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

# Camel.datagen.evol instruct.evol instruct

<a id="camel.datagen.evol_instruct.evol_instruct" />

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline" />

## EvolInstructPipeline

```python theme={"system"}
class EvolInstructPipeline:
```

Pipeline for evolving prompts using the Evol-Instruct methodology.

Supports custom templates defining evolution strategies and methods. The
pipeline leverages language models to iteratively refine prompts through
specified evolution strategies.

**Parameters:**

* **templates** (Type\[EvolInstructTemplates]): Template class containing evolution strategy and method definitions. Must provide `EVOL_METHODS` and `STRATEGY` attributes. (default: :obj:`EvolInstructTemplates`)
* **agent** (Optional\[ChatAgent]): Chat agent instance for LLM interaction.
* **If**: obj:`None`, initializes with a default ChatAgent. (default: :obj:`None`)

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline.__init__" />

### **init**

```python theme={"system"}
def __init__(
    self,
    templates: Type = EvolInstructTemplates,
    agent: Optional[ChatAgent] = None
):
```

Initialize pipeline with templates and language model agent.

**Parameters:**

* **templates** (Type\[EvolInstructTemplates]): Template class containing evolution strategy configurations. (default: :obj:`EvolInstructTemplates`)
* **agent** (Optional\[ChatAgent]): Preconfigured chat agent instance. Creates a default ChatAgent if not provided. (default: :obj:`None`)

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline._resolve_evolution_method" />

### \_resolve\_evolution\_method

```python theme={"system"}
def _resolve_evolution_method(self, method_key: str):
```

Resolve evolution method key to concrete implementation.

**Parameters:**

* **method\_key** (str): Input method identifier. Can be: - Direct method key from templates.EVOL\_METHODS - Strategy name from templates.STRATEGY keys

**Returns:**

str: Resolved method key from EVOL\_METHODS

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline._get_evolution_methods" />

### \_get\_evolution\_methods

```python theme={"system"}
def _get_evolution_methods(self, method: Union[str, List[str]], num_generations: int = 2):
```

Get list of evolution methods based on input specification.

**Parameters:**

* **method** (Union\[str, List\[str]]): Specification for method selection. Can be: - Strategy name for methods from that strategy - Specific method name - List of method specifications
* **num\_generations** (int): Number of methods to return.

**Returns:**

List\[str]: List of resolved method names

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline._generate_single_evolution" />

### \_generate\_single\_evolution

```python theme={"system"}
def _generate_single_evolution(
    self,
    prompt: str,
    method: str,
    return_method: bool = False
):
```

Generate a single evolved prompt from a seed prompt.

**Parameters:**

* **prompt** (str): The seed prompt to evolve.
* **method** (str): The evolution method key to use.
* **return\_method** (bool): If True, returns method along with prompt.

**Returns:**

Tuple\[str, str]: Evolved prompt and method

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline._generate_multiple_evolutions" />

### \_generate\_multiple\_evolutions

```python theme={"system"}
def _generate_multiple_evolutions(
    self,
    prompt: str,
    method: Union[str, List[str]],
    num_generations: int = 2,
    keep_original: bool = True,
    num_threads: int = 10
):
```

Generate multiple evolved versions of a prompt.

**Parameters:**

* **prompt** (str): Seed prompt to evolve.
* **method** (Union\[str, List\[str]]): Evolution method specification.
* **num\_generations** (int): Candidates to generate per iteration.
* **keep\_original** (bool): Whether to keep the original prompt.
* **num\_threads** (int): Number of threads for parallel processing.

**Returns:**

List\[Tuple\[str, str]]: List of (evolved\_prompt, method) pairs

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline._generate_iterative_evolutions" />

### \_generate\_iterative\_evolutions

```python theme={"system"}
def _generate_iterative_evolutions(
    self,
    prompt: str,
    evolution_spec: Union[str, List[Union[str, List[str]]]],
    num_generations: int = 2,
    num_iterations: Optional[int] = None,
    keep_original: bool = True,
    scorer: Optional[BaseScorer] = None,
    num_threads: int = 10
):
```

Generate iterative evolutions of a prompt with scoring.

**Parameters:**

* **prompt** (str): Seed prompt to evolve.
* **evolution\_spec** (Union\[str, List\[Union\[str, List\[str]]]]): Evolution method specification. If a list is provided and num\_iterations is None, then num\_iterations is set to the length of the list.
* **num\_generations** (int): Candidates to generate per iteration.
* **num\_iterations** (Optional\[int]): Number of evolution iterations. Defaults to the length of evolution\_spec.
* **keep\_original** (bool): Include original prompt in results.
* **scorer** (Optional\[BaseScorer]): Scoring model for candidate.
* **num\_threads** (int): Number of threads for parallel processing.

**Returns:**

Dict\[int, List\[Dict\[str, Any]]]: Evolution results per iteration,
where each candidate is represented as a dict with keys:
"instruction", "method", and "scores".

<a id="camel.datagen.evol_instruct.evol_instruct.EvolInstructPipeline.generate" />

### generate

```python theme={"system"}
def generate(
    self,
    prompts: List[str],
    evolution_spec: Union[str, List[Union[str, List[str]]]],
    num_generations: int = 2,
    num_iterations: Optional[int] = None,
    keep_original: bool = True,
    scorer: Optional[BaseScorer] = None,
    num_chunks: int = 1,
    retry_limit: int = 3,
    retry_delay: float = 1.0,
    num_threads: int = 10
):
```

Evolve a batch of prompts through iterative refinement.

**Parameters:**

* **prompts** (List\[str]): Seed prompts to evolve.
* **evolution\_spec** (Union\[str, List\[Union\[str, List\[str]]]]): Evolution method specification. If a list is provided and num\_iterations is None, then num\_iterations is set to the length of the list.
* **num\_generations** (int): Candidates to generate per iteration.
* **num\_iterations** (Optional\[int]): Number of evolution iterations. Defaults to the length of evolution\_spec.
* **keep\_original** (bool): Include original prompts in results.
* **scorer** (Optional\[BaseScorer]): Scoring model for candidate.
* **num\_chunks** (int): Number of parallel processing chunks.
* **retry\_limit** (int): Max retries for failed generations.
* **retry\_delay** (float): Delay between retries in seconds.
* **num\_threads** (int): Number of threads for parallel processing.

**Returns:**

List\[Dict\[int, List\[Dict\[str, Any]]]]: Evolution results.