Name | llama-index-tools-waii JSON |
Version |
0.2.0
JSON |
| download |
home_page | None |
Summary | llama-index tools waii integration |
upload_time | 2024-08-22 07:42:57 |
maintainer | wangdatan |
docs_url | None |
author | Your Name |
requires_python | <4.0,>=3.8.1 |
license | MIT |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# Waii Tool
This tool connects to database connections managed by Waii, which allows generic SQL queries, do performance analyze, describe a SQL query, and more.
## Usage
First you need to create a waii.ai account, you request an account from [here](https://waii.ai/).
Initialize the tool with your account credentials:
```python
from llama_index.tools.waii import WaiiToolSpec
waii_tool = WaiiToolSpec(
url="https://tweakit.waii.ai/api/",
# API Key of Waii (not OpenAI API key)
api_key="...",
# Connection key of WAII connected database, see https://github.com/waii-ai/waii-sdk-py#get-connections
database_key="...",
)
```
## Tools
The tools available are:
- `get_answer`: Get answer to natural language question (which generate a SQL query, run it, explain the result)
- `describe_query`: Describe a SQL query
- `performance_analyze`: Analyze performance of a SQL query (by query_id)
- `diff_query`: Compare two SQL queries
- `describe_dataset`: Describe dataset, such as table, schema, etc.
- `transcode`: Transcode SQL query to another SQL dialect
- `get_semantic_contexts`: Get semantic contexts of a SQL query
- `generate_query_only`: Generate SQL query only (not run it)
- `run_query`: Run a SQL query
You can also load the data directly call `load_data`
## Examples
### Load data
```python
documents = waii_tool.load_data("Get all tables with their number of columns")
index = VectorStoreIndex.from_documents(documents).as_query_engine()
print(index.query("Which table contains most columns?"))
```
### Use as a Tool
#### Initialize the agent:
```python
from llama_index.agent.openai import OpenAIAgent
from llama_index.llms.openai import OpenAI
agent = OpenAIAgent.from_tools(
waii_tool.to_tool_list(), llm=OpenAI(model="gpt-4-1106-preview")
)
```
#### Ask simple question
```python
agent.chat("Give me top 3 countries with the most number of car factory")
agent.chat("What are the car factories of these countries")
```
#### Do performance analyze
```python
agent.chat("Give me top 3 longest running queries, and their duration.")
agent.chat("analyze the 2nd-longest running query")
```
#### Diff two queries
```python
previous_query = """
SELECT
employee_id,
department,
salary,
AVG(salary) OVER (PARTITION BY department) AS department_avg_salary,
salary - AVG(salary) OVER (PARTITION BY department) AS diff_from_avg
FROM
employees;
"""
current_query = """
SELECT
employee_id,
department,
salary,
MAX(salary) OVER (PARTITION BY department) AS department_max_salary,
salary - AVG(salary) OVER (PARTITION BY department) AS diff_from_avg
FROM
employees;
LIMIT 100;
"""
agent.chat(f"tell me difference between {previous_query} and {current_query}")
```
#### Describe dataset
```python
agent.chat("Summarize the dataset")
agent.chat("Give me questions which I can ask about this dataset")
```
#### Describe a query
```python
q = """
SELECT
employee_id,
department,
salary,
AVG(salary) OVER (PARTITION BY department) AS department_avg_salary,
salary - AVG(salary) OVER (PARTITION BY department) AS diff_from_avg
FROM
employees;
"""
agent.chat(f"what this query can do? {q}")
```
#### Migrate query to another dialect
```python
q = """
from pyspark.sql import SparkSession
from pyspark.sql.functions import avg, col
from pyspark.sql.window import Window
# Initialize Spark session
spark = SparkSession.builder.appName("example").getOrCreate()
# Assuming you have a DataFrame called 'employees'
# If not, you need to read your data into a DataFrame first
# Define window specification
windowSpec = Window.partitionBy("department")
# Perform the query
result = (employees
.select(
col("employee_id"),
col("department"),
col("salary"),
avg("salary").over(windowSpec).alias("department_avg_salary"),
(col("salary") - avg("salary").over(windowSpec)).alias("diff_from_avg")
))
# Show the result
result.show()
"""
agent.chat(f"translate this pyspark query {q}, to Snowflake")
```
### Use Waii API directly
You can also use Waii API directly, see [here](https://github.com/waii-ai/waii-sdk-py)
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-tools-waii",
"maintainer": "wangdatan",
"docs_url": null,
"requires_python": "<4.0,>=3.8.1",
"maintainer_email": null,
"keywords": null,
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/81/42/dfef0475622ecb866fae8880f758e2e4f001bf57ed02de096eede838505a/llama_index_tools_waii-0.2.0.tar.gz",
"platform": null,
"description": "# Waii Tool\n\nThis tool connects to database connections managed by Waii, which allows generic SQL queries, do performance analyze, describe a SQL query, and more.\n\n## Usage\n\nFirst you need to create a waii.ai account, you request an account from [here](https://waii.ai/).\n\nInitialize the tool with your account credentials:\n\n```python\nfrom llama_index.tools.waii import WaiiToolSpec\n\nwaii_tool = WaiiToolSpec(\n url=\"https://tweakit.waii.ai/api/\",\n # API Key of Waii (not OpenAI API key)\n api_key=\"...\",\n # Connection key of WAII connected database, see https://github.com/waii-ai/waii-sdk-py#get-connections\n database_key=\"...\",\n)\n```\n\n## Tools\n\nThe tools available are:\n\n- `get_answer`: Get answer to natural language question (which generate a SQL query, run it, explain the result)\n- `describe_query`: Describe a SQL query\n- `performance_analyze`: Analyze performance of a SQL query (by query_id)\n- `diff_query`: Compare two SQL queries\n- `describe_dataset`: Describe dataset, such as table, schema, etc.\n- `transcode`: Transcode SQL query to another SQL dialect\n- `get_semantic_contexts`: Get semantic contexts of a SQL query\n- `generate_query_only`: Generate SQL query only (not run it)\n- `run_query`: Run a SQL query\n\nYou can also load the data directly call `load_data`\n\n## Examples\n\n### Load data\n\n```python\ndocuments = waii_tool.load_data(\"Get all tables with their number of columns\")\nindex = VectorStoreIndex.from_documents(documents).as_query_engine()\n\nprint(index.query(\"Which table contains most columns?\"))\n```\n\n### Use as a Tool\n\n#### Initialize the agent:\n\n```python\nfrom llama_index.agent.openai import OpenAIAgent\nfrom llama_index.llms.openai import OpenAI\n\nagent = OpenAIAgent.from_tools(\n waii_tool.to_tool_list(), llm=OpenAI(model=\"gpt-4-1106-preview\")\n)\n```\n\n#### Ask simple question\n\n```python\nagent.chat(\"Give me top 3 countries with the most number of car factory\")\nagent.chat(\"What are the car factories of these countries\")\n```\n\n#### Do performance analyze\n\n```python\nagent.chat(\"Give me top 3 longest running queries, and their duration.\")\nagent.chat(\"analyze the 2nd-longest running query\")\n```\n\n#### Diff two queries\n\n```python\nprevious_query = \"\"\"\nSELECT\n employee_id,\n department,\n salary,\n AVG(salary) OVER (PARTITION BY department) AS department_avg_salary,\n salary - AVG(salary) OVER (PARTITION BY department) AS diff_from_avg\nFROM\n employees;\n\"\"\"\ncurrent_query = \"\"\"\nSELECT\n employee_id,\n department,\n salary,\n MAX(salary) OVER (PARTITION BY department) AS department_max_salary,\n salary - AVG(salary) OVER (PARTITION BY department) AS diff_from_avg\nFROM\n employees;\nLIMIT 100;\n\"\"\"\nagent.chat(f\"tell me difference between {previous_query} and {current_query}\")\n```\n\n#### Describe dataset\n\n```python\nagent.chat(\"Summarize the dataset\")\nagent.chat(\"Give me questions which I can ask about this dataset\")\n```\n\n#### Describe a query\n\n```python\nq = \"\"\"\nSELECT\n employee_id,\n department,\n salary,\n AVG(salary) OVER (PARTITION BY department) AS department_avg_salary,\n salary - AVG(salary) OVER (PARTITION BY department) AS diff_from_avg\nFROM\n employees;\n\"\"\"\nagent.chat(f\"what this query can do? {q}\")\n```\n\n#### Migrate query to another dialect\n\n```python\nq = \"\"\"\nfrom pyspark.sql import SparkSession\nfrom pyspark.sql.functions import avg, col\nfrom pyspark.sql.window import Window\n\n# Initialize Spark session\nspark = SparkSession.builder.appName(\"example\").getOrCreate()\n\n# Assuming you have a DataFrame called 'employees'\n# If not, you need to read your data into a DataFrame first\n\n# Define window specification\nwindowSpec = Window.partitionBy(\"department\")\n\n# Perform the query\nresult = (employees\n .select(\n col(\"employee_id\"),\n col(\"department\"),\n col(\"salary\"),\n avg(\"salary\").over(windowSpec).alias(\"department_avg_salary\"),\n (col(\"salary\") - avg(\"salary\").over(windowSpec)).alias(\"diff_from_avg\")\n ))\n\n# Show the result\nresult.show()\n\"\"\"\nagent.chat(f\"translate this pyspark query {q}, to Snowflake\")\n```\n\n### Use Waii API directly\n\nYou can also use Waii API directly, see [here](https://github.com/waii-ai/waii-sdk-py)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index tools waii integration",
"version": "0.2.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "24ff9b9404558cb707d75f35549750f251244fcedeb1ace6d3d215449c142968",
"md5": "097f9b0bd8533ceae6e574d76df67098",
"sha256": "e78a0d633cda1093af268cc8a71c1d4bb427c388f2cef285e9a5b48389a7e89a"
},
"downloads": -1,
"filename": "llama_index_tools_waii-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "097f9b0bd8533ceae6e574d76df67098",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8.1",
"size": 5404,
"upload_time": "2024-08-22T07:42:56",
"upload_time_iso_8601": "2024-08-22T07:42:56.869294Z",
"url": "https://files.pythonhosted.org/packages/24/ff/9b9404558cb707d75f35549750f251244fcedeb1ace6d3d215449c142968/llama_index_tools_waii-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8142dfef0475622ecb866fae8880f758e2e4f001bf57ed02de096eede838505a",
"md5": "d90e2eaff05a81ed9abc138b1896540c",
"sha256": "5c9f977382561b8cf7c25acdc333d3ca3b59b4138c177e0f5ad7cd90c8ae844c"
},
"downloads": -1,
"filename": "llama_index_tools_waii-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "d90e2eaff05a81ed9abc138b1896540c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8.1",
"size": 5158,
"upload_time": "2024-08-22T07:42:57",
"upload_time_iso_8601": "2024-08-22T07:42:57.765457Z",
"url": "https://files.pythonhosted.org/packages/81/42/dfef0475622ecb866fae8880f758e2e4f001bf57ed02de096eede838505a/llama_index_tools_waii-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-22 07:42:57",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-tools-waii"
}