{"files":{"SKILL.md":"---\nname: pinecone-inference-api\ndescription: \"Pinecone Inference API skill. Use when working with Pinecone Inference for embed, rerank, models. Covers 4 endpoints.\"\nversion: 1.0.0\ngenerator: lapsh\n---\n\n# Pinecone Inference API\nAPI version: 2026-04\n\n## Auth\nApiKey Api-Key in header\n\n## Base URL\nhttps://api.pinecone.io\n\n## Setup\n1. Set your API key in the appropriate header\n2. GET /models -- verify access\n3. POST /embed -- create first embed\n\n## Endpoints\n\n4 endpoints across 3 groups. See references/api-spec.lap for full details.\n\n### embed\n| Method | Path | Description |\n|--------|------|-------------|\n| POST | /embed | Generate vectors |\n\n### rerank\n| Method | Path | Description |\n|--------|------|-------------|\n| POST | /rerank | Rerank results |\n\n### models\n| Method | Path | Description |\n|--------|------|-------------|\n| GET | /models | List available models |\n| GET | /models/{model_name} | Describe a model |\n\n## Common Questions\n\nMatch user requests to endpoints in references/api-spec.lap. Key patterns:\n- \"Create a embed?\" -> POST /embed\n- \"Create a rerank?\" -> POST /rerank\n- \"List all models?\" -> GET /models\n- \"Get model details?\" -> GET /models/{model_name}\n- \"How to authenticate?\" -> See Auth section\n\n## Response Tips\n- Check response schemas in references/api-spec.lap for field details\n- Create/update endpoints typically return the created/updated object\n\n## CLI\n\n```bash\n# Update this spec to the latest version\nnpx @lap-platform/lapsh get pinecone-inference-api -o references/api-spec.lap\n\n# Search for related APIs\nnpx @lap-platform/lapsh search pinecone-inference-api\n```\n\n## References\n- Full spec: See references/api-spec.lap for complete endpoint details, parameter tables, and response schemas\n\n> Generated from the official API spec by [LAP](https://lap.sh)\n","references/api-spec.lap":"@lap v0.3\n# Machine-readable API spec. Each @endpoint block is one API call.\n@api Pinecone Inference API\n@base https://api.pinecone.io\n@version 2026-04\n@auth ApiKey Api-Key in header\n@endpoints 4\n@toc embed(1), rerank(1), models(2)\n\n@group embed\n@endpoint POST /embed\n@desc Generate vectors\n@required {X-Pinecone-Api-Version: str=2026-04 # Required date-based version header, model: str # The [model](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) to use for embedding generation., inputs: [map{text: str}] # List of inputs to generate embeddings for.}\n@optional {parameters: map # Additional model-specific parameters. Refer to the [model guide](https://docs.pinecone.io/guides/index-data/create-an-index#embedding-models) for available model parameters.}\n@returns(200) {model: str, vector_type: str, data: [map], usage: map{total_tokens: int(int32)}} # OK\n@errors {400: Bad request. The request body included invalid request parameters., 401: Unauthorized. Possible causes: Invalid API key., 500: Internal server error.}\n\n@endgroup\n\n@group rerank\n@endpoint POST /rerank\n@desc Rerank results\n@required {X-Pinecone-Api-Version: str=2026-04 # Required date-based version header, model: str # The [model](https://docs.pinecone.io/guides/search/rerank-results#reranking-models) to use for reranking., query: str # The query to rerank documents against., documents: [map] # The documents to rerank.}\n@optional {top_n: int # The number of results to return sorted by relevance. Defaults to the number of inputs., return_documents: bool=True # Whether to return the documents in the response., rank_fields: [str]=['text'] # The field(s) to consider for reranking. If not provided, the default is `[\"text\"]`.  The number of fields supported is [model-specific](https://docs.pinecone.io/guides/search/rerank-results#reranking-models)., parameters: map # Additional model-specific parameters. Refer to the [model guide](https://docs.pinecone.io/guides/search/rerank-results#reranking-models) for available model parameters.}\n@returns(200) {model: str, data: [map], usage: map{rerank_units: int(int32)}} # OK\n@errors {400: Bad request. The request body included invalid request parameters., 401: Unauthorized. Possible causes: Invalid API key., 500: Internal server error.}\n\n@endgroup\n\n@group models\n@endpoint GET /models\n@desc List available models\n@required {X-Pinecone-Api-Version: str=2026-04 # Required date-based version header}\n@optional {type: str # Filter models by type ('embed' or 'rerank')., vector_type: str # Filter embedding models by vector type ('dense' or 'sparse'). Only relevant when `type=embed`.}\n@returns(200) {models: [map]} # The list of available models.\n@errors {401: Unauthorized. Possible causes: Invalid API key., 404: Model not found., 500: Internal server error.}\n\n@endpoint GET /models/{model_name}\n@desc Describe a model\n@required {X-Pinecone-Api-Version: str=2026-04 # Required date-based version header, model_name: str # The name of the model to look up.}\n@returns(200) {model: str, short_description: str, type: str, vector_type: str, default_dimension: int(int32), modality: str, max_sequence_length: int(int32), max_batch_size: int(int32), provider_name: str, supported_dimensions: [int(int32)], supported_metrics: [str], supported_parameters: [map]} # The model details.\n@errors {401: Unauthorized. Possible causes: Invalid API key., 404: Model not found., 500: Internal server error.}\n\n@endgroup\n\n@end\n"}}