mirror of
https://github.com/qdrant/landing_page.git
synced 2026-09-30 08:28:32 +02:00
Release 1 10 aggregated (#1005)
* Qdrant 1.10: describe IDF computation (#996) * describe IDF computation * add python snippet, fix typo * docs: Java, Csharp * add ts and rust examples * docs: Formatting Java, Csharp indexing.md * fix language --------- Co-authored-by: Luis Cossío <luis.cossio@outlook.com> Co-authored-by: Anush <anushshetty90@gmail.com> Co-authored-by: davidmyriel <davidmyriel@gmail.com> * Qdrant 1.10: add vectors page with description of vector types and datatypes (#995) * add vectors page with description of vector types and datatypes * docs: csharp vectors.md * docs: Java vectors.md * docs: Java, Csharp formatting * wip: rust and typescript snippets * Update qdrant-landing/content/documentation/concepts/vectors.md Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com> * Update qdrant-landing/content/documentation/concepts/vectors.md Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com> * add rest of snippets * add proofread and edit text --------- Co-authored-by: Anush <anushshetty90@gmail.com> Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com> Co-authored-by: davidmyriel <davidmyriel@gmail.com> * Qdrant 1.10.0: document S3 snapshots, reorganize storage text (#994) * Move snapshots storage section down, add local fs and S3 sub sections * Remove yaml suffix from S3 secrets * Update S3 example configuration, it didn't match latest release * Update GitHub Stars (#993) Co-authored-by: generall <generall@users.noreply.github.com> * Add documentation for the Query API [v1.10] (#990) * Add documentation for the Query API * review suggestions * upd url * Add rrf image, fix typos * easier intro image to fusion * add python snippets * docs: java, csharp * docs: csharp hybrid-queries.md * docs: Format hybrid-queries.md * Add Rust client search examples using Query API * docs: Java hybrid-queries.md * doc: Helper comment * Add Rust examples in hybrid queries * v1.10.0 typescript snippets (#999) * v1.10.0 typescript snippets * missed using * missed comments * missed docs * Address @agourlay's review * fix proofread & edit --------- Co-authored-by: generall <andrey@vasnetsov.com> Co-authored-by: Anush <anushshetty90@gmail.com> Co-authored-by: timvisee <tim@visee.me> Co-authored-by: Ivan Pleshkov <pleshkov.ivan@gmail.com> Co-authored-by: davidmyriel <davidmyriel@gmail.com> * [WIP] Version 1.10. Release Article (#992) * add release article draft * add wip links * fix article linnk * add more information * fix link * add parameters * add benchmark info * better issues window screenshot * fix image and descriptions * add last bits of info * update release header * fix title * docs: Java, Csharp snippets * docs: Fixed typos * Removed first Java, C# snippets for a simpler intro * Update S3 snapshot storage, link to configuration section * Update S3 configuration example * Add Rust examples * Update new Rust client text * Mention ColBERT Rust snippet as good client example * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * Update qdrant-landing/content/blog/qdrant-1.10.x.md Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * add last few changes * Fix internal link * Update Rust documentation links to point to specific version --------- Co-authored-by: Luis Cossío <luis.cossio@outlook.com> Co-authored-by: Anush <anushshetty90@gmail.com> Co-authored-by: timvisee <tim@visee.me> Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> * upd links in release blog post * dont use links with domain * [draft] bm 42 article (#969) * bm 42 article draft * upd the article * BPE -> wordpiece * azeret mono as fallback font * testing other fallback for monospace font * self hosted fonts * only proofread & edit * Update qdrant-landing/content/articles/bm42.md * last fixes --------- Co-authored-by: trean <trean.mi@gmail.com> Co-authored-by: davidmyriel <davidmyriel@gmail.com> * fix link --------- Co-authored-by: Luis Cossío <luis.cossio@outlook.com> Co-authored-by: Anush <anushshetty90@gmail.com> Co-authored-by: davidmyriel <davidmyriel@gmail.com> Co-authored-by: Arnaud Gourlay <arnaud.gourlay@gmail.com> Co-authored-by: Tim Visée <tim@visee.me> Co-authored-by: generall <generall@users.noreply.github.com> Co-authored-by: Luis Cossío <luis.cossio@qdrant.com> Co-authored-by: Ivan Pleshkov <pleshkov.ivan@gmail.com> Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com> Co-authored-by: trean <trean.mi@gmail.com>
This commit is contained in:
co-authored by
Luis Cossío
Anush
davidmyriel
Arnaud Gourlay
generall
timvisee
Ivan Pleshkov
Kacper Łukawski
trean
Luis Cossío
parent
ad6630b260
commit
f5cd7a09fe
@@ -8,7 +8,18 @@ aliases:
|
||||
# Points
|
||||
|
||||
The points are the central entity that Qdrant operates with.
|
||||
A point is a record consisting of a vector and an optional [payload](../payload/).
|
||||
A point is a record consisting of a [vector](../vectors/) and an optional [payload](../payload/).
|
||||
|
||||
It looks like this:
|
||||
|
||||
```json
|
||||
// This is a simple point
|
||||
{
|
||||
"id": 129,
|
||||
"vector": [0.1, 0.2, 0.3, 0.4],
|
||||
"payload": {"color": "red"},
|
||||
}
|
||||
```
|
||||
|
||||
You can search among the points grouped in one [collection](../collections/) based on vector similarity.
|
||||
This procedure is described in more detail in the [search](../search/) and [filtering](../filtering/) sections.
|
||||
@@ -20,40 +31,6 @@ At the first stage, the operation is written to the Write-ahead-log.
|
||||
|
||||
After this moment, the service will not lose the data, even if the machine loses power supply.
|
||||
|
||||
## Awaiting result
|
||||
|
||||
If the API is called with the `&wait=false` parameter, or if it is not explicitly specified, the client will receive an acknowledgment of receiving data:
|
||||
|
||||
```json
|
||||
{
|
||||
"result": {
|
||||
"operation_id": 123,
|
||||
"status": "acknowledged"
|
||||
},
|
||||
"status": "ok",
|
||||
"time": 0.000206061
|
||||
}
|
||||
```
|
||||
|
||||
This response does not mean that the data is available for retrieval yet. This
|
||||
uses a form of eventual consistency. It may take a short amount of time before it
|
||||
is actually processed as updating the collection happens in the background. In
|
||||
fact, it is possible that such request eventually fails.
|
||||
If inserting a lot of vectors, we also recommend using asynchronous requests to take advantage of pipelining.
|
||||
|
||||
If the logic of your application requires a guarantee that the vector will be available for searching immediately after the API responds, then use the flag `?wait=true`.
|
||||
In this case, the API will return the result only after the operation is finished:
|
||||
|
||||
```json
|
||||
{
|
||||
"result": {
|
||||
"operation_id": 0,
|
||||
"status": "completed"
|
||||
},
|
||||
"status": "ok",
|
||||
"time": 0.000206061
|
||||
}
|
||||
```
|
||||
|
||||
## Point IDs
|
||||
|
||||
@@ -306,6 +283,26 @@ await client.UpsertAsync(
|
||||
|
||||
are both possible.
|
||||
|
||||
## Vectors
|
||||
|
||||
Each point in qdrant may have one or more vectors.
|
||||
Vectors are the central component of the Qdrant architecture,
|
||||
qdrant relies on different types of vectors to provide different types of data exploration and search.
|
||||
|
||||
Here is a list of supported vector types:
|
||||
|
||||
|||
|
||||
|-|-|
|
||||
| Dense Vectors | A regular vectors, generated by majority of the embedding models. |
|
||||
| Sparse Vectors | Vectors with no fixed length, but only a few non-zero elements. <br> Useful for exact token match and collaborative filtering recommendations. |
|
||||
| MultiVectors | Matrices of numbers with fixed length but variable height. <br> Usually obtained from late interraction models like ColBERT. |
|
||||
|
||||
It is possible to attach more than one type of vector to a single point.
|
||||
In Qdrant we call it Named Vectors.
|
||||
|
||||
Read more about vector types, how they are stored and optimized in the [vectors](../vectors/) section.
|
||||
|
||||
|
||||
## Upload points
|
||||
|
||||
To optimize performance, Qdrant supports batch loading of points. I.e., you can load several points into the service in one API call.
|
||||
@@ -2306,3 +2303,39 @@ client
|
||||
|
||||
To batch many points with a single operation type, please use batching
|
||||
functionality in that operation directly.
|
||||
|
||||
|
||||
## Awaiting result
|
||||
|
||||
If the API is called with the `&wait=false` parameter, or if it is not explicitly specified, the client will receive an acknowledgment of receiving data:
|
||||
|
||||
```json
|
||||
{
|
||||
"result": {
|
||||
"operation_id": 123,
|
||||
"status": "acknowledged"
|
||||
},
|
||||
"status": "ok",
|
||||
"time": 0.000206061
|
||||
}
|
||||
```
|
||||
|
||||
This response does not mean that the data is available for retrieval yet. This
|
||||
uses a form of eventual consistency. It may take a short amount of time before it
|
||||
is actually processed as updating the collection happens in the background. In
|
||||
fact, it is possible that such request eventually fails.
|
||||
If inserting a lot of vectors, we also recommend using asynchronous requests to take advantage of pipelining.
|
||||
|
||||
If the logic of your application requires a guarantee that the vector will be available for searching immediately after the API responds, then use the flag `?wait=true`.
|
||||
In this case, the API will return the result only after the operation is finished:
|
||||
|
||||
```json
|
||||
{
|
||||
"result": {
|
||||
"operation_id": 0,
|
||||
"status": "completed"
|
||||
},
|
||||
"status": "ok",
|
||||
"time": 0.000206061
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user