Ragas Ragas
stable · 中文译文
中文译文 · 原文：https://docs.ragas.io/en/stable/howtos/integrations/oci_genai/ · 许可证 Apache-2.0

OCI Gen AI 集成

本指南说明如何将 Oracle Cloud Infrastructure (OCI) Generative AI 模型与 Ragas 一起用于评测。

安装

首先，安装 OCI 依赖：

pip install ragas[oci]

设置

1. 配置 OCI 认证

使用以下方法之一设置 OCI 配置：

选项 A：OCI CLI 配置

oci setup config

选项 B：环境变量

export OCI_CONFIG_FILE=~/.oci/config
export OCI_PROFILE=DEFAULT

选项 C：手动配置

config = {
    "user": "ocid1.user.oc1..example",
    "key_file": "~/.oci/private_key.pem",
    "fingerprint": "your_fingerprint",
    "tenancy": "ocid1.tenancy.oc1..example",
    "region": "us-ashburn-1"
}

2. 获取所需 ID

你需要：

  • Model ID：OCI 模型 ID（例如 cohere.command、meta.llama-3-8b）
  • Compartment ID：你的 OCI compartment OCID
  • Endpoint ID（可选）：如果使用自定义 endpoint

用法

基本用法

from ragas.llms import oci_genai_factory
from ragas import evaluate
from datasets import Dataset

# Initialize OCI Gen AI LLM
llm = oci_genai_factory(
    model_id="cohere.command",
    compartment_id="ocid1.compartment.oc1..example"
)

# Your dataset
dataset = Dataset.from_dict({
    "question": ["What is the capital of France?"],
    "answer": ["Paris"],
    "contexts": [["France is a country in Europe. Its capital is Paris."]],
    "ground_truth": ["Paris"]
})

# Evaluate with OCI Gen AI
result = evaluate(
    dataset,
    llm=llm,
    embeddings=None  # You can use any embedding model
)

高级配置

from ragas.llms import oci_genai_factory
from ragas.run_config import RunConfig

# Custom OCI configuration
config = {
    "user": "ocid1.user.oc1..example",
    "key_file": "~/.oci/private_key.pem",
    "fingerprint": "your_fingerprint",
    "tenancy": "ocid1.tenancy.oc1..example",
    "region": "us-ashburn-1"
}

# Custom run configuration
run_config = RunConfig(
    timeout=60,
    max_retries=3
)

# Initialize with custom config and endpoint
llm = oci_genai_factory(
    model_id="cohere.command",
    compartment_id="ocid1.compartment.oc1..example",
    config=config,
    endpoint_id="ocid1.endpoint.oc1..example",  # Optional
    run_config=run_config
)

与不同模型一起使用

# Cohere Command model
llm_cohere = oci_genai_factory(
    model_id="cohere.command",
    compartment_id="ocid1.compartment.oc1..example"
)

# Meta Llama model
llm_llama = oci_genai_factory(
    model_id="meta.llama-3-8b",
    compartment_id="ocid1.compartment.oc1..example"
)

# Using with different endpoints
llm_endpoint = oci_genai_factory(
    model_id="cohere.command",
    compartment_id="ocid1.compartment.oc1..example",
    endpoint_id="ocid1.endpoint.oc1..example"
)

可用模型

OCI Gen AI 支持多种模型，包括：

  • Cohere：cohere.command、cohere.command-light
  • Meta：meta.llama-3-8b、meta.llama-3-70b
  • Mistral：mistral.mistral-7b-instruct
  • 以及更多：查看 OCI 文档了解最新可用模型

错误处理

OCI Gen AI wrapper 包含全面的错误处理：

try:
    result = evaluate(dataset, llm=llm)
except Exception as e:
    print(f"Evaluation failed: {e}")

性能考虑

  1. 速率限制：OCI Gen AI 有速率限制。请使用合适的重试配置。
  2. 超时：根据你的用例设置合适的超时。
  3. 批处理：该 wrapper 支持对多次补全进行批处理。

故障排除

常见问题

  1. 认证错误

text Error: OCI SDK authentication failed

解决方案：核实你的 OCI 配置和凭证。

  1. 找不到模型

text Error: Model not found in compartment

解决方案：检查该 model ID 是否存在于你的 compartment 中。

  1. 权限错误

text Error: Insufficient permissions

解决方案：确保你的用户具备 Generative AI 所需的 IAM 策略。

调试模式

启用 debug 日志以排查问题：

import logging
logging.basicConfig(level=logging.DEBUG)

# Your OCI Gen AI code here

示例

完整评测示例

from ragas import evaluate
from ragas.llms import oci_genai_factory
from ragas.metrics import faithfulness, answer_relevancy, context_precision
from datasets import Dataset

# Initialize OCI Gen AI
llm = oci_genai_factory(
    model_id="cohere.command",
    compartment_id="ocid1.compartment.oc1..example"
)

# Create dataset
dataset = Dataset.from_dict({
    "question": [
        "What is the capital of France?",
        "Who wrote Romeo and Juliet?"
    ],
    "answer": [
        "Paris is the capital of France.",
        "William Shakespeare wrote Romeo and Juliet."
    ],
    "contexts": [
        ["France is a country in Europe. Its capital is Paris."],
        ["Romeo and Juliet is a play by William Shakespeare."]
    ],
    "ground_truth": [
        "Paris",
        "William Shakespeare"
    ]
})

# Evaluate
result = evaluate(
    dataset,
    metrics=[faithfulness, answer_relevancy, context_precision],
    llm=llm
)

print(result)

使用 OCI Gen AI 的自定义指标

from ragas.metrics import MetricWithLLM

# Create custom metric using OCI Gen AI
class CustomMetric(MetricWithLLM):
    def __init__(self):
        super().__init__()
        self.llm = oci_genai_factory(
            model_id="cohere.command",
            compartment_id="ocid1.compartment.oc1..example"
        )

# Use in evaluation
result = evaluate(
    dataset,
    metrics=[CustomMetric()],
    llm=llm
)

最佳实践

  1. 选用合适的模型：根据评测需求选择模型。
  2. 监控成本：OCI Gen AI 用量会计费。请监控用量。
  3. 处理错误：生产环境中实现妥善的错误处理。
  4. 使用缓存：对重复评测启用缓存。
  5. 批处理操作：尽可能使用批处理以提高效率。

支持

针对 OCI Gen AI 集成的特定问题：

  • 查看 OCI 文档：https://docs.oracle.com/en-us/iaas/Content/generative-ai/
  • OCI Python SDK：https://docs.oracle.com/en-us/iaas/tools/python/2.160.1/api/generative_ai.html
  • Ragas GitHub issues：https://github.com/vibrantlabsai/ragas/issues
← Google GeminiAG-UI →