llama-index-tools-opticparse
Official LlamaIndex BaseToolSpec integration for OpticParse Multimodal Vision Web Scraper and PhishVision Zero-Day Cybersecurity & Drainer Detection.
Empower your autonomous LlamaIndex agents, RAG workflows, and retrieval pipelines with stealth, anti-bot resilient web extraction and real-time security scanning.
Installation
pip install llama-index-tools-opticparse
Quickstart
1. Zero-CSS Autonomous Web Extraction
Equip your LlamaIndex Agent to scrape live websites without worrying about dynamic JavaScript, Cloudflare challenges, or brittle CSS selectors:
import os
from llama_index.tools.opticparse import OpticParseToolSpec
from llama_index.core.agent import FunctionCallingAgentWorker
# Initialize tool spec
tool_spec = OpticParseToolSpec(
api_key=os.getenv("OPTICPARSE_API_KEY", "op_live_demo_agent")
)
# Convert to LlamaIndex tool list
tools = tool_spec.to_tool_list()
# Attach tools directly to your LlamaIndex Agent
# agent = FunctionCallingAgentWorker.from_tools(tools, llm=llm).as_agent()
# response = agent.chat("Scrape the latest pricing and specs from https://news.ycombinator.com")
# print(response)
2. Standalone Tool Execution
You can also run tool operations directly as standard Python methods:
from llama_index.tools.opticparse import OpticParseToolSpec
tool_spec = OpticParseToolSpec()
# Extract structured content
docs = tool_spec.extract(
url="https://example.com",
query="Extract product details and main headers"
)
print("Extracted content:", docs[0].text)
# Inspect unknown URLs for zero-day phishing or wallet drainers
threat_docs = tool_spec.inspect_threat(
url="https://suspicious-crypto-portal.xyz"
)
print("Threat analysis:", threat_docs[0].text)
Tool Functions Exposed
| Function | Description | Return Type |
|---|---|---|
extract(url, query) |
Visual web scraper with anti-bot evasion & structured parsing. | List[Document] |
inspect_threat(url) |
Real-time zero-day cybersecurity & Web3 wallet-drainer scanner. | List[Document] |
Supported Ecosystems
- LlamaIndex Agents:
FunctionCallingAgent,OpenAIAgent,ReActAgent - LangChain: Use
langchain-opticparse - Model Context Protocol (MCP): Native integration on Smithery & Glama
- Coinbase AgentKit: On-chain autonomous agent action provider
License
MIT License. Maintained by OpticParse Enterprise.
Metadata
Release files for llama-index-tools-opticparse 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| llama_index_tools_opticparse-1.0.0.tar.gz | 4.6 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llama_index_tools_opticparse-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.8 kB
Release files / llama_index_tools_opticparse-1.0.0.tar.gz
| Download URL | llama_index_tools_opticparse-1.0.0.tar.gz |
|---|---|
| Size | 4.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b80f36a8cbf23607f1cab913f07efb401d2f24e5e2c31ad1c563a55d0ab35d41
|
|
BLAKE2b-256 checksum How to use checksums |
7f8bccd101fa86ca5734b24a274cca405080883973b77cd31ca489b4485aedfa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Release files / llama_index_tools_opticparse-1.0.0-py3-none-any.whl
| Download URL | llama_index_tools_opticparse-1.0.0-py3-none-any.whl |
|---|---|
| Size | 5.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2904a12cc93da61c8643e3c76d4fb8bbb78847da287a44c971c0b8e1bf11baff
|
|
BLAKE2b-256 checksum How to use checksums |
e82699a5bfa082618e0fc087e72e0e332ba9717b1a40cbae03a2f63fdbf003a4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Security for llama-index-tools-opticparse 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.