Personalizzare la logica delle chain
Scopra come costruire chain personalizzate e integrare le proprie funzioni e la propria logica Python nei workflow LangChain.
Personalizzare la logica delle chain è una lezione AI Agents with LangChain & Autonomous Workflows gratuita su CoddyKit. Questa è la lezione 3 di 4. Puoi leggere la lezione completa qui gratuitamente — poi esercitati direttamente nel browser con un editor di codice integrato e un tutor IA disponibile 24/7. Fa parte del percorso di apprendimento AI Agents with LangChain & Autonomous Workflows, e i tuoi progressi si sincronizzano tra il web e l'app CoddyKit. Il corso AI Agents with LangChain & Autonomous Workflows include 4 lezioni in totale.
Parti di questa lezione non sono ancora state tradotte e vengono mostrate in inglese.
Beyond Standard Chains
In previous lessons, you learned how to create sequential chains to perform multi-step operations. These chains are powerful for connecting standard LangChain components like prompts and LLMs.
But what if you need to do something unique? What if you need to process data in a specific way before it reaches your LLM, or format its output afterward?
When to Add Custom Steps
Standard chains are great, but they can't handle every scenario. Custom logic allows you to:
- Pre-process inputs: Clean, validate, or transform user input before sending it to a prompt or LLM.
- Post-process outputs: Parse, filter, or reformat LLM responses for display or further use.
- Integrate external logic: Call your own Python functions, external APIs, or apply conditional routing.
- Handle complex data transformations: Convert data types, merge information, or apply business rules.
Introducing RunnableLambda
LangChain's RunnableLambda is your key to integrating custom Python functions into chains. It wraps any Python callable (like a function or a lambda expression) and makes it behave like a LangChain Runnable component.
This means you can seamlessly insert your own Python logic anywhere in a chain, just like you would an LLM or a prompt template!
Your First Custom Function
Let's start with a simple custom function that adds an exclamation mark to a string. We'll wrap it with RunnableLambda to make it part of a chain.
Try running this basic example:
from langchain_core.runnables import RunnableLambda
def add_exclamation(text: str) -> str:
return text + "!"
if __name__ == "__main__":
# Wrap your function to make it a Runnable
custom_step = RunnableLambda(add_exclamation)
# Invoke it like any other Runnable
result = custom_step.invoke("Hello CoddyKit")
print(result)Chaining Custom Logic
The real power comes when you combine RunnableLambda with other LangChain components. You can place your custom logic at the beginning, middle, or end of a chain.
For example, you might have a custom function that prepares the input for a prompt, or one that processes the output from an LLM.
Custom Pre-processing Chain
Here's an example where a custom step pre-processes the input by converting it to uppercase before it's passed to a PromptTemplate and then to a simulated LLM.
Notice how the `uppercase_input` function expects a dictionary, mirroring how chain inputs often work.
from langchain_core.prompts import PromptTemplate
from langchain_core.runnables import RunnableLambda
from langchain_community.llms import FakeListLLM
def uppercase_input(data: dict) -> dict:
# Ensure 'text' key exists and convert its value to uppercase
return {"text": data.get("text", "").upper()}
if __name__ == "__main__":
# A simulated LLM for demonstration
llm = FakeListLLM(responses=["I received your uppercase text!"])
# Define a simple prompt template
prompt = PromptTemplate.from_template(
"You mentioned: {text}. What do you think?"
)
# Create the custom pre-processing step
pre_process_step = RunnableLambda(uppercase_input)
# Build the chain: custom_step -> prompt -> llm
custom_chain = pre_process_step | prompt | llm
# Invoke the chain with lowercase input
input_data = {"text": "hello world"}
response = custom_chain.invoke(input_data)
print(response)Custom Post-processing Logic
Just as you can pre-process inputs, you can also post-process the outputs from an LLM. This is useful for:
- Extracting specific information from a longer response.
- Formatting the output for display in a UI.
- Converting the output to a different data structure (e.g., JSON).
- Adding a custom header or footer to the LLM's message.
Example: Custom Output Formatting
Let's create a custom function that takes the raw LLM response and wraps it with a friendly message. This makes the output more user-friendly.
Run this example to see the LLM's response being transformed:
from langchain_core.runnables import RunnableLambda
from langchain_community.llms import FakeListLLM
def format_llm_output(llm_response: str) -> str:
# Add a custom prefix and suffix to the LLM's message
return f"🤖 AI says: '{llm_response.strip()}' - Over and out!"
if __name__ == "__main__":
# A simulated LLM for demonstration
llm = FakeListLLM(responses=["The weather is sunny today."])
# Create the custom post-processing step
post_process_step = RunnableLambda(format_llm_output)
# Build the chain: llm -> custom_step
custom_chain = llm | post_process_step
# Invoke the chain (input doesn't affect FakeListLLM's response here)
response = custom_chain.invoke("What's the weather like?")
print(response)Adding Conditional Logic
RunnableLambda isn't just for simple transformations. You can embed complex Python logic, including conditionals, loops, and even calls to other services, directly into your chain.
For instance, you could have a custom step that checks if an input meets certain criteria and, if not, redirects the flow or returns a default message, creating dynamic and intelligent workflows.
Quick Check: Custom Chain Steps
Which of the following are good use cases for integrating custom Python logic (e.g., using RunnableLambda) into a LangChain workflow?
Recap & Next Steps
You've learned how to inject your own Python functions and logic into LangChain workflows using RunnableLambda. This powerful feature allows you to:
- Perform custom pre-processing on inputs.
- Apply custom post-processing to LLM outputs.
- Integrate complex or conditional logic within your chains.
By mastering custom chain logic, you gain immense flexibility to tailor LangChain to your exact needs, building truly unique and intelligent applications. Next, explore how to use pre-built toolkits to add even more capabilities to your agents!
Domande Frequenti
La lezione «Personalizzare la logica delle chain» è gratuita?
Sì — il testo completo di «Personalizzare la logica delle chain» è gratuito qui sul web. Per esercitarvi in modo interattivo (un editor di codice integrato e un tutor IA 24/7) e sbloccare il resto del corso AI Agents with LangChain & Autonomous Workflows, passa a CoddyKit PRO. Il corso AI Agents with LangChain & Autonomous Workflows include 4 lezioni in totale.
Cosa imparerò in «Personalizzare la logica delle chain»?
Scopra come costruire chain personalizzate e integrare le proprie funzioni e la propria logica Python nei workflow LangChain. Eserciti AI Agents with LangChain & Autonomous Workflows con codice pratico che esegui direttamente nel browser, e un tutor IA 24/7 risponde alle tue domande mentre lavori sulla lezione.
Ho bisogno di esperienza per iniziare AI Agents with LangChain & Autonomous Workflows?
Non è richiesta alcuna esperienza precedente. AI Agents with LangChain & Autonomous Workflows su CoddyKit è strutturato per principianti e studenti avanzati, quindi puoi iniziare da qui o dall'inizio e procedere al tuo ritmo. Questa è la lezione 3 di 4.
Quanto tempo richiede la lezione «Personalizzare la logica delle chain»?
La maggior parte delle lezioni CoddyKit richiede circa 5–10 minuti. Ogni lezione è breve e interattiva, quindi fai progressi costanti e riprendi esattamente da dove hai lasciato su web e app.
Posso scrivere ed eseguire codice in questa lezione AI Agents with LangChain & Autonomous Workflows?
Sì. Ogni lezione AI Agents with LangChain & Autonomous Workflows include un editor di codice integrato, quindi scrivi ed esegui codice reale direttamente nel tuo browser e ricevi feedback istantaneo dall'IA — nessuna configurazione locale necessaria.
Tutte le lezioni di questo corso
- Introduzione alle chain di LangChain
- Chain sequenziali e semplici
- Personalizzare la logica delle chain
- Routing e chain condizionali