mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-16 08:42:29 +00:00
Brendan Clement
758f738b8c
This PR is part of the documentation revamp. Once the full set of PRs is merged, we’ll publish the combined site to staging for review before updating docs.lancedb.com. Ingestion, search and integration examples are incomplete or inconsistent across languages, and some guidance misstates SDK behavior. This brings the guides and their example sources together. It includes complete Python, TypeScript and Rust workflows, isolated provider and reranker examples, the Superlinked corrections, and guidance on retries that can duplicate writes. Stacked on #4491. Each MDX file has one PR owner. Rebase onto main after #4491 is squash-merged. Local assembly, Mint validation and link checks pass. Example code is unchanged from the previously validated package. Publication stays held through integration.
19 lines
9.7 KiB
Plaintext
19 lines
9.7 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyEmbeddingIbmUsage = "import tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import EmbeddingFunctionRegistry\nfrom lancedb.pydantic import LanceModel, Vector\n\nregistry = EmbeddingFunctionRegistry.get_instance()\nregistry.set_var(\"watsonx-api-key\", \"your-api-key\")\nwatsonx_embed = registry.get(\"watsonx\").create(\n name=\"ibm/slate-125m-english-rtrvr\",\n api_key=\"$var:watsonx-api-key\",\n project_id=\"your-project-id\",\n)\n\nclass TextModel(LanceModel):\n text: str = watsonx_embed.SourceField()\n vector: Vector(watsonx_embed.ndims()) = watsonx_embed.VectorField()\n\ndata = [\n {\"text\": \"hello world\"},\n {\"text\": \"goodbye world\"},\n]\n\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"watsonx-demo\"))\ntbl = db.create_table(\"watsonx_test\", schema=TextModel, mode=\"overwrite\")\ntbl.add(data)\n\nrs = tbl.search(\"hello\").limit(1).to_pandas()\nprint(rs.head())\n";
|
|
|
|
export const PyEmbeddingJinaMultimodal = "import os\nimport tempfile\nfrom pathlib import Path\n\nimport lancedb\nimport pandas as pd\nimport requests\nfrom lancedb.embeddings import get_registry\nfrom lancedb.pydantic import LanceModel, Vector\n\nos.environ[\"JINA_API_KEY\"] = \"your-api-key\"\n\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"jina-images\"))\nfunc = get_registry().get(\"jina\").create()\n\nclass Images(LanceModel):\n label: str\n image_uri: str = func.SourceField()\n image_bytes: bytes = func.SourceField()\n vector: Vector(func.ndims()) = func.VectorField()\n vec_from_bytes: Vector(func.ndims()) = func.VectorField()\n\ntable = db.create_table(\"images\", schema=Images)\nlabels = [\"cat\", \"cat\", \"dog\", \"dog\", \"horse\", \"horse\"]\nuris = [\n \"http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg\",\n \"http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg\",\n \"http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg\",\n \"http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg\",\n \"http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg\",\n \"http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg\",\n]\nimage_bytes = [requests.get(uri).content for uri in uris]\ntable.add(\n pd.DataFrame({\"label\": labels, \"image_uri\": uris, \"image_bytes\": image_bytes})\n)\n";
|
|
|
|
export const PyEmbeddingJinaText = "import os\nimport tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import EmbeddingFunctionRegistry\nfrom lancedb.pydantic import LanceModel, Vector\n\nos.environ[\"JINA_API_KEY\"] = \"your-api-key\"\n\njina_embed = (\n EmbeddingFunctionRegistry.get_instance()\n .get(\"jina\")\n .create(name=\"jina-embeddings-v2-base-en\")\n)\n\nclass TextModel(LanceModel):\n text: str = jina_embed.SourceField()\n vector: Vector(jina_embed.ndims()) = jina_embed.VectorField()\n\ndata = [{\"text\": \"hello world\"}, {\"text\": \"goodbye world\"}]\n\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"jina-text\"))\ntbl = db.create_table(\"test\", schema=TextModel, mode=\"overwrite\")\n\ntbl.add(data)\n";
|
|
|
|
export const PyRerankingCohereUsage = "import tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import get_registry\nfrom lancedb.pydantic import LanceModel, Vector\nfrom lancedb.rerankers import CohereReranker\n\nembedder = get_registry().get(\"sentence-transformers\").create()\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"cohere-rerank\"))\n\nclass Schema(LanceModel):\n text: str = embedder.SourceField()\n vector: Vector(embedder.ndims()) = embedder.VectorField()\n\ndata = [\n {\"text\": \"hello world\"},\n {\"text\": \"goodbye world\"},\n]\ntbl = db.create_table(\"test\", schema=Schema)\ntbl.add(data)\nreranker = CohereReranker(api_key=\"your-api-key\")\n\n# Run vector search with a reranker\nvector_results = tbl.search(\"hello\").rerank(reranker=reranker).to_list()\nprint(vector_results)\n\n# Build the full-text index before either FTS or hybrid search.\ntbl.create_fts_index(\"text\", replace=True)\n\n# Run FTS search with a reranker\nfts_results = (\n tbl.search(\"hello\", query_type=\"fts\").rerank(reranker=reranker).to_list()\n)\nprint(fts_results)\n\n# Run hybrid search with a reranker\nhybrid_results = (\n tbl.search(\"hello\", query_type=\"hybrid\").rerank(reranker=reranker).to_list()\n)\nprint(hybrid_results)\n";
|
|
|
|
export const PyRerankingJinaUsage = "import os\nimport tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import get_registry\nfrom lancedb.pydantic import LanceModel, Vector\nfrom lancedb.rerankers import JinaReranker\n\nos.environ[\"JINA_API_KEY\"] = \"your-api-key\"\nembedder = get_registry().get(\"jina\").create()\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"jina-rerank\"))\n\nclass Schema(LanceModel):\n text: str = embedder.SourceField()\n vector: Vector(embedder.ndims()) = embedder.VectorField()\n\ndata = [\n {\"text\": \"hello world\"},\n {\"text\": \"goodbye world\"},\n]\ntbl = db.create_table(\"test\", schema=Schema)\ntbl.add(data)\nreranker = JinaReranker(api_key=\"your-api-key\")\n\n# Run vector search with a reranker\nvector_results = tbl.search(\"hello\").rerank(reranker=reranker).to_list()\nprint(vector_results)\n\n# Build the full-text index before either FTS or hybrid search.\ntbl.create_fts_index(\"text\", replace=True)\n\n# Run FTS search with a reranker\nfts_results = (\n tbl.search(\"hello\", query_type=\"fts\").rerank(reranker=reranker).to_list()\n)\nprint(fts_results)\n\n# Run hybrid search with a reranker\nhybrid_results = (\n tbl.search(\"hello\", query_type=\"hybrid\").rerank(reranker=reranker).to_list()\n)\nprint(hybrid_results)\n";
|
|
|
|
export const PyRerankingOpenaiUsage = "import tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import get_registry\nfrom lancedb.pydantic import LanceModel, Vector\nfrom lancedb.rerankers import OpenaiReranker\n\nembedder = get_registry().get(\"sentence-transformers\").create()\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"openai-rerank\"))\n\nclass Schema(LanceModel):\n text: str = embedder.SourceField()\n vector: Vector(embedder.ndims()) = embedder.VectorField()\n\ndata = [\n {\"text\": \"hello world\"},\n {\"text\": \"goodbye world\"},\n]\ntbl = db.create_table(\"test\", schema=Schema)\ntbl.add(data)\nreranker = OpenaiReranker(api_key=\"your-api-key\")\n\n# Run vector search with a reranker\nvector_results = tbl.search(\"hello\").rerank(reranker=reranker).to_list()\nprint(vector_results)\n\n# Build the full-text index before either FTS or hybrid search.\ntbl.create_fts_index(\"text\", replace=True)\n\n# Run FTS search with a reranker\nfts_results = (\n tbl.search(\"hello\", query_type=\"fts\").rerank(reranker=reranker).to_list()\n)\nprint(fts_results)\n\n# Run hybrid search with a reranker\nhybrid_results = (\n tbl.search(\"hello\", query_type=\"hybrid\").rerank(reranker=reranker).to_list()\n)\nprint(hybrid_results)\n";
|
|
|
|
export const PyRerankingVoyageaiUsage = "import tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import get_registry\nfrom lancedb.pydantic import LanceModel, Vector\nfrom lancedb.rerankers import VoyageAIReranker\n\nembedder = get_registry().get(\"sentence-transformers\").create()\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"voyageai-rerank\"))\n\nclass Schema(LanceModel):\n text: str = embedder.SourceField()\n vector: Vector(embedder.ndims()) = embedder.VectorField()\n\ndata = [\n {\"text\": \"hello world\"},\n {\"text\": \"goodbye world\"},\n]\ntbl = db.create_table(\"test\", schema=Schema)\ntbl.add(data)\nreranker = VoyageAIReranker(api_key=\"your-api-key\", model_name=\"rerank-2\")\n\n# Run vector search with a reranker\nvector_results = tbl.search(\"hello\").rerank(reranker=reranker).to_list()\nprint(vector_results)\n\n# Build the full-text index before either FTS or hybrid search.\ntbl.create_fts_index(\"text\", replace=True)\n\n# Run FTS search with a reranker\nfts_results = (\n tbl.search(\"hello\", query_type=\"fts\").rerank(reranker=reranker).to_list()\n)\nprint(fts_results)\n\n# Run hybrid search with a reranker\nhybrid_results = (\n tbl.search(\"hello\", query_type=\"hybrid\").rerank(reranker=reranker).to_list()\n)\nprint(hybrid_results)\n";
|
|
|
|
export const PyRerankingWatsonxUsage = "import tempfile\nfrom pathlib import Path\n\nimport lancedb\nfrom lancedb.embeddings import get_registry\nfrom lancedb.pydantic import LanceModel, Vector\nfrom lancedb.rerankers import WatsonxReranker\n\nembedder = get_registry().get(\"sentence-transformers\").create()\ndb = lancedb.connect(str(Path(tempfile.mkdtemp()) / \"watsonx-rerank\"))\n\nclass Schema(LanceModel):\n text: str = embedder.SourceField()\n vector: Vector(embedder.ndims()) = embedder.VectorField()\n\ndata = [\n {\"text\": \"hello world\"},\n {\"text\": \"goodbye world\"},\n]\ntbl = db.create_table(\"test\", schema=Schema)\ntbl.add(data)\n\n# Supply your API key and project ID (or use space_id instead of project_id).\nreranker = WatsonxReranker(\n api_key=\"your-api-key\",\n project_id=\"your-project-id\",\n)\n\n# Run vector search with a reranker\nvector_results = tbl.search(\"hello\").rerank(reranker=reranker).to_list()\nprint(vector_results)\n\n# Build the full-text index before either FTS or hybrid search.\ntbl.create_fts_index(\"text\", replace=True)\n\n# Run FTS search with a reranker\nfts_results = (\n tbl.search(\"hello\", query_type=\"fts\").rerank(reranker=reranker).to_list()\n)\nprint(fts_results)\n\n# Run hybrid search with a reranker\nhybrid_results = (\n tbl.search(\"hello\", query_type=\"hybrid\").rerank(reranker=reranker).to_list()\n)\nprint(hybrid_results)\n";
|
|
|