LangChain

Overview

AI Sonar works well with LangChain’s ChatOpenAI and OpenAIEmbeddings integrations when you stay on the standard OpenAI-compatible chat and embeddings surface. This page intentionally covers the standard OpenAI-compatible LangChain surface, not provider-native LangChain features beyond that surface.

Current LangChain docs note that ChatOpenAI targets official OpenAI-compatible request/response shapes. If you need provider-specific, non-standard response fields, use a provider-specific LangChain integration instead of relying on ChatOpenAI.

Type: Framework or PlatformPrimary Path: OpenAI-compatible standard surfaceSupport Confidence: Supported standard surface

Installation

pip install langchain langchain-openai langchain-community faiss-cpu

Basic Configuration

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-5.4",
    api_key="sk-your-api-key",
    base_url="https://api.aisonar.dev/v1",
)

response = llm.invoke("Explain AI Sonar in one sentence.")
print(response.content)

Using Different Models

from langchain_openai import ChatOpenAI

gpt = ChatOpenAI(
    model="gpt-5.4",
    api_key="sk-your-key",
    base_url="https://api.aisonar.dev/v1",
)

claude = ChatOpenAI(
    model="claude-sonnet-4-6",
    api_key="sk-your-key",
    base_url="https://api.aisonar.dev/v1",
)

gemini = ChatOpenAI(
    model="gemini-3.5-flash",
    api_key="sk-your-key",
    base_url="https://api.aisonar.dev/v1",
)

deepseek = ChatOpenAI(
    model="deepseek-r1",
    api_key="sk-your-key",
    base_url="https://api.aisonar.dev/v1",
)

Message History

from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a helpful assistant."),
    HumanMessage(content="What is the capital of France?")
]

response = llm.invoke(messages)
print(response.content)

Streaming

for chunk in llm.stream("Write a short poem about coding."):
    if chunk.content:
        print(chunk.content, end="", flush=True)

Embeddings

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-small",
    api_key="sk-your-key",
    base_url="https://api.aisonar.dev/v1",
)

vector = embeddings.embed_query("Hello world")
print(vector[:5])

Simple RAG Example

from langchain_openai import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-small",
    api_key="sk-your-key",
    base_url="https://api.aisonar.dev/v1",
)

texts = [
    "AI Sonar provides one API for many AI models.",
    "AI Sonar supports OpenAI-compatible integrations."
]

vectorstore = FAISS.from_texts(texts, embeddings)
retriever = vectorstore.as_retriever()

prompt = ChatPromptTemplate.from_template(
    "Answer using the context below.\\n\\nContext:\\n{context}\\n\\nQuestion:\\n{question}"
)

rag_chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | llm
)

response = rag_chain.invoke("What does AI Sonar provide?")
print(response.content)

Agents

For new agentic projects, LangChain recommends considering LangGraph for more explicit control over long-running and tool-using workflows.

from langchain.agents import create_openai_tools_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.tools import tool

@tool
def search(query: str) -> str:
    """Search for information."""
    return f"Search results for: {query}"

tools = [search]

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant with access to tools."),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}")
])

agent = create_openai_tools_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools)

result = executor.invoke({"input": "Search for AI Sonar pricing"})
print(result["output"])

Best Practices

Pass base_url explicitly

The most reliable AI Sonar setup is to pass base_url="https://api.aisonar.dev/v1" directly to ChatOpenAI and OpenAIEmbeddings instead of depending on older environment-variable aliases.

Use standard features here

Stick to standard chat, tool calling, streaming, and embeddings on ChatOpenAI. If you need vendor-native extras, switch to the vendor’s own LangChain integration.

Use cheaper models for retrieval

Use embedding models like text-embedding-3-small for retrieval and reserve stronger chat models for the final answer step.

Compatibility Matrix

Coding Tools

Native SDKs

Frameworks & Platforms

Chat Apps

Overview

Installation

Basic Configuration

Using Different Models

Message History

Streaming

Embeddings

Simple RAG Example

Agents

Best Practices

​Overview

​Installation

​Basic Configuration

​Using Different Models

​Message History

​Streaming

​Embeddings

​Simple RAG Example

​Agents

​Best Practices

Overview

Installation

Basic Configuration

Using Different Models

Message History

Streaming

Embeddings

Simple RAG Example

Agents

Best Practices