{"_id":"@boazlai/n8n-nodes-vertex-ai","name":"@boazlai/n8n-nodes-vertex-ai","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@boazlai/n8n-nodes-vertex-ai","version":"0.1.0","description":"n8n community nodes for Google Vertex AI: Gemini context caching, batch prediction, GCS, and a chat model sub-node with cached-content support.","keywords":["n8n-community-node-package","n8n","vertex-ai","gemini","google-cloud","context-caching","batch-prediction"],"license":"MIT","homepage":"","author":{"name":"boazlai"},"repository":{"type":"git","url":""},"engines":{"node":">=22"},"main":"index.js","scripts":{"build":"n8n-node build","dev":"n8n-node dev","lint":"n8n-node lint","lint:fix":"n8n-node lint --fix","release":"n8n-node release"},"n8n":{"n8nNodesApiVersion":1,"credentials":["dist/credentials/GoogleVertexServiceAccountApi.credentials.js"],"nodes":["dist/nodes/VertexAi/VertexAi.node.js","dist/nodes/VertexAiChatModel/VertexAiChatModel.node.js"]},"devDependencies":{"@langchain/core":"^0.3.0","@langchain/google-vertexai":"^0.2.0","@n8n/node-cli":"^0.23.0","eslint":"^9.39.4","n8n-workflow":"*"},"peerDependencies":{"@langchain/core":"*","@langchain/google-vertexai":"*"},"_id":"@boazlai/n8n-nodes-vertex-ai@0.1.0","_nodeVersion":"22.22.2","_npmVersion":"10.9.7","dist":{"integrity":"sha512-42Y8DQMU7HV6O8KPjDZmWxuOv/2EzDxDaJI8DmLxqA7eS2TWR1GIddlvJJpEM1+FnNvC94Wn+HhvMQIBrh9uUA==","shasum":"e52f55baa734a85d344b1668139855d3c3bcd946","tarball":"https://registry.npmjs.org/@boazlai/n8n-nodes-vertex-ai/-/n8n-nodes-vertex-ai-0.1.0.tgz","fileCount":45,"unpackedSize":133393,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQDyUB1W3x+sobgdaN4v1AUrv8xI8AybS7czTH20vZdG8AIhAPF59iquSKFpJHYlEgvz8yf7Y7CtFF3FxGxyDHrsKIw4"}]},"_npmUser":{"name":"boazlai","email":"game94049@gmail.com"},"directories":{},"maintainers":[{"name":"boazlai","email":"game94049@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/n8n-nodes-vertex-ai_0.1.0_1777563863147_0.7794827202867955"},"_hasShrinkwrap":false}},"time":{"created":"2026-04-30T15:44:23.093Z","0.1.0":"2026-04-30T15:44:23.350Z","modified":"2026-04-30T15:44:23.816Z"},"maintainers":[{"name":"boazlai","email":"game94049@gmail.com"}],"description":"n8n community nodes for Google Vertex AI: Gemini context caching, batch prediction, GCS, and a chat model sub-node with cached-content support.","keywords":["n8n-community-node-package","n8n","vertex-ai","gemini","google-cloud","context-caching","batch-prediction"],"repository":{"type":"git","url":""},"author":{"name":"boazlai"},"license":"MIT","readme":"# n8n-nodes-vertex-ai\n\nCommunity n8n nodes for Google Vertex AI:\n\n- **Vertex AI** (regular node): three resources\n  - **Cache** — Create / Get / List / Update TTL / Delete Gemini Context Caches\n  - **Batch** — Create / Get / List / Cancel Batch Prediction Jobs (with optional internal polling)\n  - **GCS** — Upload / Download / List objects (Vertex-oriented; not a full GCS client)\n- **Vertex AI Chat Model** (sub-node, AI Agent compatible): Gemini chat model with a **Cached Content** dropdown that lists your existing context caches.\n\nSingle credential: **Google Vertex Service Account API**.\n\n## Install\n\nIn n8n: **Settings → Community Nodes → Install** → `n8n-nodes-vertex-ai`.\n\nOr self-hosted manual install:\n\n```bash\ncd ~/.n8n/custom\nnpm install n8n-nodes-vertex-ai\n```\n\n## Credential setup\n\nCreate a service account in your GCP project with:\n\n- `roles/aiplatform.user`\n- `roles/storage.objectAdmin` (only if you use the GCS resource)\n\nDownload the JSON key. In n8n, create a **Google Vertex Service Account API** credential and fill:\n\n- **Service Account Email** — `client_email` from the JSON.\n- **Private Key** — `private_key` from the JSON (literal `\\n` is accepted).\n- **Project ID** — your GCP project id.\n- **Location** — Vertex region (e.g. `us-central1`).\n\nThe credential test calls the Vertex publishers endpoint to verify auth.\n\n## Cache resource example\n\nReproduces the standard \"cache a PDF for grounding\" payload:\n\n1. Resource: **Cache**, Operation: **Create**.\n2. Model: `Gemini 2.5 Flash`.\n3. Display Name: `Cache_Public_URL_Test`.\n4. TTL: `3` Hours (or `10800` Seconds).\n5. System Instruction: `Analyze the provided document to provide context for upcoming chunks.`\n6. Contents → Add Content Block (`role: user`):\n   - Add Part — Type: `Text`, Text: `Here is the full document context to be used for grounding subsequent chunks:\\n`\n   - Add Part — Type: `File (GCS URI)`, MIME: `application/pdf`, GCS URI: `gs://your-bucket/DFA2025z.pdf`\n7. Tools → Add Tool → Mode: `Structured` → Function Declaration:\n   - Name: `format_final_json_response`\n   - Description: …\n   - Parameters Schema: paste your OBJECT schema.\n\n## Batch resource example\n\n1. Resource: **Batch**, Operation: **Create**.\n2. Display Name: `Contextual-Chunking`.\n3. Model: `Gemini 2.5 Flash`.\n4. GCS Source URIs: `gs://your-bucket/vertex-batch-input-1.jsonl`.\n5. Output URI Prefix: `gs://your-bucket/batchResults/`.\n6. **Wait For Completion**: ON to block until terminal state (Poll Interval and Timeout reveal).\n\nTo poll separately, run **Get** with the job name returned from Create.\n\n## Chat Model with Cached Content\n\nAdd the **Vertex AI Chat Model** node, wire it into an **AI Agent**'s Model port. The **Cached Content** dropdown is populated from `cachedContents.list` for the credential's project + location.\n\n## Local development\n\n```bash\nnpm install\nnpm run build\nnpm run dev   # embedded n8n at http://localhost:5678\n```\n\nOr copy `dist/` into a Docker n8n container:\n\n```bash\ndocker cp dist/ n8n:/home/node/.n8n/custom/node_modules/n8n-nodes-vertex-ai/dist/\ndocker compose restart n8n\n```\n\n## License\n\nMIT\n","readmeFilename":"README.md","_rev":"1-04eb3d4b4139f723397790d25155e558"}