> ## 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.

# Attributes of the DataAnalyzr Class

> Overview of the attributes of the DataAnalyzr class in the lyzr library

1. [**Basic Attributes**](/pre-built-agents/data-analyzr/api-reference/attributes#basic-attributes) - Instance configuration attributes. Include `analysis_type`, `params`, `generator_llm`, `analysis_llm`, `context`, `logger`.
2. [**Data Related Attributes**](/pre-built-agents/data-analyzr/api-reference/attributes#data-related-attributes) - Input dataset and vector store connections. Include `df_dict`, `database_connector`, `vector_store`.
3. [**Analysis Related Attributes**](/pre-built-agents/data-analyzr/api-reference/attributes#analysis-related-attributes) - Values generated during analysis. Include `analysis_code`, `analysis_guide`, `analysis_output`, `plot_code`.
4. [**Output Attributes**](/pre-built-agents/data-analyzr/api-reference/attributes#output-attributes) - Output values returned as responses. Include `plot_output`, `insights_output`, `recommendations_output`, `tasks_output`, `ai_queries_output`.

## Basic Attributes

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

<ParamField path="params" type="ParamsDict">
  Dictionary of class parameters.

  <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.

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

  <Expandable title="details">
    <ParamField path="model" type="string">
      Name of the LLM model to use.
    </ParamField>

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

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

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

  <Expandable title="details">
    <ParamField path="model" type="string">
      Name of the LLM model to use.
    </ParamField>

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

<ParamField path="context" type="ContextDict">
  Context dictionary for the analysis.

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

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

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

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

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

<ParamField path="logger" type="logging.Logger">
  Logger object for logging messages.
</ParamField>

## Data Related Attributes

<ParamField path="df_dict" type="dictionary">
  Dictionary of dataframes loaded from files or databases.

  ```python theme={null}
  df_dict = {
      "table_name": pandas.DataFrame,
  }
  ```
</ParamField>

<ParamField path="database_connector" type="DatabaseConnector">
  Database connector object for connecting to databases.

  <Expandable title="details">
    <ParamField path="host" type="string">
      Hostname of the database server. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="port" type="string">
      Port number of the database server. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="user" type="string">
      Username for the database connection. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="database" type="string">
      Name of the database to connect to. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="password" type="string">
      Password for the database connection. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="schema" type="list">
      Schema names to load. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="tables" type="list">
      Table names to load. Applicable for PostgreSQL and Redshift databases.
    </ParamField>

    <ParamField path="conn" type="psycopg2.connect or redshift_connector.connect or sqlite3.connect">
      Connection object for the database.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField path="vector_store" type="ChromaDBVectorStore">
  Vector store object for storing questions and their SQL queries or Python code.

  For details on configuring the vector store, see the [Vector Store](/pre-built-agents/data-analyzr/advanced-configuration/vector-store) guide.

  <Expandable title="details">
    <ParamField path="path" type="string">
      Path to the vector store file.
    </ParamField>

    <ParamField path="chroma_client" type="chromadb.PersistentClient">
      ChromaDB client object for storing vectors.
    </ParamField>

    <ParamField path="documentation_collection" type="chromadb.Collection">
      Collection object for storing documentation.
    </ParamField>

    <ParamField path="ddl_collection" type="chromadb.Collection">
      Collection object for storing DDL queries.
    </ParamField>

    <ParamField path="sql_collection" type="chromadb.Collection">
      Collection object for storing question and SQL query pairs.
    </ParamField>

    <ParamField path="python_collection" type="chromadb.Collection">
      Collection object for storing question and Python code pairs.
    </ParamField>

    <ParamField path="plot_collection" type="chromadb.Collection">
      Collection object for storing question and plot code pairs.
    </ParamField>
  </Expandable>
</ParamField>

## Analysis Related Attributes

<ParamField path="analysis_code" type="string">
  Code generated by the LLM for analysis.
</ParamField>

<ParamField path="analysis_guide" type="string">
  Guide used to generate the analysis code.
</ParamField>

<ParamField path="analysis_output" type="pandas.DataFrame or dictionary or string">
  Output generated by executing the analysis code.
</ParamField>

<ParamField path="plot_code" type="string">
  Code generated by the LLM for generating visualisations.
</ParamField>

## Output Attributes

<ParamField path="plot_output" type="string">
  Path to a PNG file containing the plot generated by executing the plot code.
</ParamField>

<ParamField path="insights_output" type="string">
  Insights generated by the LLM.
</ParamField>

<ParamField path="recommendations_output" type="string">
  Recommendations generated by the LLM.
</ParamField>

<ParamField path="tasks_output" type="string">
  Tasks generated by the LLM.
</ParamField>

<ParamField path="ai_queries_output" type="dictionary">
  AI queries generated by the LLM.

  ```python theme={null}
  ai_queries_output = {
      "type_of_analysis1": ["query1", "query2", "query3", "query4"],
      "type_of_analysis2": ["query1", "query2", "query3", "query4"],
      "type_of_analysis3": ["query1", "query2", "query3", "query4"],
  }
  ```
</ParamField>