langchain-polaris

LangChain integration for The Polaris Report — verified news intelligence with confidence scores, bias ratings, and source analysis.

Installation

pip install langchain-polaris

Quick Start

Agent with Tools

from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_polaris import PolarisSearchTool, PolarisBriefTool, PolarisCompareTool

tools = [
    PolarisSearchTool(api_key="pr_live_xxx"),
    PolarisBriefTool(api_key="pr_live_xxx"),
    PolarisCompareTool(api_key="pr_live_xxx"),
]

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

llm = ChatOpenAI(model="gpt-4o")
agent = create_openai_tools_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools)

result = executor.invoke({"input": "What's happening with AI regulation?"})
print(result["output"])

Retriever for RAG

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
from langchain_polaris import PolarisRetriever

retriever = PolarisRetriever(
    api_key="pr_live_xxx",
    category="ai_ml",
    min_confidence=0.7,
    limit=5,
)

prompt = ChatPromptTemplate.from_template(
    "Answer based on these verified news briefs:\n\n{context}\n\nQuestion: {question}"
)

chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | ChatOpenAI(model="gpt-4o")
    | StrOutputParser()
)

print(chain.invoke("What are the latest developments in AI?"))

Tools

Retriever

PolarisRetriever implements LangChain's BaseRetriever interface, returning Document objects with:

• page_content: Headline, summary, and body text
• metadata: brief_id, confidence, bias_score, category, published_at, counter_argument, sources, entities

Retriever Options

Documentation

Full API docs at thepolarisreport.com/docs