# llm

The `llm` module provides a function to send text to a large language model (LLM) and return the completion directly from Cypher. It uses [LiteLLM](https://docs.litellm.ai/) for model-agnostic completion, so you can use OpenAI, Anthropic, Ollama, and other providers with the same interface.

| Trait               | Value            |
| ------------------- | ---------------- |
| **Module type**     | util             |
| **Implementation**  | Python           |
| **Parallelism**     | sequential       |

> **Info**
>
> **Requirement**: Install LiteLLM in the MAGE Python environment: `pip install litellm`.
> Set the API key for your provider (e.g. `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`). For local providers like Ollama, you can set `api_base` in the config or `LITELLM_API_BASE` in the environment.

## Functions

### `complete()`

Sends text to an LLM and returns the completion as a string (e.g. for summarization or text generation).

#### Input:

- `text: str` ➡ Input text to send to the LLM (e.g. concatenated node text to summarize or complete).
- `config: Map` (**OPTIONAL**) ➡ Configuration map. Defaults to `{}`.

**Config options:**

| Name            | Type   | Description                                                                 |
|-----------------|--------|-----------------------------------------------------------------------------|
| `model`         | string | Model name (e.g. `ollama/llama2`, `openai/gpt-4o-mini`). Falls back to env `LITELLM_MODEL` or a default. |
| `api_base`      | string | Base URL for the API (e.g. `http://localhost:11434` for Ollama). Can also be set via `LITELLM_API_BASE`. |
| `system_prompt` | string | System prompt for the completion. Default: `"Complete the following text."` |

#### Output:

- **Returns** `str` ➡ The model's completion (trimmed string). Empty string if the model returns no content.

#### Usage:

Using default or environment configuration:

```cypher
RETURN llm.complete("Summarize in one sentence: Memgraph is a graph database.");
```

With explicit config (e.g. Ollama):

```cypher
RETURN llm.complete("Hello", {model: "ollama/llama2", api_base: "http://localhost:11434"});
```

With a custom system prompt:

```cypher
RETURN llm.complete(
  "List the main topics.",
  {system_prompt: "You are a concise assistant. Reply with a short bullet list."}
);
```

Using graph data (e.g. summarize node text):

```cypher
MATCH (n:Article)
WITH collect(n.title + ": " + n.abstract) AS texts
WITH reduce(s = "", t IN texts | s + t + "\n") AS combined
RETURN llm.complete(combined, {system_prompt: "Summarize the following articles in 2 sentences."}) AS summary;
```