LangChain

pip install langchain-parallel

export PARALLEL_API_KEY="your-api-key-here"

from langchain_parallel import ParallelWebSearchTool

# Initialize the search tool
search_tool = ParallelWebSearchTool()

# Search with queries and an objective
result = search_tool.invoke({
    "search_queries": [
        "renewable energy technology developments 2026",
        "renewable energy policy updates 2026"
    ],
    "objective": "What are the latest developments in renewable energy?",
    "mode": "advanced"
})

print(result)
# {
#     "search_id": "search_123...",
#     "results": [
#         {
#             "url": "https://example.com/renewable-energy",
#             "title": "Latest Renewable Energy Developments",
#             "excerpts": [
#                 "Solar energy has seen remarkable growth...",
#                 "Wind power capacity increased by 15%..."
#             ]
#         }
#     ]
# }

# Search with specific queries
result = search_tool.invoke({
    "search_queries": [
        "renewable energy 2024",
        "solar power developments",
        "wind energy statistics"
    ],
    "mode": "advanced"
})

from langchain.agents import create_openai_functions_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

# Bring your own LLM
llm = ChatOpenAI(model="gpt-6-astra")

# Create agent with search capabilities
tools = [search_tool]

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a research assistant. Use the search tool to find current information."),
    ("human", "{input}"),
    ("placeholder", "{agent_scratchpad}"),
])

agent = create_openai_functions_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

# Run the agent
result = agent_executor.invoke({
    "input": "What are the latest developments in artificial intelligence?"
})
print(result["output"])

from langchain_parallel import ParallelExtractTool

# Initialize the extract tool
extract_tool = ParallelExtractTool()

# Extract from a single URL
result = extract_tool.invoke({
    "urls": ["https://en.wikipedia.org/wiki/Artificial_intelligence"]
})

print(result)
# [
#     {
#         "url": "https://en.wikipedia.org/wiki/Artificial_intelligence",
#         "title": "Artificial intelligence - Wikipedia",
#         "content": "# Artificial intelligence\n\nMain content in markdown...",
#         "publish_date": "2024-01-15"  # Optional
#     }
# ]

# Extract content focused on a specific objective with excerpt settings
result = extract_tool.invoke({
    "urls": ["https://en.wikipedia.org/wiki/Artificial_intelligence"],
    "search_objective": "What are the main applications and ethical concerns of AI?",
    "excerpts": {"max_chars_per_result": 2000},
    "full_content": False,
    "fetch_policy": {
        "max_age_seconds": 86400,
        "timeout_seconds": 60,
        "disable_cache_fallback": False
    }
})

# Returns relevant excerpts focused on the objective
print(result[0]["excerpts"])  # List of relevant text excerpts

# Extract content focused on specific queries
result = extract_tool.invoke({
    "urls": [
        "https://en.wikipedia.org/wiki/Machine_learning",
        "https://en.wikipedia.org/wiki/Deep_learning"
    ],
    "search_queries": ["neural networks", "training algorithms", "applications"],
    "excerpts": True
})

for item in result:
    print(f"Title: {item['title']}")
    print(f"Relevant excerpts: {len(item['excerpts'])}")
    print()

# Control full content length per extraction
result = extract_tool.invoke({
    "urls": ["https://en.wikipedia.org/wiki/Quantum_computing"],
    "full_content": {"max_chars_per_result": 3000}
})

print(f"Content length: {len(result[0]['content'])} characters")

# Mix of valid and invalid URLs
result = extract_tool.invoke({
    "urls": [
        "https://en.wikipedia.org/wiki/Python_(programming_language)",
        "https://this-domain-does-not-exist-12345.com/"
    ]
})

for item in result:
    if "error_type" in item:
        print(f"Failed: {item['url']} - {item['content']}")
    else:
        print(f"Success: {item['url']} - {len(item['content'])} chars")

import asyncio

async def extract_async():
    result = await extract_tool.ainvoke({
        "urls": ["https://en.wikipedia.org/wiki/Artificial_intelligence"]
    })
    return result

# Run async extraction
result = asyncio.run(extract_async())

try:
    result = search_tool.invoke({
        "search_queries": ["renewable energy 2026"],
        "mode": "advanced",
    })
    print(result)
except ValueError as e:
    if "API key not found" in str(e):
        print("Please set your PARALLEL_API_KEY environment variable")
    else:
        print(f"API Error: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")