fintom8

LiteLLM connector for Gemini / Vertex AI / OpenAI / Azure. Chat, stream, and document extract. Students install with pip and call a few methods — keys stay in .env.

pip install fintom8

from fintom8 import LLM

llm = LLM()  # reads .env / environment
print(llm.chat("Summarize this invoice").text)

Local development from this repo:

pip install -e ./fintom8
# or: pip install -e "./fintom8[dev]"

Configuration

Resolution order: constructor kwargs / LLMConfig > environment > defaults.

Copy .env.example to .env in your project (never commit it).

from fintom8 import LLM, LLMConfig

llm = LLM()  # env defaults
llm = LLM(model="gpt-4o", api_key="sk-...", temperature=0)
llm = LLM(LLMConfig(
    model="azure/my-deploy",
    api_key="...",
    api_base="https://....openai.azure.com",
    api_version="2024-10-21",
))

Switch provider

Usage

from fintom8 import LLM

llm = LLM()

resp = llm.chat("Hello")
print(resp.text, resp.usage)

# Structured output — pass field key→type, get a JSON dict back
data = llm.structured(
    "Invoice total is 42.5 from Acme",
    {"total": "number", "vendor": "string"},
    temperature=0,
)
# {"total": 42.5, "vendor": "Acme"}

# Or a full JSON Schema / Python types
data = llm.structured("...", {"total": float, "vendor": str})
data = llm.structured(
    "...",
    {"type": "object", "properties": {"total": {"type": "number"}}, "required": ["total"]},
)

for chunk in llm.stream([{"role": "user", "content": "Write a haiku"}]):
    print(chunk, end="", flush=True)

resp = llm.extract("invoice.pdf", response_schema={...})

Async twins: achat, astream, aextract, astructured.

Helpers: fields_to_schema, json_schema_response_format, enforce_strict, inline_refs.

Failures raise Fintom8Error.

If you see an authentication error (for example missing GEMINI_API_KEY, OPENAI_API_KEY, or Vertex setup), that means package import and retries are working; configure credentials for the selected LLM_MODEL.

See examples/chat.py and examples/extract.py.

Publish (maintainers)

1. Install dev extras and run tests:

   cd fintom8
   pip install -e ".[dev]"
   pytest
   python -c "from fintom8 import LLM"
   

2. Build:

   python -m build
   

3. Upload to TestPyPI first, then PyPI:

   python -m twine upload --repository testpypi dist/*
   python -m twine upload dist/*
   

4. Tag for CI Trusted Publishing (OIDC). Create the PyPI project once and add a GitHub environment pypi with Trusted Publisher pointing at .github/workflows/publish-fintom8.yml. Then:

   git tag fintom8-v0.1.0
   git push origin fintom8-v0.1.0