本页尚未翻译

本页内容仍为英文原文，源自官方文档 integrations/reranking/watsonx。中文翻译正在分批进行中。

Watsonx Reranker

Rerank LanceDB search results with the IBM watsonx.ai text rerank API. Supports vector, FTS, and hybrid search with configurable models, projects, and spaces.

Watsonx Reranker

This reranker uses the IBM watsonx.ai text rerank API to reorder search results. Pass WatsonxReranker() to the rerank() method on a query. Credentials come from the WATSONX_API_KEY and WATSONX_PROJECT_ID (or WATSONX_SPACE_ID) environment variables, or can be passed explicitly as arguments.

Note: Supported query types: Hybrid, Vector, and FTS.

pip install ibm-watsonx-ai

Replace the credential placeholders with your provider credentials. In application code, load credentials from environment variables or a secrets manager.

import tempfile
from pathlib import Path

import lancedb
from lancedb.embeddings import get_registry
from lancedb.pydantic import LanceModel, Vector
from lancedb.rerankers import WatsonxReranker

embedder = get_registry().get("sentence-transformers").create()
db = lancedb.connect(str(Path(tempfile.mkdtemp()) / "watsonx-rerank"))

class Schema(LanceModel):
    text: str = embedder.SourceField()
    vector: Vector(embedder.ndims()) = embedder.VectorField()

data = [
    {"text": "hello world"},
    {"text": "goodbye world"},
]
tbl = db.create_table("test", schema=Schema)
tbl.add(data)

# Supply your API key and project ID (or use space_id instead of project_id).
reranker = WatsonxReranker(
    api_key="your-api-key",
    project_id="your-project-id",
)

# Run vector search with a reranker
vector_results = tbl.search("hello").rerank(reranker=reranker).to_list()
print(vector_results)

# Build the full-text index before either FTS or hybrid search.
tbl.create_fts_index("text", replace=True)

# Run FTS search with a reranker
fts_results = (
    tbl.search("hello", query_type="fts").rerank(reranker=reranker).to_list()
)
print(fts_results)

# Run hybrid search with a reranker
hybrid_results = (
    tbl.search("hello", query_type="hybrid").rerank(reranker=reranker).to_list()
)
print(hybrid_results)

Accepted Arguments

Argument	Type	Default	Description
model_name	str	"cross-encoder/ms-marco-minilm-l-12-v2"	The rerank model ID. See supported rerank models.
column	str	"text"	The name of the table column to use as document input.
top_n	int	None	The number of results to return. If None, all results are returned.
return_score	str	"relevance"	Options are "relevance" or "all". Controls which score columns are kept on the result.
api_key	str	None	IBM Cloud API key. Falls back to the WATSONX_API_KEY environment variable.
project_id	str	None	watsonx.ai project ID. Falls back to WATSONX_PROJECT_ID. Mutually exclusive with space_id.
space_id	str	None	watsonx.ai deployment space ID. Falls back to WATSONX_SPACE_ID. Mutually exclusive with project_id.
url	str	"https://us-south.ml.cloud.ibm.com"	watsonx.ai service URL.
truncate_input_tokens	int	None	Truncate each document to this many tokens before scoring.

说明

You must supply exactly one of project_id or space_id (either as an argument or via its environment variable). Setting both, or neither, raises a ValueError.

Supported scores for each query type

You can specify the type of scores you want the reranker to return. The following are the supported scores for each query type:

Hybrid Search

return_score	Status	Description
relevance	✅ Supported	Results only have the _relevance_score column.
all	❌ Not Supported	Results have vector(_distance) and FTS(score) along with Hybrid Search score(_relevance_score).

Vector Search

return_score	Status	Description
relevance	✅ Supported	Results only have the _relevance_score column.
all	✅ Supported	Results have vector(_distance) along with Hybrid Search score(_relevance_score).

FTS Search

return_score	Status	Description
relevance	✅ Supported	Results only have the _relevance_score column.
all	✅ Supported	Results have FTS(score) along with Hybrid Search score(_relevance_score).