{"_id":"@dkhalife/n8n-nodes-litellm","name":"@dkhalife/n8n-nodes-litellm","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@dkhalife/n8n-nodes-litellm","version":"0.1.0","description":"n8n community node for LiteLLM proxy — Chat Completions, Embeddings, and AI Agent model","keywords":["n8n-community-node-package","litellm","llm","ai","openai"],"license":"MIT","homepage":"https://github.com/dkhalife/n8n-nodes-litellm","author":{"name":"dkhalife"},"repository":{"type":"git","url":"git+https://github.com/dkhalife/n8n-nodes-litellm.git"},"main":"dist/index.js","engines":{"node":">=18.17"},"scripts":{"build":"n8n-node build","build:watch":"tsc --watch","dev":"n8n-node dev","lint":"n8n-node lint","lint:fix":"n8n-node lint --fix","prepare":"npm run build","prepublishOnly":"n8n-node prerelease","release":"n8n-node release","test":"jest --testPathPatterns=tests/"},"n8n":{"n8nNodesApiVersion":1,"credentials":["dist/credentials/LiteLlmApi.credentials.js"],"nodes":["dist/nodes/LiteLlm/LiteLlm.node.js","dist/nodes/LiteLlm/LiteLlmModel.node.js"]},"devDependencies":{"@langchain/core":"^1.1.38","@langchain/openai":"^1.4.1","@n8n/ai-utilities":">=0.7.0","@n8n/node-cli":"^0.23.1","@types/jest":"^30.0.0","@types/node":"^18.19.130","@typescript-eslint/eslint-plugin":"^8.58.0","@typescript-eslint/parser":"^8.58.0","eslint":"^9.39.4","jest":"^30.3.0","n8n-workflow":"*","prettier":"^3.8.1","release-it":"^19.2.4","ts-jest":"^29.4.9","typescript":"^5.9.3"},"peerDependencies":{"@langchain/core":">=1.0.0","@langchain/openai":">=1.0.0","@n8n/ai-utilities":"*","n8n-workflow":"*"},"gitHead":"d6e31cdbe5cf28db5db81da067c735f97374fa40","types":"./dist/index.d.ts","_id":"@dkhalife/n8n-nodes-litellm@0.1.0","bugs":{"url":"https://github.com/dkhalife/n8n-nodes-litellm/issues"},"_nodeVersion":"22.21.1","_npmVersion":"11.7.0","dist":{"integrity":"sha512-tbFDzTyexIuVhYXd7cvMW35tRuxhyjwkta40ZJWPumoC0hIoptoi9fUzJ2RPb/oh7xJb5qwJ2g3mUSJC0vw2zw==","shasum":"602e4dc3ce348db6c70a326f2427c09ac15b3dcf","tarball":"https://registry.npmjs.org/@dkhalife/n8n-nodes-litellm/-/n8n-nodes-litellm-0.1.0.tgz","fileCount":25,"unpackedSize":81043,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIChia/CMekOzmbhf4BpnXT8HhmmbanJg6efHhOlLJ+F3AiEApAZoq3VCon52GMzujapwKfPNrRxQMR+NTf+EthPb8MY="}]},"_npmUser":{"name":"dkhalife","email":"npm@dkhalife.com"},"directories":{},"maintainers":[{"name":"dkhalife","email":"npm@dkhalife.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/n8n-nodes-litellm_0.1.0_1775267601560_0.4216500974006139"},"_hasShrinkwrap":false}},"time":{"created":"2026-04-04T01:53:21.449Z","0.1.0":"2026-04-04T01:53:21.749Z","modified":"2026-04-04T01:53:21.984Z"},"maintainers":[{"name":"dkhalife","email":"npm@dkhalife.com"}],"description":"n8n community node for LiteLLM proxy — Chat Completions, Embeddings, and AI Agent model","homepage":"https://github.com/dkhalife/n8n-nodes-litellm","keywords":["n8n-community-node-package","litellm","llm","ai","openai"],"repository":{"type":"git","url":"git+https://github.com/dkhalife/n8n-nodes-litellm.git"},"author":{"name":"dkhalife"},"bugs":{"url":"https://github.com/dkhalife/n8n-nodes-litellm/issues"},"license":"MIT","readme":"# n8n-nodes-litellm\r\n\r\n[![CI](https://github.com/dkhalife/n8n-nodes-litellm/actions/workflows/ci.yml/badge.svg)](https://github.com/dkhalife/n8n-nodes-litellm/actions/workflows/ci.yml)\r\n[![npm](https://img.shields.io/npm/v/@dkhalife/n8n-nodes-litellm)](https://www.npmjs.com/package/@dkhalife/n8n-nodes-litellm)\r\n\r\nAn [n8n](https://n8n.io) community node package for integrating with a [LiteLLM](https://docs.litellm.ai) proxy. Provides a standalone node for Chat Completions, Responses API calls, and Embeddings, plus a LangChain-compatible Chat Model node for use inside AI Agent and Chain workflows.\r\n\r\n---\r\n\r\n## Nodes\r\n\r\n### LiteLLM\r\n\r\nA general-purpose node with three operations:\r\n\r\n| Operation | Endpoint | Description |\r\n|---|---|---|\r\n| **Chat Completion** | `POST /v1/chat/completions` | Send messages to any chat model and receive a response |\r\n| **Responses** | `POST /v1/responses` | Call OpenAI-compatible responses models such as Copilot Codex / GPT-5 |\r\n| **Embeddings** | `POST /v1/embeddings` | Generate vector embeddings for one or more text inputs |\r\n\r\n#### Chat Completion parameters\r\n\r\n| Parameter | Description |\r\n|---|---|\r\n| **Model** | Loaded dynamically from your proxy (filtered to chat-capable models) |\r\n| **System Prompt** | Convenience field — prepended as a `system` message |\r\n| **Messages** | Ordered list of `role` + `content` pairs (user / assistant / system / tool) |\r\n| **Reasoning Effort** | `low / medium / high` — for extended-thinking models (o1, o3, claude-3-7, etc.) |\r\n| **Tools** | JSON array of function/tool definitions (OpenAI format) |\r\n| **Tool Choice** | `auto / none / required` |\r\n\r\n#### Embeddings parameters\r\n\r\n| Parameter | Description |\r\n|---|---|\r\n| **Model** | Loaded dynamically (filtered to embedding models) |\r\n| **Input** | Plain string or JSON array of strings for batch embedding |\r\n| **Encoding Format** | `float` (default) or `base64` |\r\n\r\n#### Responses parameters\r\n\r\n| Parameter | Description |\r\n|---|---|\r\n| **Model** | Loaded dynamically from your proxy (filtered to `mode: responses` models) |\r\n| **Input** | Prompt or input text sent to `/v1/responses` |\r\n| **Instructions** | Optional system-style instructions |\r\n| **Reasoning Effort** | `low / medium / high` for supported reasoning models |\r\n| **Tools** | JSON array of Responses API tool definitions, including built-in tools and function tools |\r\n| **Tool Choice** | `auto / none / required` |\r\n\r\n---\r\n\r\n### LiteLLM Chat Model\r\n\r\nA LangChain-compatible node that exposes the LiteLLM proxy as an **AI Language Model**. Connect it to the **Model** input of an [AI Agent](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/), Chain, or any other LangChain node.\r\n\r\n| Parameter | Description |\r\n|---|---|\r\n| **Model** | Chat model loaded dynamically from your proxy |\r\n| **Temperature** | Sampling temperature 0–2 |\r\n| **Max Tokens** | Maximum tokens to generate |\r\n| **Reasoning Effort** | Extended thinking level for supported models |\r\n| **Max Retries** | How many times to retry failed API calls |\r\n\r\n---\r\n\r\n## Credentials\r\n\r\n### LiteLlmApi\r\n\r\n| Field | Required | Description |\r\n|---|---|---|\r\n| **Base URL** | ✅ | URL of your LiteLLM proxy, e.g. `http://localhost:4000` |\r\n| **API Key** | ❌ | Bearer token — leave blank for open (unauthenticated) deployments |\r\n\r\n> **Tip:** The credential is entirely optional on both nodes. If you don't attach one, the node will attempt to connect to `http://localhost:4000` without authentication.\r\n\r\n---\r\n\r\n## Dynamic model discovery\r\n\r\nThe model dropdowns call `GET /model/info` at node-configuration time and filter results by the `mode` field reported by LiteLLM (`chat` for Chat Completion, `responses` for the Responses API, `embedding` for Embeddings). If `/model/info` is unavailable the nodes fall back to `GET /v1/models`. You can also type any model name manually.\r\n\r\n---\r\n\r\n## Installation\r\n\r\n### In n8n (community nodes)\r\n\r\n1. Open **Settings → Community Nodes**\r\n2. Enter `@dkhalife/n8n-nodes-litellm` and click **Install**\r\n3. Restart n8n if prompted\r\n\r\n### Manual / self-hosted\r\n\r\n```bash\r\n# Inside your n8n custom nodes directory (or the n8n data volume):\r\nnpm install @dkhalife/n8n-nodes-litellm\r\n```\r\n\r\n### Development\r\n\r\n```bash\r\ngit clone https://github.com/dkhalife/n8n-nodes-litellm.git\r\ncd n8n-nodes-litellm\r\nnpm install\r\nnpm run build\r\n```\r\n\r\nLink into a local n8n instance:\r\n\r\n```bash\r\n# From this repo root:\r\nnpm link\r\n\r\n# From your n8n installation:\r\nnpm link n8n-nodes-litellm\r\n```\r\n\r\n---\r\n\r\n## Releasing\r\n\r\nNew versions are published to npm automatically when a version tag is pushed.\r\n\r\n```bash\r\nnpm run release\r\n```\r\n\r\nThis will lint, build, prompt for a version bump, update the changelog, commit, tag, and push — which triggers the [publish workflow](.github/workflows/publish.yml) to publish to npm with provenance.\r\n\r\n> **One-time setup:** Configure OIDC trusted publishing on npmjs.com for this package. See the [publish workflow](.github/workflows/publish.yml) header for detailed instructions.\r\n\r\n---\r\n\r\n## Requirements\r\n\r\n- n8n ≥ 1.0\r\n- Node.js ≥ 18.17\r\n\r\n---\r\n\r\n## License\r\n\r\nMIT\r\n","readmeFilename":"README.md","_rev":"1-3630b5ad96ccfa6fbb8bf5b89b2b72c0"}