Database
- Indexes
- Vectors
- Search
- Imports
- Backups
Inference
- Embed
- Rerank
Architecture
Search with text
Search a namespace with a query text, query vector, or record ID and return the most similar records, along with their similarity scores. Optionally, rerank the initial results based on their relevance to the query.
Searching with text is supported only for indexes with integrated embedding. Searching with a query vector or record ID is supported for all indexes.
For guidance and examples, see Query data.
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
# To get the unique host for an index,
# see https://docs.pinecone.io/guides/data/target-an-index
index = pc.Index("example-index")
# Search with a query text and rerank the results
# Supported only for indexes with integrated embedding
search_with_text = index.search(
namespace="example-namespace",
query={
"inputs": {"text": "Disease prevention"},
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_text)
# Search with a query vector and rerank the results
search_with_vector = index.search(
namespace="example-namespace",
query={
"vector": {
"values": [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]
},
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"query": "Disease prevention",
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_vector)
# Search with a record ID and rerank the results
search_with_id = index.search(
namespace="example-namespace",
query={
"id": "rec1",
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"query": "Disease prevention",
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_id)
{'result': {'hits': [{'_id': 'rec3',
'_score': 0.004399413242936134,
'fields': {'category': 'immune system',
'chunk_text': 'Rich in vitamin C and other '
'antioxidants, apples '
'contribute to immune health '
'and may reduce the risk of '
'chronic diseases.'}},
{'_id': 'rec4',
'_score': 0.0029235430993139744,
'fields': {'category': 'endocrine system',
'chunk_text': 'The high fiber content in '
'apples can also help regulate '
'blood sugar levels, making '
'them a favorable snack for '
'people with diabetes.'}}]},
'usage': {'embed_total_tokens': 8, 'read_units': 6, 'rerank_units': 1}}
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
# To get the unique host for an index,
# see https://docs.pinecone.io/guides/data/target-an-index
index = pc.Index("example-index")
# Search with a query text and rerank the results
# Supported only for indexes with integrated embedding
search_with_text = index.search(
namespace="example-namespace",
query={
"inputs": {"text": "Disease prevention"},
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_text)
# Search with a query vector and rerank the results
search_with_vector = index.search(
namespace="example-namespace",
query={
"vector": {
"values": [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]
},
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"query": "Disease prevention",
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_vector)
# Search with a record ID and rerank the results
search_with_id = index.search(
namespace="example-namespace",
query={
"id": "rec1",
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"query": "Disease prevention",
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_id)
{'result': {'hits': [{'_id': 'rec3',
'_score': 0.004399413242936134,
'fields': {'category': 'immune system',
'chunk_text': 'Rich in vitamin C and other '
'antioxidants, apples '
'contribute to immune health '
'and may reduce the risk of '
'chronic diseases.'}},
{'_id': 'rec4',
'_score': 0.0029235430993139744,
'fields': {'category': 'endocrine system',
'chunk_text': 'The high fiber content in '
'apples can also help regulate '
'blood sugar levels, making '
'them a favorable snack for '
'people with diabetes.'}}]},
'usage': {'embed_total_tokens': 8, 'read_units': 6, 'rerank_units': 1}}
Authorizations
Path Parameters
The namespace to search.
Body
A search request for records in a specific namespace.
The query inputs to search with. Each request can contain only one of the following parameters: inputs, vector, or id.
The number of similar records to return.
10
The filter to apply. You can use vector metadata to limit your search. See Understanding metadata.
{ "text": "chunk_text" }
The unique ID of the vector to be used as a query vector.
512"example-vector-1"
The fields to return in the search results. If not specified, the response will include all fields.
["chunk_text"]
Parameters for reranking the initial search results.
The name of the reranking model to use.
"bge-reranker-v2-m3"
The field(s) to consider for reranking. If not provided, the default is ["text"].
The number of fields supported is model-specific.
["chunk_text", "title"]
The number of top results to return after reranking. Defaults to top_k.
5
Additional model-specific parameters. Refer to the model guide for available model parameters.
{ "truncate": "END" }
The query to rerank documents against. If a specific rerank query is specified, it overwrites the query input that was provided at the top level.
"What is the capital of France?"
Response
The records search response.
The hits for the search document request.
A record whose vector values are similar to the provided search query.
The number of read units consumed by this operation.
x >= 05
The number of embedding tokens consumed by this operation.
x >= 02
The number of rerank units consumed by this operation.
x >= 01
Was this page helpful?
from pinecone import Pinecone
pc = Pinecone(api_key="YOUR_API_KEY")
# To get the unique host for an index,
# see https://docs.pinecone.io/guides/data/target-an-index
index = pc.Index("example-index")
# Search with a query text and rerank the results
# Supported only for indexes with integrated embedding
search_with_text = index.search(
namespace="example-namespace",
query={
"inputs": {"text": "Disease prevention"},
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_text)
# Search with a query vector and rerank the results
search_with_vector = index.search(
namespace="example-namespace",
query={
"vector": {
"values": [0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]
},
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"query": "Disease prevention",
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_vector)
# Search with a record ID and rerank the results
search_with_id = index.search(
namespace="example-namespace",
query={
"id": "rec1",
"top_k": 4
},
fields=["category", "chunk_text"],
rerank={
"query": "Disease prevention",
"model": "bge-reranker-v2-m3",
"top_n": 2,
"rank_fields": ["chunk_text"] # Specified field must also be included in 'fields'
}
)
print(search_with_id)
{'result': {'hits': [{'_id': 'rec3',
'_score': 0.004399413242936134,
'fields': {'category': 'immune system',
'chunk_text': 'Rich in vitamin C and other '
'antioxidants, apples '
'contribute to immune health '
'and may reduce the risk of '
'chronic diseases.'}},
{'_id': 'rec4',
'_score': 0.0029235430993139744,
'fields': {'category': 'endocrine system',
'chunk_text': 'The high fiber content in '
'apples can also help regulate '
'blood sugar levels, making '
'them a favorable snack for '
'people with diabetes.'}}]},
'usage': {'embed_total_tokens': 8, 'read_units': 6, 'rerank_units': 1}}