Horizon Data Wave Tools
Project description
🔎 Horizon Data Wave Tools
Horizon Data Wave Tools is a library designed for seamless integration with llamaindex and crewai.
This library provides robust tools and endpoints to fetch data directly from LinkedIn via the HorizonDataWave data provider. With hdw_tools, you can simplify and automate the process of integrating LinkedIn data queries into projects that utilize llamaindex or crewai.
Python Version Requirement
HDW tools requires Python 3.12 or higher.
Installation
Install using pip:
pip install hdw_tools
Environment Variables
To use this project, you need to set the following environment variables:
HDW_API_KEY: The API key required for authentication. You can obtain this key by visiting Horizon Data Wave.
Make sure to add these variables to your environment configuration before running the project.
Examples
Using with LlamaIndex
from hdw_tools.tools.llama_linkedin import LinkedInToolSpec
from llama_index.agent.openai import OpenAIAgent
from llama_index.llms.openai import OpenAI
agent = OpenAIAgent.from_tools(
[tool for sublist in [LinkedInToolSpec().to_tool_list()] for tool in sublist],
llm=OpenAI(model="gpt-4", temperature=0.1),
verbose=True,
system_prompt="You are an AI assistant helping users with LinkedIn searches",
)
Using with CrewAI
from crewai import Task
from hdw_tools.tools import crewai_linkedin
find_user_data = Task(
description=(
"Analyze {user_request}. Define provided data and tasks. Create plan to use existing tools to find information "
"in requred sources based on provided information and tasks. And execute this plan."
),
expected_output="Provide results in markdown format.",
tools=[
crewai_linkedin.GetLinkedInCompany(),
crewai_linkedin.GetLinkedInUser(),
crewai_linkedin.GetLinkedInPost()
]
)
License
This project is licensed under the MIT License. See the LICENSE file for more information.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hdw_tools-0.0.6.tar.gz.
File metadata
- Download URL: hdw_tools-0.0.6.tar.gz
- Upload date:
- Size: 13.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
13e5c0c7a853eb60b7252f7166f81673d888647caa551aa5956d7efd823728fc
|
|
| MD5 |
adf111e126c1628fe77f3b529ebbaeb7
|
|
| BLAKE2b-256 |
97cc42c91f247ab4f950172ff312e34044698d364405f64c05ca9ff302d02250
|
File details
Details for the file hdw_tools-0.0.6-py3-none-any.whl.
File metadata
- Download URL: hdw_tools-0.0.6-py3-none-any.whl
- Upload date:
- Size: 12.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
61ad26da9f641e1c5f6659770ff6cb6aeee05f45d7e0d6171bf41cfd0bfe7928
|
|
| MD5 |
9bb574c112be95c0cf36411a4084c764
|
|
| BLAKE2b-256 |
8c0be5b9a133a0b1ff5d9af762d582549c40918784fd57a48803b0951e28d642
|