> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lyzr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# DataAnalyzr constructor

> API reference for the DataAnalyzr constructor

```python theme={null}
DataAnalyzr(
    analysis_type: Literal["sql", "ml", "skip"],
    api_key: Optional[str] = None,
    class_params: Optional[dict] = None,
    generator_llm: Optional[LiteLLM] = None,
    analysis_llm: Optional[LiteLLM] = None,
    context: Optional[str] = None,
    log_params: Optional[dict] = None,
) -> DataAnalyzr
```

Constructor method for initializing a `DataAnalyzr` object.

## Parameters

<ParamField path="analysis_type" type="Literal['sql', 'ml', 'skip']" required>
  The type of analysis to be performed.

  ```python theme={null}
  analysis_type = "sql"
  ```
</ParamField>

<ParamField path="api_key" type="string">
  API key for accessing LLM services. May also be set as an environment variable.

  ```python theme={null}
  api_key = "sk-apikey"
  ```
</ParamField>

<ParamField path="class_params" type="dictionary">
  Dictionary of class parameters. Accepts `max_retries`, `time_limit`, and `auto_train`.

  ```python theme={null}
  class_params = {
      "max_retries": 5, # int
      "time_limit": 60, # int
      "auto_train": True, # bool
  }
  ```

  <Expandable title="details">
    <ParamField path="max_retries" type="integer">
      Maximum number of retries for the LLM calls and analysis. Default is 10.
    </ParamField>

    <ParamField path="time_limit" type="integer">
      Time limit in seconds for the LLM calls and analysis. Default is 45 for analysis and 60 for visualisation.
    </ParamField>

    <ParamField path="auto_train" type="boolean">
      Whether to automatically add questions with their SQL query or Python code to the vector store. Default is True.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField path="generator_llm" type="LiteLLM">
  LLM instance for generating analysis. Default LLM used is GPT-4o.

  ```python theme={null}
  from lyzr.base import LyzrLLMFactory
  generator_llm = LyzrLLMFactory.from_defaults(model="gpt-4-turbo")
  ```

  For details on configuring the LLM, see the [Large Language Models](/pre-built-agents/data-analyzr/advanced-configuration/llms) guide.
</ParamField>

<ParamField path="analysis_llm" type="LiteLLM">
  LLM instance for performing analysis. Default LLM used is GPT-4o.

  ```python theme={null}
  from lyzr.base import LyzrLLMFactory
  analysis_llm = LyzrLLMFactory.from_defaults(model="gpt-4o")
  ```

  For details on configuring the LLM, see the [Large Language Models](/pre-built-agents/data-analyzr/advanced-configuration/llms) guide.
</ParamField>

<ParamField path="context" type="string or dictionary">
  Context for analysis and response generation. Default is an empty string.

  * This context is used in the analysis, insights, recommendations, and tasks methods.
  * When passed as a string, the same context is applied to all sections - analysis, insights, recommendations, and tasks.
  * When passed as a dictionary, it should have keys `analysis`, `visualisation`, `insights`, `recommendations`, and `tasks`.
  * To override the class context for a specific query, pass the context to the [`ask` method](/pre-built-agents/data-analyzr/api-reference/ask).

  ```python theme={null}
  context = "Sales data analysis for Q1 2023"
  # or
  context = {
      "analysis": "Sales data analysis for Q1 2023",
      "visualisation": "Distribution plot for sales data",
      "insights": "Key trends in sales data",
      "recommendations": "Improve sales performance",
      "tasks": "Analyze sales data",
  }
  ```

  <Expandable title="details">
    <ParamField path="analysis" type="string">
      Context for the analysis method.
    </ParamField>

    <ParamField path="visualisation" type="string">
      Context for the visualisation method.
    </ParamField>

    <ParamField path="insights" type="string">
      Context for the insights method.
    </ParamField>

    <ParamField path="recommendations" type="string">
      Context for the recommendations method.
    </ParamField>

    <ParamField path="tasks" type="string">
      Context for the tasks method.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField path="log_params" type="dictionary">
  Dictionary of logging parameters. Accepts `log_filename`, `log_level`, and `print_log`.

  ```python theme={null}
  log_params = {
      "log_filename": "dataanalyzr.csv", # str
      "log_level": "INFO", # str
      "print_log": False, # bool
  }
  ```

  <Expandable title="details">
    <ParamField path="log_filename" type="string">
      Name of the log file. Default is `dataanalyzr.csv`.
    </ParamField>

    <ParamField path="log_level" type="string">
      Log level for the logger. Default is `INFO`.
    </ParamField>

    <ParamField path="print_log" type="boolean">
      Whether to print logs to the console. Default is `False`.
    </ParamField>
  </Expandable>
</ParamField>

## Returns

<ResponseField name="data_analyzr" type="DataAnalyzr">
  DataAnalyzr object for performing conversational data analysis.
</ResponseField>

## Example usage

```python theme={null}
from lyzr.base import LyzrLLMFactory
from lyzr.data_analyzr.data_analyzr import DataAnalyzr

analysis_type = "sql"
log_params = {
    "log_filename": "dataanalyzr.log",
    "log_level": "DEBUG",
    "print_log": True,
}
class_params = {
    "max_retries": 5,
    "time_limit": 60,
    "auto_train": True,
}
generator_llm = LyzrLLMFactory.from_defaults(model="gpt-4-turbo")
analysis_llm = LyzrLLMFactory.from_defaults(model="gpt-4o")
context = "Sales data analysis for Q1 2023"

data_analyzr = DataAnalyzr(
    analysis_type=analysis_type,
    api_key=api_key,
    class_params=class_params,
    generator_llm=generator_llm,
    analysis_llm=analysis_llm,
    context=context,
    log_params=log_params,
)
```