RunPod Chat Model

import getpass
import os

# Make sure environment variables are set (or pass them directly to ChatRunPod)
if "RUNPOD_API_KEY" not in os.environ:
    os.environ["RUNPOD_API_KEY"] = getpass.getpass("Enter your RunPod API Key: ")

if "RUNPOD_ENDPOINT_ID" not in os.environ:
    os.environ["RUNPOD_ENDPOINT_ID"] = input(
        "Enter your RunPod Endpoint ID (used if RUNPOD_CHAT_ENDPOINT_ID is not set): "
    )

# Optionally use a different endpoint ID specifically for chat models
# if "RUNPOD_CHAT_ENDPOINT_ID" not in os.environ:
#     os.environ["RUNPOD_CHAT_ENDPOINT_ID"] = input("Enter your RunPod Chat Endpoint ID (Optional): ")

chat_endpoint_id = os.environ.get(
    "RUNPOD_CHAT_ENDPOINT_ID", os.environ.get("RUNPOD_ENDPOINT_ID")
)
if not chat_endpoint_id:
    raise ValueError(
        "No RunPod Endpoint ID found. Please set RUNPOD_ENDPOINT_ID or RUNPOD_CHAT_ENDPOINT_ID."
    )

from langchain_runpod import ChatRunPod

chat = ChatRunPod(
    runpod_endpoint_id=chat_endpoint_id,  # Specify the correct endpoint ID
    model_kwargs={
        "max_new_tokens": 512,
        "temperature": 0.7,
        "top_p": 0.9,
        # Add other parameters supported by your endpoint handler
    },
    # Optional: Adjust polling
    # poll_interval=0.2,
    # max_polling_attempts=150
)

from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a helpful AI assistant."),
    HumanMessage(content="What is the RunPod Serverless API flow?"),
]

# Invoke (Sync)
try:
    response = chat.invoke(messages)
    print("--- Sync Invoke Response ---")
    print(response.content)
except Exception as e:
    print(
        f"Error invoking Chat Model: {e}. Ensure endpoint ID/API key are correct and endpoint is active/compatible."
    )

# Stream (Sync, simulated via polling /stream)
print("\n--- Sync Stream Response ---")
try:
    for chunk in chat.stream(messages):
        print(chunk.content, end="", flush=True)
    print()  # Newline
except Exception as e:
    print(
        f"\nError streaming Chat Model: {e}. Ensure endpoint handler supports streaming output format."
    )

### Async Usage

# AInvoke (Async)
try:
    async_response = await chat.ainvoke(messages)
    print("--- Async Invoke Response ---")
    print(async_response.content)
except Exception as e:
    print(f"Error invoking Chat Model asynchronously: {e}.")

# AStream (Async)
print("\n--- Async Stream Response ---")
try:
    async for chunk in chat.astream(messages):
        print(chunk.content, end="", flush=True)
    print()  # Newline
except Exception as e:
    print(
        f"\nError streaming Chat Model asynchronously: {e}. Ensure endpoint handler supports streaming output format.\n"
    )

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "You are a helpful assistant."),
        ("human", "{input}"),
    ]
)

parser = StrOutputParser()

chain = prompt | chat | parser

try:
    chain_response = chain.invoke(
        {"input": "Explain the concept of serverless computing in simple terms."}
    )
    print("--- Chain Response ---")
    print(chain_response)
except Exception as e:
    print(f"Error running chain: {e}")


# Async chain
try:
    async_chain_response = await chain.ainvoke(
        {"input": "What are the benefits of using RunPod for AI/ML workloads?"}
    )
    print("--- Async Chain Response ---")
    print(async_chain_response)
except Exception as e:
    print(f"Error running async chain: {e}")