github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-06-09 10:17:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

style(core): more cleanup all around (#33711)

Browse Source
This commit is contained in:
Mason Daugherty
2025-10-28 22:58:19 -04:00
committed by GitHub
parent e5e1d6c705
commit a2a9a02ecb
12 changed files with 121 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
libs/core/langchain_core/prompts/chat.py
View File

@@ -776,42 +776,41 @@ class ChatPromptTemplate(BaseChatPromptTemplate):
Use to create flexible templated prompts for chat models.
Examples:
!!! warning "Behavior changed in 0.2.24"
You can pass any Message-like formats supported by
`ChatPromptTemplate.from_messages()` directly to `ChatPromptTemplate()`
init.
!!! warning "Behavior changed in 0.2.24"
You can pass any Message-like formats supported by
`ChatPromptTemplate.from_messages()` directly to `ChatPromptTemplate()`
init.
```python
from langchain_core.prompts import ChatPromptTemplate
```python
from langchain_core.prompts import ChatPromptTemplate
template = ChatPromptTemplate(
[
("system", "You are a helpful AI bot. Your name is {name}."),
("human", "Hello, how are you doing?"),
("ai", "I'm doing well, thanks!"),
("human", "{user_input}"),
]
)
template = ChatPromptTemplate(
[
("system", "You are a helpful AI bot. Your name is {name}."),
("human", "Hello, how are you doing?"),
("ai", "I'm doing well, thanks!"),
("human", "{user_input}"),
]
)
prompt_value = template.invoke(
{
"name": "Bob",
"user_input": "What is your name?",
}
)
# Output:
# ChatPromptValue(
# messages=[
# SystemMessage(content='You are a helpful AI bot. Your name is Bob.'),
# HumanMessage(content='Hello, how are you doing?'),
# AIMessage(content="I'm doing well, thanks!"),
# HumanMessage(content='What is your name?')
# ]
# )
```
prompt_value = template.invoke(
{
"name": "Bob",
"user_input": "What is your name?",
}
)
# Output:
# ChatPromptValue(
# messages=[
# SystemMessage(content='You are a helpful AI bot. Your name is Bob.'),
# HumanMessage(content='Hello, how are you doing?'),
# AIMessage(content="I'm doing well, thanks!"),
# HumanMessage(content='What is your name?')
# ]
# )
```
Messages Placeholder:
!!! note "Messages Placeholder"
```python
# In addition to Human/AI/Tool/Function messages,
@@ -852,13 +851,12 @@ class ChatPromptTemplate(BaseChatPromptTemplate):
# )
```
Single-variable template:
!!! note "Single-variable template"
If your prompt has only a single input variable (i.e., 1 instance of "{variable_nams}"),
and you invoke the template with a non-dict object, the prompt template will
inject the provided argument into that variable location.
```python
from langchain_core.prompts import ChatPromptTemplate