Structured Resume Data for LlamaIndex
Stop writing custom chunking strategies for messy resume PDFs. The HireSquire ToolSpec gives your LlamaIndex agents the power to perfectly parse, score, and query candidate data.
from llama_hub.tools.hiresquire import HireSquireToolSpecSolving the RAG Resume Problem
Structured Extraction
Resumes are incredibly messy data sources. HireSquire standardizes them before they ever reach your vector database, turning unstructured text into clean JSON profiles.
High-Reasoning Models
A standard text-embedding model can't easily tell the difference between "Java" and "JavaScript". HireSquire uses high-reasoning GPT models to perform accurate, semantic screening.
Idempotent Processing
RAG pipelines often retry or loop during execution. Our API supports Idempotency-Key headers, ensuring you never pay twice if your LlamaIndex agent repeats a tool call.
LlamaIndex Integration
Connect HireSquire directly to your LlamaIndex workflow. Query your local candidate documents and let HireSquire provide the final analysis and matching score.
Read the LlamaHub Documentationfrom llama_hub.tools.hiresquire import HireSquireToolSpec
from llama_index.agent import OpenAIAgent
# Initialize the ToolSpec
tool_spec = HireSquireToolSpec(api_key="hs_your_agent_key")
agent = OpenAIAgent.from_tools(tool_spec.to_tool_list())
# Query your agent
response = agent.chat(
"Evaluate the resumes in ./data against our "
"Senior DevOps role. Return only candidates "
"scoring above 85."
)
print(response)