自定义模型

Ragas 可以使用 LLM 和/或 Embedding 进行评估和合成数据生成。这些模型都可以根据你的可用性进行定制。

注意

Ragas 支持 langchain 中所有可用的 LLM 和 Embedding 模型。

BaseRagasLLM 和 BaseRagasEmbeddings 是 Ragas 在内部用于 LLM 和 Embedding 的基类。任何自定义的 LLM 或 Embedding 都应该是这些基类的子类。
如果你正在使用 Langchain，你可以直接传递 Langchain LLM 和 Embedding，Ragas 会根据需要用 LangchainLLMWrapper 或 LangchainEmbeddingsWrapper 对其进行封装。

Azure OpenAI

pip install langchain_openai

from langchain_openai.chat_models import AzureChatOpenAI
from langchain_openai.embeddings import AzureOpenAIEmbeddings
from ragas.llms import LangchainLLMWrapper
from ragas.embeddings import LangchainEmbeddingsWrapper

azure_configs = {
    "base_url": "https://<your-endpoint>.openai.azure.com/",
    "model_deployment": "your-deployment-name",
    "model_name": "your-model-name",
    "embedding_deployment": "your-deployment-name",
    "embedding_name": "text-embedding-ada-002",  # most likely
}


azure_llm = AzureChatOpenAI(
    openai_api_version="2023-05-15",
    azure_endpoint=azure_configs["base_url"],
    azure_deployment=azure_configs["model_deployment"],
    model=azure_configs["model_name"],
    validate_base_url=False,
)

# init the embeddings for answer_relevancy, answer_correctness and answer_similarity
azure_embeddings = AzureOpenAIEmbeddings(
    openai_api_version="2023-05-15",
    azure_endpoint=azure_configs["base_url"],
    azure_deployment=azure_configs["embedding_deployment"],
    model=azure_configs["embedding_name"],
)

azure_llm = LangchainLLMWrapper(azure_llm)
azure_embeddings = LangchainEmbeddingsWrapper(azure_embeddings)

耶！现在你可以使用 ragas 与 Azure OpenAI 端点一起工作了

Google Vertex

!pip install langchain_google_vertexai

import google.auth
from langchain_google_vertexai import ChatVertexAI, VertexAIEmbeddings
from ragas.llms import LangchainLLMWrapper
from ragas.embeddings import LangchainEmbeddingsWrapper
from langchain_core.outputs import LLMResult, ChatGeneration

config = {
    "project_id": "<your-project-id>",
    "chat_model_id": "gemini-1.5-pro-002",
    "embedding_model_id": "text-embedding-005",
}

# authenticate to GCP
creds, _ = google.auth.default(quota_project_id=config["project_id"])

# create Langchain LLM and Embeddings
vertextai_llm = ChatVertexAI(
    credentials=creds,
    model_name=config["chat_model_id"],
)
vertextai_embeddings = VertexAIEmbeddings(
    credentials=creds, model_name=config["embedding_model_id"]
)

# Create a custom is_finished_parser to capture Gemini generation completion signals
def gemini_is_finished_parser(response: LLMResult) -> bool:
    is_finished_list = []
    for g in response.flatten():
        resp = g.generations[0][0]

        # Check generation_info first
        if resp.generation_info is not None:
            finish_reason = resp.generation_info.get("finish_reason")
            if finish_reason is not None:
                is_finished_list.append(
                    finish_reason in ["STOP", "MAX_TOKENS"]
                )
                continue

        # Check response_metadata as fallback
        if isinstance(resp, ChatGeneration) and resp.message is not None:
            metadata = resp.message.response_metadata
            if metadata.get("finish_reason"):
                is_finished_list.append(
                    metadata["finish_reason"] in ["STOP", "MAX_TOKENS"]
                )
            elif metadata.get("stop_reason"):
                is_finished_list.append(
                    metadata["stop_reason"] in ["STOP", "MAX_TOKENS"] 
                )

        # If no finish reason found, default to True
        if not is_finished_list:
            is_finished_list.append(True)

    return all(is_finished_list)


vertextai_llm = LangchainLLMWrapper(vertextai_llm, is_finished_parser=gemini_is_finished_parser)
vertextai_embeddings = LangchainEmbeddingsWrapper(vertextai_embeddings)

耶！现在你可以使用 ragas 与 Google VertexAI 端点一起工作了

AWS Bedrock

pip install langchain_aws

from langchain_aws import ChatBedrockConverse
from langchain_aws import BedrockEmbeddings
from ragas.llms import LangchainLLMWrapper
from ragas.embeddings import LangchainEmbeddingsWrapper

config = {
    "credentials_profile_name": "your-profile-name",  # E.g "default"
    "region_name": "your-region-name",  # E.g. "us-east-1"
    "llm": "your-llm-model-id",  # E.g "anthropic.claude-3-5-sonnet-20241022-v2:0"
    "embeddings": "your-embedding-model-id",  # E.g "amazon.titan-embed-text-v2:0"
    "temperature": 0.4,
}

bedrock_llm = ChatBedrockConverse(
    credentials_profile_name=config["credentials_profile_name"],
    region_name=config["region_name"],
    base_url=f"https://bedrock-runtime.{config['region_name']}.amazonaws.com",
    model=config["llm"],
    temperature=config["temperature"],
)

# init the embeddings
bedrock_embeddings = BedrockEmbeddings(
    credentials_profile_name=config["credentials_profile_name"],
    region_name=config["region_name"],
    model_id=config["embeddings"],
)

bedrock_llm = LangchainLLMWrapper(bedrock_llm)
bedrock_embeddings = LangchainEmbeddingsWrapper(bedrock_embeddings)

耶！现在你可以使用 ragas 与 AWS Bedrock 端点一起工作了