github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-28 17:38:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

OpenAI function calling docstring and notebook imports (#10663)

Browse Source 
This PR is a documentation fix.

Description:
* fixes imports in the code samples in the docstrings of
`create_openai_fn_chain` and `create_structured_output_chain`
* fixes imports in
`docs/extras/modules/chains/how_to/openai_functions.ipynb`
* removes unused imports from the notebook

Issues:
* the docstrings use `from pydantic_v1 import BaseModel, Field` which
this PR changes to `from langchain.pydantic_v1 import BaseModel, Field`
* importing `pydantic` instead of `langchain.pydantic_v1` leads to
errors later in the notebook
This commit is contained in:
Joshua Sundance Bailey 2023-09-16 17:24:50 -04:00 committed by GitHub
parent 6f36bc6d38
commit c4e591a57d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 32 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
docs/extras/modules/chains/how_to/openai_functions.ipynb
View File

@ -26,8 +26,7 @@
" create_structured_output_chain,\n", " create_structured_output_chain,\n",
")\n", ")\n",
"from langchain.chat_models import ChatOpenAI\n", "from langchain.chat_models import ChatOpenAI\n",
"from langchain.prompts import ChatPromptTemplate, HumanMessagePromptTemplate\n", "from langchain.prompts import ChatPromptTemplate"
"from langchain.schema import HumanMessage, SystemMessage"
] ]
}, },
{ {
@ -57,7 +56,7 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"from pydantic import BaseModel, Field\n", "from langchain.pydantic_v1 import BaseModel, Field\n",
"\n", "\n",
"\n", "\n",
"class Person(BaseModel):\n", "class Person(BaseModel):\n",
@ -80,13 +79,13 @@
"text": [ "text": [
"\n", "\n",
"\n", "\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n", "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n", "Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mSystem: You are a world class algorithm for extracting information in structured formats.\n", "\u001B[32;1m\u001B[1;3mSystem: You are a world class algorithm for extracting information in structured formats.\n",
"Human: Use the given format to extract information from the following input: Sally is 13\n", "Human: Use the given format to extract information from the following input: Sally is 13\n",
"Human: Tip: Make sure to answer in the correct format\u001b[0m\n", "Human: Tip: Make sure to answer in the correct format\u001B[0m\n",
"\n", "\n",
"\u001b[1m> Finished chain.\u001b[0m\n" "\u001B[1m> Finished chain.\u001B[0m\n"
] ]
}, },
{ {
@ -135,13 +134,13 @@
"text": [ "text": [
"\n", "\n",
"\n", "\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n", "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n", "Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mSystem: You are a world class algorithm for extracting information in structured formats.\n", "\u001B[32;1m\u001B[1;3mSystem: You are a world class algorithm for extracting information in structured formats.\n",
"Human: Use the given format to extract information from the following input: Sally is 13, Joey just turned 12 and loves spinach. Caroline is 10 years older than Sally.\n", "Human: Use the given format to extract information from the following input: Sally is 13, Joey just turned 12 and loves spinach. Caroline is 10 years older than Sally.\n",
"Human: Tip: Make sure to answer in the correct format\u001b[0m\n", "Human: Tip: Make sure to answer in the correct format\u001B[0m\n",
"\n", "\n",
"\u001b[1m> Finished chain.\u001b[0m\n" "\u001B[1m> Finished chain.\u001B[0m\n"
] ]
}, },
{ {
@ -217,13 +216,13 @@
"text": [ "text": [
"\n", "\n",
"\n", "\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n", "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n", "Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mSystem: You are a world class algorithm for extracting information in structured formats.\n", "\u001B[32;1m\u001B[1;3mSystem: You are a world class algorithm for extracting information in structured formats.\n",
"Human: Use the given format to extract information from the following input: Sally is 13\n", "Human: Use the given format to extract information from the following input: Sally is 13\n",
"Human: Tip: Make sure to answer in the correct format\u001b[0m\n", "Human: Tip: Make sure to answer in the correct format\u001B[0m\n",
"\n", "\n",
"\u001b[1m> Finished chain.\u001b[0m\n" "\u001B[1m> Finished chain.\u001B[0m\n"
] ]
}, },
{ {
@ -301,13 +300,13 @@
"text": [ "text": [
"\n", "\n",
"\n", "\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n", "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n", "Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mSystem: You are a world class algorithm for recording entities.\n", "\u001B[32;1m\u001B[1;3mSystem: You are a world class algorithm for recording entities.\n",
"Human: Make calls to the relevant function to record the entities in the following input: Harry was a chubby brown beagle who loved chicken\n", "Human: Make calls to the relevant function to record the entities in the following input: Harry was a chubby brown beagle who loved chicken\n",
"Human: Tip: Make sure to answer in the correct format\u001b[0m\n", "Human: Tip: Make sure to answer in the correct format\u001B[0m\n",
"\n", "\n",
"\u001b[1m> Finished chain.\u001b[0m\n" "\u001B[1m> Finished chain.\u001B[0m\n"
] ]
}, },
{ {
@ -357,13 +356,13 @@
"text": [ "text": [
"\n", "\n",
"\n", "\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n", "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n", "Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mSystem: You are a world class algorithm for recording entities.\n", "\u001B[32;1m\u001B[1;3mSystem: You are a world class algorithm for recording entities.\n",
"Human: Make calls to the relevant function to record the entities in the following input: The most important thing to remember about Tommy, my 12 year old, is that he'll do anything for apple pie.\n", "Human: Make calls to the relevant function to record the entities in the following input: The most important thing to remember about Tommy, my 12 year old, is that he'll do anything for apple pie.\n",
"Human: Tip: Make sure to answer in the correct format\u001b[0m\n", "Human: Tip: Make sure to answer in the correct format\u001B[0m\n",
"\n", "\n",
"\u001b[1m> Finished chain.\u001b[0m\n" "\u001B[1m> Finished chain.\u001B[0m\n"
] ]
}, },
{ {
@ -427,13 +426,13 @@
"text": [ "text": [
"\n", "\n",
"\n", "\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n", "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n", "Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mSystem: You are a world class algorithm for recording entities.\n", "\u001B[32;1m\u001B[1;3mSystem: You are a world class algorithm for recording entities.\n",
"Human: Make calls to the relevant function to record the entities in the following input: I can't find my dog Henry anywhere, he's a small brown beagle. Could you send a message about him?\n", "Human: Make calls to the relevant function to record the entities in the following input: I can't find my dog Henry anywhere, he's a small brown beagle. Could you send a message about him?\n",
"Human: Tip: Make sure to answer in the correct format\u001b[0m\n", "Human: Tip: Make sure to answer in the correct format\u001B[0m\n",
"\n", "\n",
"\u001b[1m> Finished chain.\u001b[0m\n" "\u001B[1m> Finished chain.\u001B[0m\n"
] ]
}, },
{ {

8
libs/langchain/langchain/chains/openai_functions/base.py
View File

@ -220,11 +220,13 @@ def create_openai_fn_chain(
Example: Example:
.. code-block:: python .. code-block:: python
from typing import Optional
from langchain.chains.openai_functions import create_openai_fn_chain from langchain.chains.openai_functions import create_openai_fn_chain
from langchain.chat_models import ChatOpenAI from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate from langchain.prompts import ChatPromptTemplate
from pydantic_v1 import BaseModel, Field from langchain.pydantic_v1 import BaseModel, Field
class RecordPerson(BaseModel): class RecordPerson(BaseModel):
@ -306,11 +308,13 @@ def create_structured_output_chain(
Example: Example:
.. code-block:: python .. code-block:: python
from typing import Optional
from langchain.chains.openai_functions import create_structured_output_chain from langchain.chains.openai_functions import create_structured_output_chain
from langchain.chat_models import ChatOpenAI from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate from langchain.prompts import ChatPromptTemplate
from pydantic_v1 import BaseModel, Field from langchain.pydantic_v1 import BaseModel, Field
class Dog(BaseModel): class Dog(BaseModel):
\"\"\"Identifying information about a dog.\"\"\" \"\"\"Identifying information about a dog.\"\"\"