lmcore 0.2.0

Personal core toolkit for AI projects — config loading, LLM client factory, and logging.

lmcore

Personal core toolkit for AI projects. Install once, call with inputs, never edit the package.

Covers three things every project needs:

• Config — load and validate .env secrets
• LLM — build AI clients from a models.yaml file
• Logging — colored, consistent logging across all modules

---

Install

pip install lmcore

With specific provider dependencies:

pip install lmcore[openai]
pip install lmcore[anthropic]
pip install lmcore[ollama]
pip install lmcore[all]       # all three providers

---

Config

Call load_config once at startup. Pass the keys your project needs — the package handles loading from .env, validating, and returning a plain dict.

from lmcore import load_config

cfg = load_config(
    required=["OPENAI_API_KEY", "CHROMA_API_KEY"],
    optional={"ACTIVE_ARCH": "arch_1", "LOG_LEVEL": "INFO"}
)

• required — must exist in .env, raises EnvironmentError if any are missing
• optional — uses the default value if not set in .env

---

LLM

models.yaml

Lives in your project root. Define only what your project uses — chat and embed are both optional. Each section is a list so you can define multiple clients and reference them by index.

arch_1:
  chat:
    - provider: openai
      model: gpt-4o
      api_key_env: OPENAI_API_KEY
    - provider: anthropic
      model: claude-sonnet-4-6
      api_key_env: ANTHROPIC_API_KEY
  embed:
    - provider: ollama
      model: nomic-embed-text
      base_url_env: OLLAMA_URL

arch_2:
  chat:
    - provider: anthropic
      model: claude-opus-4-8
      api_key_env: ANTHROPIC_API_KEY

Supported fields per client:

Field	Required	Description
provider	yes	ollama, openai, or anthropic
model	yes	model name string
api_key_env	when needed	env var name that holds the API key
base_url	no	override default endpoint (e.g. local Ollama)
base_url_env	no	env var name that holds the base URL (alternative to base_url)

Getting clients

from lmcore import get_chat_client, get_embed_client

# index defaults to 0 — covers most single-client projects
chat  = get_chat_client("models.yaml", arch="arch_1")
embed = get_embed_client("models.yaml", arch="arch_1")

# specify index for multiple clients
openai_client    = get_chat_client("models.yaml", arch="arch_1", index=0)
anthropic_client = get_chat_client("models.yaml", arch="arch_1", index=1)

Adding a custom provider

If you need a provider not built into the package, register it in your project:

from lmcore import register_provider

def _build_groq(cfg):
    from groq import Groq
    return Groq(api_key=cfg["api_key"])

register_provider("groq", _build_groq)

Once registered, groq works as a provider: value in models.yaml like any built-in.

---

Logging

from lmcore import configure_logging, get_logger

configure_logging()          # call once at app startup
configure_logging("DEBUG")   # optional level override

logger = get_logger(__name__)

logger.info("Starting up")
logger.warning("Something looks off")
logger.error("Connection failed")

Color scheme:

Color	Level
Cyan	INFO
Yellow	WARNING
Red	ERROR / CRITICAL
Dim	DEBUG

---

Full Example

Project layout:

my-project/
├── .env
├── models.yaml
└── app/
    └── core/
        ├── config.py
        └── llm.py

.env:

OPENAI_API_KEY=sk-...
ACTIVE_ARCH=arch_1

models.yaml:

arch_1:
  chat:
    - provider: openai
      model: gpt-4o
      api_key_env: OPENAI_API_KEY
    - provider: ollama
      model: llama3
      base_url_env: OLLAMA_URL

app/core/config.py:

from lmcore import load_config, configure_logging

configure_logging()

cfg = load_config(
    required=["OPENAI_API_KEY"],
    optional={"ACTIVE_ARCH": "arch_1"}
)

app/core/llm.py:

from lmcore import get_chat_client
from app.core.config import cfg

chat = get_chat_client("models.yaml", arch=cfg["ACTIVE_ARCH"])

Anywhere in the project:

from lmcore import get_logger
from app.core.llm import chat

logger = get_logger(__name__)

response = chat.chat(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Summarize this document."}]
)
logger.info(f"Done: {response.choices[0].message.content}")

---

Built-in Providers

Provider	provider: value	Install extra
Ollama	ollama	pip install lmcore[ollama]
OpenAI	openai	pip install lmcore[openai]
Anthropic	anthropic	pip install lmcore[anthropic]