https://gist.githubusercontent.com/Dtenwolde/81c32c9002d4059c2c3073dbca155275/raw/8b440e810a48dcaa08c07086e493ec0e2ec6b3cb/person_knows_person-sf0.003.csv';
 
     CREATE PROPERTY GRAPH snb
       VERTEX TABLES (
@@ -24,7 +24,7 @@ docs:
     EDGE TABLES (
       Person_knows_person 	SOURCE KEY (Person1Id) REFERENCES Person (id)
                             DESTINATION KEY (Person2Id) REFERENCES Person (id)
-      LABEL Knows
+      LABEL knows
     );
 
     FROM GRAPH_TABLE (snb
@@ -52,4 +52,3 @@ docs:
     
 
     *Disclaimer*: As this extension is part of an ongoing research project by the Database Architectures group at CWI, some features may still be under development. We appreciate your understanding and patience as we continue to improve it.
-

extensions/evalexpr_rhai/description.yml

@@ -51,19 +51,19 @@ docs:
     \ employees (name text, state text, zip integer);\nINSERT INTO employees values\n\
     \  ('Jane', 'FL', 33139),\n  ('John', 'NJ', 08520);\n\n-- Pass the row from the\
     \ employees table in as \"context.row\"\nSELECT evalexpr_rhai(\n  '\n  context.row.name\
-    \ + \" is in \" + context.row.state\n  ',\n  {\n    row: employees\n  }) as result\
+    \ + \" is in \" + context.row.state\n  ',\n  {\n    row: employees\n  }) AS result\
     \ from employees;\n\n┌───────────────────────────────┐\n│            result  \
     \           │\n│ union(ok json, error varchar) │\n├───────────────────────────────┤\n\
     │ \"Jane is in FL\"               │\n│ \"John is in NJ\"               │\n└───────────────────────────────┘\n\
     \n-- To demonstrate how Rhai can be used to implement\n-- a function in DuckDB,\
     \ the next example creates\n-- a macro function that calls a Rhai function\n--\
     \ to calculate the Collatz sequence length.\n\nCREATE MACRO collatz_series_length(n)\
-    \ as\n  evalexpr_rhai('\n    fn collatz_series(n) {\n        let count = 0;\n\
+    \ AS\n  evalexpr_rhai('\n    fn collatz_series(n) {\n        let count = 0;\n\
     \        while n > 1 {\n          count += 1;\n          if n % 2 == 0 {\n   \
     \           n /= 2;\n          } else {\n              n = n * 3 + 1;\n      \
     \    }\n        }\n        return count\n    }\n    collatz_series(context.n)\n\
     \  ', {'n': n});\n\n-- Use the previously defined macro.\nSELECT\n  collatz_series_length(range).ok::bigint\
-    \ as sequence_length,\n  range as starting_value\nFROM\n  range(10000, 20000)\n\
+    \ AS sequence_length,\n  range AS starting_value\nFROM\n  range(10000, 20000)\n\
     ORDER BY 1 DESC limit 10;\n\n┌─────────────────┬────────────────┐\n│ sequence_length\
     \ │ starting_value │\n│      int64      │     int64      │\n├─────────────────┼────────────────┤\n\
     │             278 │          17647 │\n│             278 │          17673 │\n│\

extensions/faiss/description.yml

@@ -1,6 +1,6 @@
 extension:
   name: faiss
-  description: Provides a subset of the faiss API to duckdb
+  description: Provides a subset of the faiss API to DuckDB
   version: 0.9.0
   language: C++
   build: cmake
@@ -21,16 +21,16 @@ docs:
   hello_world: |
     -- Generate semi-random input data and queries
     -- Note that the dimensionality of our data will be 5
-    CREATE TABLE input AS SELECT i as id, apply(generate_series(1, 5), j-> CAST(hash(i*1000+j) AS FLOAT)/18446744073709551615) as data FROM generate_series(1, 1000) s(i);
-    CREATE TABLE queries AS SELECT i as id, apply(generate_series(1, 5), j-> CAST(hash(i*1000+j+8047329823) AS FLOAT)/18446744073709551615) as data FROM generate_series(1, 10) s(i);
+    CREATE TABLE input AS SELECT i AS id, apply(generate_series(1, 5), j-> CAST(hash(i*1000+j) AS FLOAT)/18446744073709551615) AS data FROM generate_series(1, 1000) s(i);
+    CREATE TABLE queries AS SELECT i AS id, apply(generate_series(1, 5), j-> CAST(hash(i*1000+j+8047329823) AS FLOAT)/18446744073709551615) AS data FROM generate_series(1, 10) s(i);
     -- Create the index and insert data into it
     CALL FAISS_CREATE('name', 5, 'IDMap,HNSW32');
     CALL FAISS_ADD((SELECT id, data FROM input), 'name');
     -- Get 10 results with uneven id
-    SELECT id, UNNEST(FAISS_SEARCH_FILTER('name', 10, data, 'id%2==0', 'rowid', 'input')) FROM queries;
+    SELECT id, UNNEST(FAISS_SEARCH_FILTER('name', 10, data, 'id%2==1', 'rowid', 'input')) FROM queries;
     -- Get 10 results with even id
     SELECT id, UNNEST(FAISS_SEARCH_FILTER('name', 10, data, 'id%2==0', 'rowid', 'input')) FROM queries;
     -- Get 10 results
     SELECT id, UNNEST(FAISS_SEARCH('name', 10, data)) FROM queries;
   extended_description: |
-    The FAISS extension allows duckdb users to store vector data in faiss, and query this data, making reliable vector search more accessible.
+    The FAISS extension allows DuckDB users to store vector data in faiss, and query this data, making reliable vector search more accessible.

extensions/flockmtl/description.yml

@@ -0,0 +1,44 @@
+extension:
+  name: flockmtl
+  description: DuckDB LLM Extension
+  version: 0.1.0
+  language: SQL & C++
+  build: cmake
+  license: MIT
+  maintainers:
+    - dorbanianas
+    - SunnyYasser
+    - queryproc
+
+repo:
+  github: dsg-polymtl/duckdb-flockmtl
+  ref: 1bd8ac0f54f8bf4c7da1c3793b88e73daa127653
+
+docs:
+  hello_world: |
+    -- After loading, any function call will throw an error if an OPENAI_API_KEY environment variable is not set
+
+    -- Call an OpenAI model with a predefined prompt ('Tell me hello world') and default model ('gpt-4o-mini')
+    D SELECT llm_complete('hello-world', 'default');
+    ┌──────────────────────────────────────────┐
+    │ llm_complete(hello_world, default_model) │
+    │                 varchar                  │
+    ├──────────────────────────────────────────┤
+    │                Hello world               │
+    └──────────────────────────────────────────┘
+
+    -- Check the prompts and supported models
+    D GET PROMPTS;
+    D GET MODELS;
+
+    -- Create a new prompt for summarizing text
+    D CREATE PROMPT('summarize', 'summarize the text into 1 word: {{text}}');
+
+    -- Create a variable name for the model to do the summarizing
+    D CREATE MODEL('summarizer-model', 'gpt-4o', 128000);
+
+    -- Summarize text and pass it as parameter 
+    D SELECT llm_complete('summarize', 'summarizer-model', {'text': 'We support more functions and approaches to combine relational analytics and semantic analysis. Check our repo for documentation and examples.'});
+
+  extended_description: |
+    This extension is experimental and potentially unstable. Do not use it in production.

extensions/fuzzycomplete/description.yml

@@ -49,7 +49,7 @@ docs:
     CREATE TABLE automobile_vehicles(serial_number text);
 
 
-    SELECT suggestion from sql_auto_complete(''SELECT * from veh'');
+    SELECT suggestion FROM sql_auto_complete(''SELECT * FROM veh'');
 
     ┌─────────────────────┐
 
@@ -64,7 +64,7 @@ docs:
     └─────────────────────┘
 
 
-    select suggestion from sql_auto_complete(''SELECT * from auto'');
+    SELECT suggestion FROM sql_auto_complete(''SELECT * FROM auto'');
 
     ┌──────────────────────────────────────┐
 
@@ -89,7 +89,7 @@ docs:
     └──────────────────────────────────────┘
 
 
-    SELECT suggestion from sql_auto_complete(''SELECT * from bar'');
+    SELECT suggestion FROM sql_auto_complete(''SELECT * FROM bar'');
 
     ┌──────────────────────────────────────┐
 
@@ -108,7 +108,7 @@ docs:
 
     -- Demonstrate completion across databases/catalogs and schemas.
 
-    SELECT suggestion from sql_auto_complete(''SELECT * from table'');
+    SELECT suggestion FROM sql_auto_complete(''SELECT * FROM table'');
 
     ┌───────────────────────────────────────────────┐
 

extensions/gsheets/description.yml

@@ -0,0 +1,57 @@
+extension:
+  name: gsheets
+  description: Read and write Google Sheets using SQL
+  version: 0.0.2
+  language: C++
+  build: cmake
+  license: MIT
+  excluded_platforms: "windows_amd64_rtools;wasm_mvp;wasm_eh;wasm_threads"
+  maintainers:
+    - archiewood
+
+repo:
+  github: evidence-dev/duckdb_gsheets
+  ref: 01bdf2872b78af1b9234792766392840fc4a91b7
+
+docs:
+  hello_world: |
+    -- Authenticate with Google Account in the browser (easiest)
+    CREATE SECRET (TYPE gsheet);
+    
+    -- OR create a secret with your Google API access token (boring, see extension docs)
+    CREATE SECRET (
+      TYPE gsheet, 
+      PROVIDER access_token, 
+      TOKEN '<your_token>'
+    );
+    
+    -- Read a spreadsheet by full URL
+    FROM read_gsheet('https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit');
+    
+    -- Read a spreadsheet by full URL, implicitly
+    FROM 'https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit';
+    
+    -- Read a spreadsheet by spreadsheet id
+    FROM read_gsheet('11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8');
+    
+    -- Read a spreadsheet with no header row
+    SELECT * FROM read_gsheet('11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8', headers=false);
+    
+    -- Read a sheet other than the first sheet using the sheet name
+    SELECT * FROM read_gsheet('11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8', sheet='Sheet2');
+    
+    -- Read a sheet other than the first sheet using the sheet id in the URL
+    SELECT * FROM read_gsheet('https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit?gid=644613997#gid=644613997');
+    
+    -- Write a spreadsheet from a table by spreadsheet id
+    COPY <table_name> TO '11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8' (FORMAT gsheet);
+    
+    -- Write a spreadsheet from a table by full URL
+    COPY <table_name> TO 'https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit?usp=sharing' (FORMAT gsheet);
+    
+    -- Write a spreadsheet to a specific sheet using the sheet id in the URL
+    COPY <table_name> TO 'https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit?gid=1295634987#gid=1295634987' (FORMAT gsheet);
+  
+  extended_description: |
+    The DuckDB GSheets Extension allows reading and writing of data in Google Sheets from DuckDB.
+    For detailed setup and usage instructions, visit the docs at [duckdb-gsheets.com](https://duckdb-gsheets.com).

extensions/gsheets/docs/function_description.csv

@@ -0,0 +1,3 @@
+function,description,comment,example
+read_gsheet,"Read a single sheet directly from a Google Sheet via the sheet URL, or spreadsheet ID.",,"SELECT * FROM read_gsheet('https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit?gid=644613997#gid=644613997');"
+"COPY TO","Write data from a table to a Google Sheet via the sheet URL, or spreadsheet ID.",,"COPY <table_name> TO 'https://docs.google.com/spreadsheets/d/11QdEasMWbETbFVxry-SsD8jVcdYIT1zBQszcF84MdE8/edit?gid=1295634987#gid=1295634987' (FORMAT gsheet);"