krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-07 11:58:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs auto-sync

Browse Source
This commit is contained in:
qdrant
2023-05-26 23:50:14 +00:00
parent f3f5421226
commit 14c15d727a
11 changed files with 35 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/administration.md
+1 -1
View File
@@ -31,7 +31,7 @@ You can optionally provide the error message that should be used for error respo
## Recovery mode ## Recovery mode
*Available since v1.2.0* *Available as of v1.2.0*
Recovery mode can help in situations where Qdrant fails to start repeatedly. Recovery mode can help in situations where Qdrant fails to start repeatedly.
When starting in recovery mode, Qdrant only loads collection metadata to prevent When starting in recovery mode, Qdrant only loads collection metadata to prevent
qdrant-landing/content/documentation/collections.md
+3 -3
View File
@@ -63,7 +63,7 @@ See [schema definitions](https://qdrant.github.io/qdrant/redoc/index.html#operat
### Create collection from another collection ### Create collection from another collection
*Available since v1.0.0* *Available as of v1.0.0*
It is possible to initialize a collection from another existing collection. It is possible to initialize a collection from another existing collection.
@@ -103,7 +103,7 @@ client.recreate_collection(
### Collection with multiple vectors ### Collection with multiple vectors
*Available since v0.10.0* *Available as of v0.10.0*
It is possible to have multiple vectors per record. It is possible to have multiple vectors per record.
This feature allows for multiple vector storages per collection. This feature allows for multiple vector storages per collection.
@@ -144,7 +144,7 @@ client.recreate_collection(
For rare use cases, it is possible to create a collection without any vector storage. For rare use cases, it is possible to create a collection without any vector storage.
*Available since v1.1.1* *Available as of v1.1.1*
For each named vector you can optionally specify For each named vector you can optionally specify
[`hnsw_config`](../indexing/#vector-index) or [`hnsw_config`](../indexing/#vector-index) or
qdrant-landing/content/documentation/configuration.md
+1 -1
View File
@@ -223,7 +223,7 @@ tls:
## Validation ## Validation
*Available since v1.1.1* *Available as of v1.1.1*
The configuration is validated on startup. If a configuration is loaded but The configuration is validated on startup. If a configuration is loaded but
validation fails, a warning is logged. E.g.: validation fails, a warning is logged. E.g.:
qdrant-landing/content/documentation/distributed_deployment.md
+3 -3
View File
@@ -3,7 +3,7 @@ title: Distributed deployment
weight: 100 weight: 100
--- ---
Since version v0.8.0 Qdrant supports a distributed deployment mode. As of v0.8.0 Qdrant supports a distributed deployment mode.
In this mode, multiple Qdrant services communicate with each other to distribute the data across the peers to extend the storage capabilities and increase stability. In this mode, multiple Qdrant services communicate with each other to distribute the data across the peers to extend the storage capabilities and increase stability.
To enable distributed deployment - enable the cluster mode in the [configuration](../configuration) or using the ENV variable: `QDRANT__CLUSTER__ENABLED=true`. To enable distributed deployment - enable the cluster mode in the [configuration](../configuration) or using the ENV variable: `QDRANT__CLUSTER__ENABLED=true`.
@@ -160,7 +160,7 @@ For example, if you have 3 nodes, 6 shards could be a good option.
If you want to extend your cluster with new nodes or some nodes become slower than the others, it might be helpful to re-balance the shard distribution in the cluster. If you want to extend your cluster with new nodes or some nodes become slower than the others, it might be helpful to re-balance the shard distribution in the cluster.
*Since version v0.9.0*, Qdrant allows moving shards between nodes in the cluster and removing nodes from the cluster. *As of v0.9.0:* Qdrant allows moving shards between nodes in the cluster and removing nodes from the cluster.
This functionality unlocks the ability to dynamically scale the cluster size without downtime. This functionality unlocks the ability to dynamically scale the cluster size without downtime.
@@ -193,7 +193,7 @@ After that, Qdrant will exclude the node from the consensus, and the instance wi
## Replication ## Replication
*Since version v0.11.0*, Qdrant allows to replicate shards between nodes in the cluster. *As of v0.11.0:* Qdrant allows to replicate shards between nodes in the cluster.
Shard replication increases the reliability of the cluster by keeping several copies of a shard spread among the cluster. Shard replication increases the reliability of the cluster by keeping several copies of a shard spread among the cluster.
This ensure the availability of the shards in case of node failures, except if all replicas are lost. This ensure the availability of the shards in case of node failures, except if all replicas are lost.
qdrant-landing/content/documentation/filtering.md
+5 -5
View File
@@ -330,7 +330,7 @@ You can apply it to [keyword](../payload/#keyword), [integer](../payload/#intege
### Match Any ### Match Any
_Available since version 1.1.0_ *Available as of v1.1.0*
In case you want to check if the stored value is one of multiple values, you can use the Match Any condition. In case you want to check if the stored value is one of multiple values, you can use the Match Any condition.
Match Any works as a logical OR for the given values. It can also be described as a `IN` operator. Match Any works as a logical OR for the given values. It can also be described as a `IN` operator.
@@ -362,7 +362,7 @@ If the stored value is an array, it should have at least one value matching any
### Match Except ### Match Except
_Available since version 1.2.0_ *Available as of v1.2.0*
In case you want to check if the stored value is not one of multiple values, you can use the Match Except condition. In case you want to check if the stored value is not one of multiple values, you can use the Match Except condition.
Match Except works as a logical NOR for the given values. Match Except works as a logical NOR for the given values.
@@ -394,7 +394,7 @@ If the stored value is an array, it should have at least one value not matching
### Nested key ### Nested key
_Available since version 1.1.0_ *Available as of v1.1.0*
Payloads being arbitrary JSON object, it is likely that you will need to filter on a nested field. Payloads being arbitrary JSON object, it is likely that you will need to filter on a nested field.
@@ -553,7 +553,7 @@ This query would only output the point with id 2 as only Japan has a city with t
### Nested object filter ### Nested object filter
_Available since version 1.2.0_ *Available as of v1.2.0*
By default, the conditions are taking into account the entire payload of a point. By default, the conditions are taking into account the entire payload of a point.
@@ -767,7 +767,7 @@ client.scroll(
### Full Text Match ### Full Text Match
_Available since version 0.10.0_ *Available as of v0.10.0*
A special case of the `match` condition is the `text` match condition. A special case of the `match` condition is the `text` match condition.
It allows you to search for a specific substring, token or phrase within the text field. It allows you to search for a specific substring, token or phrase within the text field.
qdrant-landing/content/documentation/indexing.md
+2 -2
View File
@@ -54,7 +54,7 @@ You should not create an index for Boolean fields and fields with only a few pos
### Full-text index ### Full-text index
*Available since Qdrant v0.10.0* *Available as of v0.10.0*
Qdrant supports full-text search for string payload. Qdrant supports full-text search for string payload.
Full-text index allows you to filter points by the presence of a word or a phrase in the payload field. Full-text index allows you to filter points by the presence of a word or a phrase in the payload field.
@@ -143,7 +143,7 @@ HNSW is chosen for several reasons.
First, HNSW is well-compatible with the modification that allows Qdrant to use filters during a search. First, HNSW is well-compatible with the modification that allows Qdrant to use filters during a search.
Second, it is one of the most accurate and fastest algorithms, according to [public benchmarks](https://github.com/erikbern/ann-benchmarks). Second, it is one of the most accurate and fastest algorithms, according to [public benchmarks](https://github.com/erikbern/ann-benchmarks).
*Available since v1.1.1* *Available as of v1.1.1*
The HNSW parameters can also be configured on a collection and named vector The HNSW parameters can also be configured on a collection and named vector
level by setting [`hnsw_config`](../indexing/#vector-index) to fine-tune search level by setting [`hnsw_config`](../indexing/#vector-index) to fine-tune search
qdrant-landing/content/documentation/points.md
+5 -5
View File
@@ -250,7 +250,7 @@ In this case, it means that points with the same id will be overwritten when re-
Idempotence property is useful if you use, for example, a message queue that doesn't provide an exactly-ones guarantee. Idempotence property is useful if you use, for example, a message queue that doesn't provide an exactly-ones guarantee.
Even with such a system, Qdrant ensures data consistency. Even with such a system, Qdrant ensures data consistency.
*Available since v0.10.0* *Available as of v0.10.0*
If the collection was created with multiple vectors, each vector data can be provided using the vector's name: If the collection was created with multiple vectors, each vector data can be provided using the vector's name:
@@ -299,7 +299,7 @@ client.upsert(
) )
``` ```
*Available since v1.2.0* *Available as of v1.2.0*
Named vectors are optional. When uploading points, some vectors may be omitted. Named vectors are optional. When uploading points, some vectors may be omitted.
For example, you can upload one point with only the `image` vector and a second For example, you can upload one point with only the `image` vector and a second
@@ -317,7 +317,7 @@ ways to do this.
### Update vectors ### Update vectors
*Available since v1.2.0* *Available as of v1.2.0*
This method updates the specified vectors on the given points. Unspecified This method updates the specified vectors on the given points. Unspecified
vectors are kept unchanged. All given points must exist. vectors are kept unchanged. All given points must exist.
@@ -370,7 +370,7 @@ points](#upload-points).
### Delete vectors ### Delete vectors
*Available since v1.2.0* *Available as of v1.2.0*
This method deletes just the specified vectors from the given points. Other This method deletes just the specified vectors from the given points. Other
vectors are kept unchanged. Points are never deleted. vectors are kept unchanged. Points are never deleted.
@@ -724,7 +724,7 @@ Python client:
## Counting points ## Counting points
*Available since v0.8.4* *Available as of v0.8.4*
Sometimes it can be useful to know how many points fit the filter conditions without doing a real search. Sometimes it can be useful to know how many points fit the filter conditions without doing a real search.
qdrant-landing/content/documentation/quantization.md
+3 -3
View File
@@ -19,7 +19,7 @@ The level of this tradeoff depends on the quantization method and its parameters
## Scalar Quantization ## Scalar Quantization
*Available in Qdrant since v1.1.0* *Available as of v1.1.0*
Scalar quantization, in the context of vector search engines, is a compression technique that compresses vectors by reducing the number of bits used to represent each vector component. Scalar quantization, in the context of vector search engines, is a compression technique that compresses vectors by reducing the number of bits used to represent each vector component.
@@ -42,7 +42,7 @@ Please refer to the [Quantization Tips](#quantization-tips) section for more inf
## Product Quantization ## Product Quantization
*Available in Qdrant since v1.2.0* *Available as of v1.2.0*
Product quantization is a method of compressing vectors to minimize their memory usage by dividing them into Product quantization is a method of compressing vectors to minimize their memory usage by dividing them into
chunks and quantizing each segment individually. chunks and quantizing each segment individually.
@@ -63,7 +63,7 @@ You can configure quantization for a collection by specifying the quantization p
Quantization will be automatically applied to all vectors during the indexation process. Quantization will be automatically applied to all vectors during the indexation process.
Quantized vectors are stored alongside the original vectors in the collection, so you will still have access to the original vectors if you need them. Quantized vectors are stored alongside the original vectors in the collection, so you will still have access to the original vectors if you need them.
*Available since v1.1.1* *Available as of v1.1.1*
The `quantization_config` can also be set on a per vector basis by specifying it in a named vector. The `quantization_config` can also be set on a per vector basis by specifying it in a named vector.
qdrant-landing/content/documentation/search.md
+6 -6
View File
@@ -136,7 +136,7 @@ Example result of this API would be
The `result` contains ordered by `score` list of found point ids. The `result` contains ordered by `score` list of found point ids.
*Available since v0.10.0* *Available as of v0.10.0*
If the collection was created with multiple vectors, the name of the vector to use for searching should be provided: If the collection was created with multiple vectors, the name of the vector to use for searching should be provided:
@@ -232,7 +232,7 @@ client.search(
## Batch search API ## Batch search API
*Available since v0.10.0* *Available as of v0.10.0*
The batch search API enables to perform multiple search requests via a single request. The batch search API enables to perform multiple search requests via a single request.
@@ -416,7 +416,7 @@ Example result of this API would be
} }
``` ```
*Available since v0.10.0* *Available as of v0.10.0*
If the collection was created with multiple vectors, the name of the vector should be specified in the recommendation request: If the collection was created with multiple vectors, the name of the vector should be specified in the recommendation request:
@@ -445,7 +445,7 @@ Parameter `using` specifies which stored vectors to use for the recommendation.
## Batch recommendation API ## Batch recommendation API
*Available since v0.10.0* *Available as of v0.10.0*
Similar to the batch search API in terms of usage and advantages, it enables the batching of recommendation requests. Similar to the batch search API in terms of usage and advantages, it enables the batching of recommendation requests.
@@ -549,7 +549,7 @@ The result of this API contains one array per recommendation requests.
## Pagination ## Pagination
*Available since v0.8.3* *Available as of v0.8.3*
Search and recommendation APIs allow to skip first results of the search and return only the result starting from some specified offset: Search and recommendation APIs allow to skip first results of the search and return only the result starting from some specified offset:
@@ -595,7 +595,7 @@ Using an `offset` parameter, will require to internally retrieve `offset + limit
## Grouping API ## Grouping API
*Available since v1.2.0* *Available as of v1.2.0*
It is possible to group results by a certain field. This is useful when you have multiple points for the same item, and you want to avoid redundancy of the same item in the results. It is possible to group results by a certain field. This is useful when you have multiple points for the same item, and you want to avoid redundancy of the same item in the results.
qdrant-landing/content/documentation/snapshots.md
+5 -5
View File
@@ -3,7 +3,7 @@ title: Snapshots
weight: 110 weight: 110
--- ---
*Available since v0.8.4* *Available as of v0.8.4*
Snapshots are performed on a per collection basis and consist in a `tar` archive file containing the necessary data to restore the collection at the time of the snapshot. Snapshots are performed on a per collection basis and consist in a `tar` archive file containing the necessary data to restore the collection at the time of the snapshot.
@@ -41,7 +41,7 @@ This is a synchronous operation for which a `tar` archive file will be generated
### Delete snapshot ### Delete snapshot
*Available since v1.0.0* *Available as of v1.0.0*
```http ```http
DELETE /collections/{collection_name}/snapshots/{snapshot_name} DELETE /collections/{collection_name}/snapshots/{snapshot_name}
@@ -109,7 +109,7 @@ If you wish instead to overwrite an existing collection, use the `--force_snapsh
### Recover in cluster deployment ### Recover in cluster deployment
*Available since v0.11.3* *Available as of v0.11.3*
Recovering in cluster mode is more sophisticated, as Qdrant should maintain consistency across peers even during the recovery process. Recovering in cluster mode is more sophisticated, as Qdrant should maintain consistency across peers even during the recovery process.
As the information about created collections is stored in the consensus, even a newly attached cluster node will automatically create collections. As the information about created collections is stored in the consensus, even a newly attached cluster node will automatically create collections.
@@ -146,7 +146,7 @@ If there are other active replicas of the recovered shards in the cluster, Qdran
## Snapshots for the whole storage ## Snapshots for the whole storage
*Available since v0.8.5* *Available as of v0.8.5*
Sometimes it might be handy to create snapshot not just for a single collection, but for the whole storage, including collection aliases. Sometimes it might be handy to create snapshot not just for a single collection, but for the whole storage, including collection aliases.
Qdrant provides a dedicated API for that as well. It is similar to collection-level snapshots, but does not require `collecton_name`: Qdrant provides a dedicated API for that as well. It is similar to collection-level snapshots, but does not require `collecton_name`:
@@ -167,7 +167,7 @@ client.create_full_snapshot()
### Delete full storage snapshot ### Delete full storage snapshot
*Available since v1.0.0* *Available as of v1.0.0*
```http ```http
DELETE /snapshots/{snapshot_name} DELETE /snapshots/{snapshot_name}
qdrant-landing/content/documentation/storage.md
+1 -1
View File
@@ -41,7 +41,7 @@ There are two ways to configure the usage of mmap(also known as on-disk) storage
- Set up `on_disk` option for the vectors in the collection create API: - Set up `on_disk` option for the vectors in the collection create API:
**Available since v1.2.0** *Available as of v1.2.0*
```http ```http