Skip to main content

Transformer API Python SDK

Official Python client for the Transformer API — career-graph extraction, job matching, and career intelligence over raw text, with real provenance on every derived fact.

Install

pip install careerstudiomax-transformer

Quickstart

from transformer import TransformerClient

client = TransformerClient(api_key="csk_live_your_key_here")

result = client.extract("Led backend team at Acme, hired by a recruiter for a Senior Engineer role, $145k")
print(result["data"]["entities"])

What you can do

Method Description
client.extract(text) Extract career entities and relationships from raw text
client.career_graph(text=...) Build a knowledge graph, with real provenance on every node/edge
client.career_graph_diff(text_a=..., text_b=...) Structured diff between two career-graph snapshots over time
client.job_match(job_description, candidate_text=...) Score a candidate against a job description
client.job_match_delta(candidate_text_a=..., candidate_text_b=..., job_description_a=...) Why a match score moved between two calls
client.talent_pool_search(target_skills) Search your own tracked candidates for a target skill set
client.team_fit(team_members=..., candidate_skills=...) How a candidate complements an existing team
client.embeddings(texts) Real embedding vectors
client.org_chart_infer(postings) Infer likely reporting structure from job postings you provide
client.trajectory_predict(candidate_text) Common next job titles for a role/seniority level
client.negotiation_leverage(skills, target_role) Negotiation-leverage read plus a counter-offer script
client.skills_freshness(skills) Per-skill current-vs-aging judgment
client.attrition_risk(candidate_text=...) Observable tenure/role-change pattern signal (a weak heuristic, not a behavioral prediction)
client.synthetic_profile(seed=42) Realistic-but-fake candidate profile for prototyping, no key required
client.ontology() The published entity/relationship taxonomy, no key required
client.chat(model, messages) Call an exact model by name
client.chat_stream(on_event, model, messages) Same as chat(), streamed
client.usage() Your key's real usage

Example: career graph + webhook tracking

graph = client.career_graph(text=resume_text, candidate_id="cand-123")
print(graph["data"]["careerScore"])

Webhooks (account access token, not an API key)

hook = client.create_webhook(
    "https://your-app.example.com/hooks/transformer",
    access_token="your_account_access_token",
    candidate_id="cand-123",
)
print(hook["secret"])  # shown once

Errors

from transformer import TransformerClient, TransformerError

try:
    client.job_match("...", candidate_text="...")
except TransformerError as e:
    print(e.status, str(e))

Context manager

with TransformerClient(api_key="...") as client:
    ...

Full endpoint reference: transformer.careerstudiomax.com/docs

Metadata

Release files for careerstudiomax-transformer 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for careerstudiomax-transformer 1.0.0
File Size Uploaded Provenance
careerstudiomax_transformer-1.0.0.tar.gz 7.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for careerstudiomax-transformer 1.0.0
File Interpreter ABI Platform
careerstudiomax_transformer-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 15.1 kB

Release files / careerstudiomax_transformer-1.0.0.tar.gz

Download URL careerstudiomax_transformer-1.0.0.tar.gz
Size 7.2 kB
Tags Source
SHA-256 checksum
How to use checksums
658bc1f3719c3b36cd8cfb454caa828c649f17ad84c61f4402b27bdb06fc91f5
BLAKE2b-256 checksum
How to use checksums
155063c02d150cd039c061ef841322edfcc2273865b82ab3d7f0f1363482cff5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Release files / careerstudiomax_transformer-1.0.0-py3-none-any.whl

Download URL careerstudiomax_transformer-1.0.0-py3-none-any.whl
Size 7.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
4f3663ac933e0612767fa5ed91952f6af57bec49a3b0160dbee8a6393fdcbae5
BLAKE2b-256 checksum
How to use checksums
157adb876d27e7c60602e4b50aca0119501c3ca09f4c2cdb583dac40259da019
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.10

Security for careerstudiomax-transformer 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.

Release history Release notifications | RSS feed

This release

1.0.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page