LangChain Core Package

Install and use the `langchain-core` Python package to build LLM applications with composable, modular abstractions.

What This Skill Does

This skill helps you install and work with `langchain-core`, the foundational package of the LangChain ecosystem. It provides base abstractions for prompts, language models, output parsers, runnables, and chains that enable building complex LLM applications through composability.

When to Use This Skill

Instructions

1. Install langchain-core

First, install the package in your Python environment:

```bash

pip install langchain-core

```

For a specific version:

```bash

pip install langchain-core==1.2.7

```

2. Understand Core Abstractions

LangChain Core provides these key abstractions:

3. Import and Use Core Components

Import the base classes you need:

```python

from langchain_core.prompts import PromptTemplate, ChatPromptTemplate

from langchain_core.output_parsers import StrOutputParser, JsonOutputParser

from langchain_core.runnables import RunnablePassthrough, RunnableSequence

from langchain_core.messages import HumanMessage, SystemMessage, AIMessage

```

4. Build Composable Chains

Use the pipe operator to compose runnables:

```python

from langchain_core.prompts import ChatPromptTemplate

from langchain_core.output_parsers import StrOutputParser

prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}")

Assume you have a model instance

chain = prompt | model | StrOutputParser()

result = chain.invoke({"topic": "programming"})

```

5. Work with Messages

Structure conversational interactions:

```python

from langchain_core.messages import HumanMessage, SystemMessage

messages = [

SystemMessage(content="You are a helpful assistant."),

HumanMessage(content="What is LangChain?")

]

```

6. Create Custom Components

Extend base classes to create custom components:

```python

from langchain_core.output_parsers import BaseOutputParser

class CustomParser(BaseOutputParser):

def parse(self, text: str):

# Your custom parsing logic

return text.strip().upper()

```

7. Use with LangSmith (Optional)

For production monitoring and testing:

Key Benefits

Documentation References

Common Patterns

**Simple chain with prompt and parser:**

```python

chain = prompt_template | model | output_parser

result = chain.invoke(input_data)

```

**Parallel execution:**

```python

from langchain_core.runnables import RunnableParallel

parallel = RunnableParallel(

summary=summarize_chain,

translation=translate_chain

)

```

**Conditional routing:**

```python

from langchain_core.runnables import RunnableBranch

branch = RunnableBranch(

(condition1, chain1),

(condition2, chain2),

default_chain

)

```

Notes