mirror of https://github.com/hwchase17/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
282 lines
12 KiB
Plaintext
282 lines
12 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "657d2c8c-54b4-42a3-9f02-bdefa0ed6728",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Custom Pairwise Evaluator\n",
|
|
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/guides/evaluation/comparison/custom.ipynb)\n",
|
|
"\n",
|
|
"You can make your own pairwise string evaluators by inheriting from `PairwiseStringEvaluator` class and overwriting the `_evaluate_string_pairs` method (and the `_aevaluate_string_pairs` method if you want to use the evaluator asynchronously).\n",
|
|
"\n",
|
|
"In this example, you will make a simple custom evaluator that just returns whether the first prediction has more whitespace tokenized 'words' than the second.\n",
|
|
"\n",
|
|
"You can check out the reference docs for the [PairwiseStringEvaluator interface](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.schema.PairwiseStringEvaluator.html#langchain.evaluation.schema.PairwiseStringEvaluator) for more info.\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "93f3a653-d198-4291-973c-8d1adba338b2",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from typing import Optional, Any\n",
|
|
"from langchain.evaluation import PairwiseStringEvaluator\n",
|
|
"\n",
|
|
"\n",
|
|
"class LengthComparisonPairwiseEvalutor(PairwiseStringEvaluator):\n",
|
|
" \"\"\"\n",
|
|
" Custom evaluator to compare two strings.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" def _evaluate_string_pairs(\n",
|
|
" self,\n",
|
|
" *,\n",
|
|
" prediction: str,\n",
|
|
" prediction_b: str,\n",
|
|
" reference: Optional[str] = None,\n",
|
|
" input: Optional[str] = None,\n",
|
|
" **kwargs: Any,\n",
|
|
" ) -> dict:\n",
|
|
" score = int(len(prediction.split()) > len(prediction_b.split()))\n",
|
|
" return {\"score\": score}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "7d4a77c3-07a7-4076-8e7f-f9bca0d6c290",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'score': 1}"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"evaluator = LengthComparisonPairwiseEvalutor()\n",
|
|
"\n",
|
|
"evaluator.evaluate_string_pairs(\n",
|
|
" prediction=\"The quick brown fox jumped over the lazy dog.\",\n",
|
|
" prediction_b=\"The quick brown fox jumped over the dog.\",\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "d90f128f-6f49-42a1-b05a-3aea568ee03b",
|
|
"metadata": {},
|
|
"source": [
|
|
"## LLM-Based Example\n",
|
|
"\n",
|
|
"That example was simple to illustrate the API, but it wasn't very useful in practice. Below, use an LLM with some custom instructions to form a simple preference scorer similar to the built-in [PairwiseStringEvalChain](https://api.python.langchain.com/en/latest/evaluation/langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain.html#langchain.evaluation.comparison.eval_chain.PairwiseStringEvalChain). We will use `ChatAnthropic` for the evaluator chain."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "b4b43098-4d96-417b-a8a9-b3e75779cfe8",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"# %pip install anthropic\n",
|
|
"# %env ANTHROPIC_API_KEY=YOUR_API_KEY"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "b6e978ab-48f1-47ff-9506-e13b1a50be6e",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from typing import Optional, Any\n",
|
|
"from langchain.evaluation import PairwiseStringEvaluator\n",
|
|
"from langchain.chat_models import ChatAnthropic\n",
|
|
"from langchain.chains import LLMChain\n",
|
|
"\n",
|
|
"\n",
|
|
"class CustomPreferenceEvaluator(PairwiseStringEvaluator):\n",
|
|
" \"\"\"\n",
|
|
" Custom evaluator to compare two strings using a custom LLMChain.\n",
|
|
" \"\"\"\n",
|
|
"\n",
|
|
" def __init__(self) -> None:\n",
|
|
" llm = ChatAnthropic(model=\"claude-2\", temperature=0)\n",
|
|
" self.eval_chain = LLMChain.from_string(\n",
|
|
" llm,\n",
|
|
" \"\"\"Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
|
|
"\n",
|
|
"Input: How do I get the path of the parent directory in python 3.8?\n",
|
|
"Option A: You can use the following code:\n",
|
|
"```python\n",
|
|
"import os\n",
|
|
"\n",
|
|
"os.path.dirname(os.path.dirname(os.path.abspath(__file__)))\n",
|
|
"```\n",
|
|
"Option B: You can use the following code:\n",
|
|
"```python\n",
|
|
"from pathlib import Path\n",
|
|
"Path(__file__).absolute().parent\n",
|
|
"```\n",
|
|
"Reasoning: Both options return the same result. However, since option B is more concise and easily understand, it is preferred.\n",
|
|
"Preference: B\n",
|
|
"\n",
|
|
"Which option is preferred? Do not take order into account. Evaluate based on accuracy and helpfulness. If neither is preferred, respond with C. Provide your reasoning, then finish with Preference: A/B/C\n",
|
|
"Input: {input}\n",
|
|
"Option A: {prediction}\n",
|
|
"Option B: {prediction_b}\n",
|
|
"Reasoning:\"\"\",\n",
|
|
" )\n",
|
|
"\n",
|
|
" @property\n",
|
|
" def requires_input(self) -> bool:\n",
|
|
" return True\n",
|
|
"\n",
|
|
" @property\n",
|
|
" def requires_reference(self) -> bool:\n",
|
|
" return False\n",
|
|
"\n",
|
|
" def _evaluate_string_pairs(\n",
|
|
" self,\n",
|
|
" *,\n",
|
|
" prediction: str,\n",
|
|
" prediction_b: str,\n",
|
|
" reference: Optional[str] = None,\n",
|
|
" input: Optional[str] = None,\n",
|
|
" **kwargs: Any,\n",
|
|
" ) -> dict:\n",
|
|
" result = self.eval_chain(\n",
|
|
" {\n",
|
|
" \"input\": input,\n",
|
|
" \"prediction\": prediction,\n",
|
|
" \"prediction_b\": prediction_b,\n",
|
|
" \"stop\": [\"Which option is preferred?\"],\n",
|
|
" },\n",
|
|
" **kwargs,\n",
|
|
" )\n",
|
|
"\n",
|
|
" response_text = result[\"text\"]\n",
|
|
" reasoning, preference = response_text.split(\"Preference:\", maxsplit=1)\n",
|
|
" preference = preference.strip()\n",
|
|
" score = 1.0 if preference == \"A\" else (0.0 if preference == \"B\" else None)\n",
|
|
" return {\"reasoning\": reasoning.strip(), \"value\": preference, \"score\": score}"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "5cbd8b1d-2cb0-4f05-b435-a1a00074d94a",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"evaluator = CustomPreferenceEvaluator()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "2c0a7fb7-b976-4443-9f0e-e707a6dfbdf7",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'reasoning': 'Option B is preferred over option A for importing from a relative directory, because it is more straightforward and concise.\\n\\nOption A uses the importlib module, which allows importing a module by specifying the full name as a string. While this works, it is less clear compared to option B.\\n\\nOption B directly imports from the relative path using dot notation, which clearly shows that it is a relative import. This is the recommended way to do relative imports in Python.\\n\\nIn summary, option B is more accurate and helpful as it uses the standard Python relative import syntax.',\n",
|
|
" 'value': 'B',\n",
|
|
" 'score': 0.0}"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"evaluator.evaluate_string_pairs(\n",
|
|
" input=\"How do I import from a relative directory?\",\n",
|
|
" prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
|
|
" prediction_b=\"from .sibling import foo\",\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 13,
|
|
"id": "f13a1346-7dbe-451d-b3a3-99e8fc7b753b",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"CustomPreferenceEvaluator requires an input string.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Setting requires_input to return True adds additional validation to avoid returning a grade when insufficient data is provided to the chain.\n",
|
|
"\n",
|
|
"try:\n",
|
|
" evaluator.evaluate_string_pairs(\n",
|
|
" prediction=\"use importlib! importlib.import_module('.my_package', '.')\",\n",
|
|
" prediction_b=\"from .sibling import foo\",\n",
|
|
" )\n",
|
|
"except ValueError as e:\n",
|
|
" print(e)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e7829cc3-ebd1-4628-ae97-15166202e9cc",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.11.2"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|