forked from Archives/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.
154 lines
9.6 KiB
Plaintext
154 lines
9.6 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4d6c0c86",
|
|
"metadata": {},
|
|
"source": [
|
|
"# OutputFixingParser\n",
|
|
"\n",
|
|
"This output parser wraps another output parser and tries to fix any mistakes\n",
|
|
"\n",
|
|
"The Pydantic guardrail simply tries to parse the LLM response. If it does not parse correctly, then it errors.\n",
|
|
"\n",
|
|
"But we can do other things besides throw errors. Specifically, we can pass the misformatted output, along with the formatted instructions, to the model and ask it to fix it.\n",
|
|
"\n",
|
|
"For this example, we'll use the above OutputParser. Here's what happens if we pass it a result that does not comply with the schema:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "50048777",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.prompts import PromptTemplate, ChatPromptTemplate, HumanMessagePromptTemplate\n",
|
|
"from langchain.llms import OpenAI\n",
|
|
"from langchain.chat_models import ChatOpenAI\n",
|
|
"from langchain.output_parsers import PydanticOutputParser\n",
|
|
"from pydantic import BaseModel, Field, validator\n",
|
|
"from typing import List"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "4f1b563f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"class Actor(BaseModel):\n",
|
|
" name: str = Field(description=\"name of an actor\")\n",
|
|
" film_names: List[str] = Field(description=\"list of names of films they starred in\")\n",
|
|
" \n",
|
|
"actor_query = \"Generate the filmography for a random actor.\"\n",
|
|
"\n",
|
|
"parser = PydanticOutputParser(pydantic_object=Actor)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "73beb20d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"misformatted = \"{'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "f0e5ba80",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"ename": "OutputParserException",
|
|
"evalue": "Failed to parse Actor from completion {'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}. Got: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[0;31mJSONDecodeError\u001b[0m Traceback (most recent call last)",
|
|
"File \u001b[0;32m~/workplace/langchain/langchain/output_parsers/pydantic.py:23\u001b[0m, in \u001b[0;36mPydanticOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 22\u001b[0m json_str \u001b[38;5;241m=\u001b[39m match\u001b[38;5;241m.\u001b[39mgroup()\n\u001b[0;32m---> 23\u001b[0m json_object \u001b[38;5;241m=\u001b[39m \u001b[43mjson\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloads\u001b[49m\u001b[43m(\u001b[49m\u001b[43mjson_str\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 24\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpydantic_object\u001b[38;5;241m.\u001b[39mparse_obj(json_object)\n",
|
|
"File \u001b[0;32m~/.pyenv/versions/3.9.1/lib/python3.9/json/__init__.py:346\u001b[0m, in \u001b[0;36mloads\u001b[0;34m(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)\u001b[0m\n\u001b[1;32m 343\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m object_hook \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m 344\u001b[0m parse_int \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m parse_float \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m 345\u001b[0m parse_constant \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m object_pairs_hook \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m kw):\n\u001b[0;32m--> 346\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_default_decoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 347\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
|
|
"File \u001b[0;32m~/.pyenv/versions/3.9.1/lib/python3.9/json/decoder.py:337\u001b[0m, in \u001b[0;36mJSONDecoder.decode\u001b[0;34m(self, s, _w)\u001b[0m\n\u001b[1;32m 333\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Return the Python representation of ``s`` (a ``str`` instance\u001b[39;00m\n\u001b[1;32m 334\u001b[0m \u001b[38;5;124;03mcontaining a JSON document).\u001b[39;00m\n\u001b[1;32m 335\u001b[0m \n\u001b[1;32m 336\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m--> 337\u001b[0m obj, end \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraw_decode\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_w\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mend\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 338\u001b[0m end \u001b[38;5;241m=\u001b[39m _w(s, end)\u001b[38;5;241m.\u001b[39mend()\n",
|
|
"File \u001b[0;32m~/.pyenv/versions/3.9.1/lib/python3.9/json/decoder.py:353\u001b[0m, in \u001b[0;36mJSONDecoder.raw_decode\u001b[0;34m(self, s, idx)\u001b[0m\n\u001b[1;32m 352\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 353\u001b[0m obj, end \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscan_once\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 354\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
|
|
"\u001b[0;31mJSONDecodeError\u001b[0m: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)",
|
|
"\nDuring handling of the above exception, another exception occurred:\n",
|
|
"\u001b[0;31mOutputParserException\u001b[0m Traceback (most recent call last)",
|
|
"Cell \u001b[0;32mIn[6], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmisformatted\u001b[49m\u001b[43m)\u001b[49m\n",
|
|
"File \u001b[0;32m~/workplace/langchain/langchain/output_parsers/pydantic.py:29\u001b[0m, in \u001b[0;36mPydanticOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m 27\u001b[0m name \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpydantic_object\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\n\u001b[1;32m 28\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFailed to parse \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m from completion \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. Got: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 29\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(msg)\n",
|
|
"\u001b[0;31mOutputParserException\u001b[0m: Failed to parse Actor from completion {'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}. Got: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"parser.parse(misformatted)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "6c7c82b6",
|
|
"metadata": {},
|
|
"source": [
|
|
"Now we can construct and use a `OutputFixingParser`. This output parser takes as an argument another output parser but also an LLM with which to try to correct any formatting mistakes."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "39b1a5ce",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.output_parsers import OutputFixingParser\n",
|
|
"\n",
|
|
"new_parser = OutputFixingParser.from_llm(parser=parser, llm=ChatOpenAI())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "0fd96d68",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"Actor(name='Tom Hanks', film_names=['Forrest Gump'])"
|
|
]
|
|
},
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"new_parser.parse(misformatted)"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.9.1"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|