RE: Vector based store and ANN

[Pedram Rezaei]

Merging the threads and pasting all the replies into here and responding to 
them below:

Thank you all for your detailed and thoughtful contributions.

Here at Bing, we used to use the coarse approximation nearest neighbor approach 
(using something similar to the LSH hashing technique) on the inverted index 
and a finer-grained final rescoring method. However, for Bing, we have seen a 
visible impact on relevance using ANN. This even applies to smaller indexes 
with 20M records. We also find that recall varies on LSH on our interested 
dataset. Hence we adopted KD-tree & RNG which has more stable recall. The 
algorithm is open sourced here<https://github.com/Microsoft/SPTAG>. We have 
also seen success with HNSW and FAISS.

The links provided by Doug and J. are attempting to add vectors to the existing 
index. These solutions typically inefficient on medium to large size indexes if 
used for online querying as they tend to behave more like a linear search. The 
author of EsAknn has also alluded to this on its github 
page<https://github.com/alexklibisz/elastik-nearest-neighbors/>:

“If you need to quickly run KNN on an extremely large corpus in an offline job, 
use one of the libraries from 
Ann-Benchmarks<https://github.com/erikbern/ann-benchmarks>. If you need KNN in 
an online setting with support for horizontally-scalable searching and indexing 
new vectors in near-real-time, consider EsAknn (especially if you already use 
Elasticsearch).”

Using a vector-based index tuned for ANN searches, with an ability to hook in 
other index formats and algorithms as Rene requested below, we can provide a 
solution that can, for example, index and serve hundreds of millions of images 
and offers fast query over those indexes. We use these algorithms and indexes 
that are referenced above for image and text search. The user can choose the 
most relevant one or even combine multiple of those before the final scoring.

I would love to hear your thoughts on this and see if the community is open to 
a proposal by Bing on contributing some of its tech to Lucene. We will run the 
design and the development incrementally with the full input from the community.

Thanks,

Pedram

From: Doug Turnbull 
Sent: Saturday, March 2, 2019 3:50 PM
To: dev@lucene.apache.org
Cc: Pedram Rezaei ; Radhakrishnan Srikanth (SRIKANTH) 
; Arun Sacheti ; Kun Wu 
; Junhua Wang ; Jason Li 

Subject: Re: Vector based store and ANN

I'll add that Elasticsearch has a vector scoring (though not 
filtering/matching) coming in to Elasticsearch mainline by Mayya Sharipova

https://github.com/elastic/elasticsearch/pull/33022<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Felastic%2Felasticsearch%2Fpull%2F33022=02%7C01%7Cpedramr%40microsoft.com%7C199a871ace7f4bc9898408d69f69e825%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636871674551616746=2GS4Wwienaw3Bnb0kHaA1MKooVVNfkreG9f4F3FPfSk%3D=0>

It uses doc values to do some reranking using standard similarities. It's a 
start, hopefully something that can be built upon

Hoping Mayya can be at Haystack... vector filtering/similarities/use cases 
could even be its own breakout/collaboration session

From: René Kriegler 
Sent: Saturday, March 2, 2019 3:23 PM
To: J. Delgado 
Cc: dev@lucene.apache.org; Radhakrishnan Srikanth (SRIKANTH) 
; Arun Sacheti ; Kun Wu 
; Junhua Wang ; Jason Li 

Subject: Re: Vector based store and ANN

Thanks for the links, Joaquin!

Yet another thought related to an implementation at Lucene level: I wonder how 
much sense it makes to try to implement a one-approach-fits-all solution for 
vector-based retrieval. We have different expectations of a solution, depending 
on aspects such as vector dimensionality, domain (text vs. image recognition 
vs. …) and retrieval quality priorities (recall vs precision). I think that was 
also reflected in the Slack discussion. I think it would be very helpful to 
have real-life vector datasets (labelled for specific retrieval tasks), so that 
we could benchmarks solutions for retrieval speed and quality metrics. For 
example, we could easily create synthetic vector datasets for KNN search (which 
is still a good starting point!) - but using random vectors probably doesn’t 
reflect the distribution we would normally face in an image search or when 
searching by word embeddings.

Best,
René

On 2 Mar 2019, at 22:06, J. Delgado 
mailto:joaquin.delg...@gmail.com>> wrote:

Apparently, there is already an implementation along the lines discussed here:

https://blog.insightdatascience.com/elastik-nearest-neighbors-4b1f6821bd62<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fblog.insightdatascience.com%2Felastik-nearest-neighbors-4b1f6821bd62=02%7C01%7Cpedramr%40microsoft.com%7C11383da6057f4f387d8e08d69f66159f%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636871658141994760=pV5mDyNJtpXYZmaggUtAeWL%2BrcqbX%2BSp2peyhp%2FcV2k%3D=0>
https://github.com/alexklibisz/

Re: Vector based store and ANN

[Doug Turnbull]

I'll add that Elasticsearch has a vector scoring (though not
filtering/matching) coming in to Elasticsearch mainline by Mayya Sharipova

https://github.com/elastic/elasticsearch/pull/33022

It uses doc values to do some reranking using standard similarities. It's a
start, hopefully something that can be built upon

Hoping Mayya can be at Haystack... vector filtering/similarities/use cases
could even be its own breakout/collaboration session

On Fri, Mar 1, 2019 at 8:59 PM René Kriegler  wrote:

> Hi there,
>
> Thank you for looping me in. Just a few random thoughts on this topic:
>
> - I’ve heard ;-) that this ES plugin is fast for vector-based scoring:
> https://github.com/StaySense/fast-cosine-similarity. The links in the
> ‘General’ section provide some history. As far as I can see, there is
> nothing which couldn’t be implemented at Lucene level.
>
> - For retrieval, I think a two-pass approach looks like something worth
> trying out. First pass: look up documents in a low dimensional space (maybe
> produced via LSH) and then, in the second pass, calculate vector distances
> in the high-dimensional space just for the documents that resulted from the
> first pass. This solution will come with some compromises to make. For
> example, a higher dimensionality of LSH would increase precision but also
> produce more hash tokens and make the lookup slower, especially for large
> indexes.
>
> - Day 2 of Haystack 2019 (https://haystackconf.com/agenda/) will have a
> talk by Simon Hughes about ’Search with Vectors’. There is a channel on
> this topic at OpenSource Connections’ search relevance Slack (
> https://relevancy.slack.com) and Simon has been one of the drivers of the
> discussion.
>
> Best,
> René
>
>
> On 1 Mar 2019, at 20:51, Pedram Rezaei  wrote:
>
> Thank you for sharing, and it is exciting to see how advanced your
> thinking is.
>
> Yes, the idea is the same idea with an extra step that Rene also seems to
> elude to here
> <https://www.slideshare.net/RenKriegler/a-picture-is-worth-a-thousand-words-93680178>
>  in his comment. Instead of using these types of techniques only at the
> scoring time, we can use them for information retrieval from the index.
> This will allow us to, for example, index millions of images and quickly
> and efficiently lookup the most relevant images.
>
> I would love to hear yours and others thoughts on this. I think there is a
> great opportunity here, but it would need a lot of input and guidance from
> the experts here.
>
> Thank you,
>
> Pedram
>
> *From:* David Smiley 
> *Sent:* Friday, March 1, 2019 12:11 PM
> *To:* dev@lucene.apache.org
> *Cc:* Radhakrishnan Srikanth (SRIKANTH) ; Arun
> Sacheti ; Kun Wu ; Junhua Wang <
> junhua.w...@microsoft.com>; Jason Li ; René Kriegler
> 
> *Subject:* Re: Vector based store and ANN
>
> This presentation by Rene Kriegler at Haystack 2018 was a real eye-opener
> to me on this subject: https://haystackconf.com/2018/relevance-scoring/
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2F2018%2Frelevance-scoring%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908753995=sD7ZF4x1iXIjJ1GDAwlc0lUWkTpkarEkd2SAXI5qev0%3D=0>.
>  Uses
> random-projection forests which is a very clever technique.  (CC'ing Rene)
>
>
> ~ David
> On Fri, Mar 1, 2019 at 1:30 PM Pedram Rezaei <
> pedr...@microsoft.com.invalid> wrote:
>
> Hi there,
>
> Thank you for the responses. Yes, we have a few scenarios in mind that can
> benefit from a vector-based index optimized for ANN searches:
>
>
>- Advanced, optimized, and high precision visual search: For this to
>work, we would convert the images to their vector representations and then
>use algorithms and implementations such as SPTAG
>
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FMicrosoft%2FSPTAG=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=pOKRUksZ4sTsgtbE7eW88kiFLovTAQJRiPz%2F2LQXvCg%3D=0>
>, FAISS
>
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ffacebookresearch%2Ffaiss=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=if7uUn9OysK1c%2FDh6qb7hLcWGuaDjU9W5gKF2JQzOrk%3D=0>,
>and HNSWLIB
>
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnmslib%2Fhnswlib=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908774009=%2BFHGSAWnlsfe%2BhLii

Re: Vector based store and ANN

[Doug Turnbull]

Hi Pedram (and community)

The invite link for Relevance slack is http://o19s.com/slack ...

Best!
-Doug

On Fri, Mar 1, 2019 at 7:23 PM Pedram Rezaei 
wrote:

> Hi there,
>
>
>
> Thank you for sharing your thoughts. I am finding them extremely useful
> and to be honest exciting!
>
>
>
> Regarding the vector-based scoring, you are 100% correct. There are many
> ways of having an efficient vector-based similarity scorer implemented on
> top of an encoded vector stored at the document level in Lucene.
>
>
>
> As you have rightly pointed out, this in itself might not be sufficient
> for large indexes. After all, the engine would need to read the vector per
> document and then calculate similarity.
>
>
>
> LSH or similar n-pass (n>1) techniques are pretty interesting and
> certainly can get us closer to using the existing index for lookup. As you
> rightly point out below, it can come at a cost either to the performance or
> the precision.
>
>
>
> I am personally very intrigued by the new generation of vector-based
> indexes such as Facebook’s FAISS
> <https://github.com/facebookresearch/faiss> library for similarity search
> and clustering of dense vectors used as part of larger search offerings. Do
> you think there might be a world in which Lucene would want to have
> first-class support for vector-based searches? I think with such a
> capability, we might open the door for new and innovative ways of
> information retrieval.
>
>
>
> I am grateful to you all for your insights and this fascinating discussion!
>
>
>
> Pedram
>
>
>
> P.S. How do I join https://relevancy.slack.com
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>
> ?
>
>
>
> *From:* René Kriegler 
> *Sent:* Friday, March 1, 2019 3:24 PM
> *To:* Pedram Rezaei 
> *Cc:* dev@lucene.apache.org; Radhakrishnan Srikanth (SRIKANTH) <
> rsri...@microsoft.com>; Arun Sacheti ; Kun Wu <
> wu@microsoft.com>; Junhua Wang ; Jason Li <
> ja...@microsoft.com>
> *Subject:* Re: Vector based store and ANN
>
>
>
> Hi there,
>
>
>
> Thank you for looping me in. Just a few random thoughts on this topic:
>
>
>
> - I’ve heard ;-) that this ES plugin is fast for vector-based scoring:
> https://github.com/StaySense/fast-cosine-similarity
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStaySense%2Ffast-cosine-similarity=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499747411=kHEdnvi3o9ZfSAiE%2FJQIhbI54Zf%2BLEwr%2F%2B40tpFDnv8%3D=0>.
> The links in the ‘General’ section provide some history. As far as I can
> see, there is nothing which couldn’t be implemented at Lucene level.
>
>
>
> - For retrieval, I think a two-pass approach looks like something worth
> trying out. First pass: look up documents in a low dimensional space (maybe
> produced via LSH) and then, in the second pass, calculate vector distances
> in the high-dimensional space just for the documents that resulted from the
> first pass. This solution will come with some compromises to make. For
> example, a higher dimensionality of LSH would increase precision but also
> produce more hash tokens and make the lookup slower, especially for large
> indexes.
>
>
>
> - Day 2 of Haystack 2019 (https://haystackconf.com/agenda/
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2Fagenda%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=6cD7%2BHoxVsuozhLN27m7Jmowv3D4CUYtVHCipGRO8Ss%3D=0>)
> will have a talk by Simon Hughes about ’Search with Vectors’. There is a
> channel on this topic at OpenSource Connections’ search relevance Slack (
> https://relevancy.slack.com
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>)
> and Simon has been one of the drivers of the discussion.
>
>
>
> Best,
>
> René
>
>
>
>
>
> On 1 Mar 2019, at 20:51, Pedram Rezaei  wrote:
>
>
>
> Thank you for sharing, and it is exciting to see how advanced your
> thinking is.
>
>
>
> Yes, the idea is the same idea with an extra step that Rene also seems to
> elude to here
> <

Re: Vector based store and ANN

[René Kriegler]

Thanks for the links, Joaquin!

Yet another thought related to an implementation at Lucene level: I wonder how 
much sense it makes to try to implement a one-approach-fits-all solution for 
vector-based retrieval. We have different expectations of a solution, depending 
on aspects such as vector dimensionality, domain (text vs. image recognition 
vs. …) and retrieval quality priorities (recall vs precision). I think that was 
also reflected in the Slack discussion. I think it would be very helpful to 
have real-life vector datasets (labelled for specific retrieval tasks), so that 
we could benchmarks solutions for retrieval speed and quality metrics. For 
example, we could easily create synthetic vector datasets for KNN search (which 
is still a good starting point!) - but using random vectors probably doesn’t 
reflect the distribution we would normally face in an image search or when 
searching by word embeddings.

Best,
René


> On 2 Mar 2019, at 22:06, J. Delgado  wrote:
> 
> Apparently, there is already an implementation along the lines discussed here:
> 
> https://blog.insightdatascience.com/elastik-nearest-neighbors-4b1f6821bd62 
> <https://blog.insightdatascience.com/elastik-nearest-neighbors-4b1f6821bd62>
> https://github.com/alexklibisz/elastik-nearest-neighbors/ 
> <https://github.com/alexklibisz/elastik-nearest-neighbors/>
> 
> -- J
> 
> On Fri, Mar 1, 2019 at 4:23 PM Pedram Rezaei  
> wrote:
> Hi there,
> 
>  
> 
> Thank you for sharing your thoughts. I am finding them extremely useful and 
> to be honest exciting!
> 
>  
> 
> Regarding the vector-based scoring, you are 100% correct. There are many ways 
> of having an efficient vector-based similarity scorer implemented on top of 
> an encoded vector stored at the document level in Lucene.
> 
>  
> 
> As you have rightly pointed out, this in itself might not be sufficient for 
> large indexes. After all, the engine would need to read the vector per 
> document and then calculate similarity.
> 
>  
> 
> LSH or similar n-pass (n>1) techniques are pretty interesting and certainly 
> can get us closer to using the existing index for lookup. As you rightly 
> point out below, it can come at a cost either to the performance or the 
> precision.
> 
>  
> 
> I am personally very intrigued by the new generation of vector-based indexes 
> such as Facebook’s FAISS <https://github.com/facebookresearch/faiss> library 
> for similarity search and clustering of dense vectors used as part of larger 
> search offerings. Do you think there might be a world in which Lucene would 
> want to have first-class support for vector-based searches? I think with such 
> a capability, we might open the door for new and innovative ways of 
> information retrieval.
> 
>  
> 
> I am grateful to you all for your insights and this fascinating discussion!
> 
>  
> 
> Pedram
> 
>  
> 
> P.S. How do I join https://relevancy.slack.com 
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>?
> 
>  
> 
> From: René Kriegler mailto:r...@rene-kriegler.de>> 
> Sent: Friday, March 1, 2019 3:24 PM
> To: Pedram Rezaei mailto:pedr...@microsoft.com>>
> Cc: dev@lucene.apache.org <mailto:dev@lucene.apache.org>; Radhakrishnan 
> Srikanth (SRIKANTH) mailto:rsri...@microsoft.com>>; 
> Arun Sacheti mailto:ar...@bing.com>>; Kun Wu 
> mailto:wu@microsoft.com>>; Junhua Wang 
> mailto:junhua.w...@microsoft.com>>; Jason Li 
> mailto:ja...@microsoft.com>>
> Subject: Re: Vector based store and ANN
> 
>  
> 
> Hi there,
> 
>  
> 
> Thank you for looping me in. Just a few random thoughts on this topic: 
> 
>  
> 
> - I’ve heard ;-) that this ES plugin is fast for vector-based scoring: 
> https://github.com/StaySense/fast-cosine-similarity 
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStaySense%2Ffast-cosine-similarity=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499747411=kHEdnvi3o9ZfSAiE%2FJQIhbI54Zf%2BLEwr%2F%2B40tpFDnv8%3D=0>.
>  The links in the ‘General’ section provide some history. As far as I can 
> see, there is nothing which couldn’t be implemented at Lucene level.
> 
>  
> 
> - For retrieval, I think a two-pass approach looks like something worth 
> trying out. First pass: look up documents in a low dimensional space (maybe 
> produced via LSH) and then, in the second pass, calculate vector dis

Re: Vector based store and ANN

[J. Delgado]

Apparently, there is already an implementation along the lines discussed
here:

https://blog.insightdatascience.com/elastik-nearest-neighbors-4b1f6821bd62
https://github.com/alexklibisz/elastik-nearest-neighbors/

-- J

On Fri, Mar 1, 2019 at 4:23 PM Pedram Rezaei 
wrote:

> Hi there,
>
>
>
> Thank you for sharing your thoughts. I am finding them extremely useful
> and to be honest exciting!
>
>
>
> Regarding the vector-based scoring, you are 100% correct. There are many
> ways of having an efficient vector-based similarity scorer implemented on
> top of an encoded vector stored at the document level in Lucene.
>
>
>
> As you have rightly pointed out, this in itself might not be sufficient
> for large indexes. After all, the engine would need to read the vector per
> document and then calculate similarity.
>
>
>
> LSH or similar n-pass (n>1) techniques are pretty interesting and
> certainly can get us closer to using the existing index for lookup. As you
> rightly point out below, it can come at a cost either to the performance or
> the precision.
>
>
>
> I am personally very intrigued by the new generation of vector-based
> indexes such as Facebook’s FAISS
> <https://github.com/facebookresearch/faiss> library for similarity search
> and clustering of dense vectors used as part of larger search offerings. Do
> you think there might be a world in which Lucene would want to have
> first-class support for vector-based searches? I think with such a
> capability, we might open the door for new and innovative ways of
> information retrieval.
>
>
>
> I am grateful to you all for your insights and this fascinating discussion!
>
>
>
> Pedram
>
>
>
> P.S. How do I join https://relevancy.slack.com
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>
> ?
>
>
>
> *From:* René Kriegler 
> *Sent:* Friday, March 1, 2019 3:24 PM
> *To:* Pedram Rezaei 
> *Cc:* dev@lucene.apache.org; Radhakrishnan Srikanth (SRIKANTH) <
> rsri...@microsoft.com>; Arun Sacheti ; Kun Wu <
> wu@microsoft.com>; Junhua Wang ; Jason Li <
> ja...@microsoft.com>
> *Subject:* Re: Vector based store and ANN
>
>
>
> Hi there,
>
>
>
> Thank you for looping me in. Just a few random thoughts on this topic:
>
>
>
> - I’ve heard ;-) that this ES plugin is fast for vector-based scoring:
> https://github.com/StaySense/fast-cosine-similarity
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStaySense%2Ffast-cosine-similarity=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499747411=kHEdnvi3o9ZfSAiE%2FJQIhbI54Zf%2BLEwr%2F%2B40tpFDnv8%3D=0>.
> The links in the ‘General’ section provide some history. As far as I can
> see, there is nothing which couldn’t be implemented at Lucene level.
>
>
>
> - For retrieval, I think a two-pass approach looks like something worth
> trying out. First pass: look up documents in a low dimensional space (maybe
> produced via LSH) and then, in the second pass, calculate vector distances
> in the high-dimensional space just for the documents that resulted from the
> first pass. This solution will come with some compromises to make. For
> example, a higher dimensionality of LSH would increase precision but also
> produce more hash tokens and make the lookup slower, especially for large
> indexes.
>
>
>
> - Day 2 of Haystack 2019 (https://haystackconf.com/agenda/
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2Fagenda%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=6cD7%2BHoxVsuozhLN27m7Jmowv3D4CUYtVHCipGRO8Ss%3D=0>)
> will have a talk by Simon Hughes about ’Search with Vectors’. There is a
> channel on this topic at OpenSource Connections’ search relevance Slack (
> https://relevancy.slack.com
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>)
> and Simon has been one of the drivers of the discussion.
>
>
>
> Best,
>
> René
>
>
>
>
>
> On 1 Mar 2019, at 20:51, Pedram Rezaei  wrote:
>
>
>
> Thank you for sharing, and it is exciting to see how advanced your
> thinking is.

Re: Vector based store and ANN

[René Kriegler]

Hi there,

Thank you for looping me in. Just a few random thoughts on this topic: 

- I’ve heard ;-) that this ES plugin is fast for vector-based scoring: 
https://github.com/StaySense/fast-cosine-similarity. The links in the ‘General’ 
section provide some history. As far as I can see, there is nothing which 
couldn’t be implemented at Lucene level.

- For retrieval, I think a two-pass approach looks like something worth trying 
out. First pass: look up documents in a low dimensional space (maybe produced 
via LSH) and then, in the second pass, calculate vector distances in the 
high-dimensional space just for the documents that resulted from the first 
pass. This solution will come with some compromises to make. For example, a 
higher dimensionality of LSH would increase precision but also produce more 
hash tokens and make the lookup slower, especially for large indexes.

- Day 2 of Haystack 2019 (https://haystackconf.com/agenda/) will have a talk by 
Simon Hughes about ’Search with Vectors’. There is a channel on this topic at 
OpenSource Connections’ search relevance Slack (https://relevancy.slack.com) 
and Simon has been one of the drivers of the discussion.

Best,
René


> On 1 Mar 2019, at 20:51, Pedram Rezaei  wrote:
> 
> Thank you for sharing, and it is exciting to see how advanced your thinking 
> is.
>  
> Yes, the idea is the same idea with an extra step that Rene also seems to 
> elude to here 
> <https://www.slideshare.net/RenKriegler/a-picture-is-worth-a-thousand-words-93680178>
>  in his comment. Instead of using these types of techniques only at the 
> scoring time, we can use them for information retrieval from the index. This 
> will allow us to, for example, index millions of images and quickly and 
> efficiently lookup the most relevant images.
>  
> I would love to hear yours and others thoughts on this. I think there is a 
> great opportunity here, but it would need a lot of input and guidance from 
> the experts here.
>  
> Thank you,
>  
> Pedram
>  
> From: David Smiley  
> Sent: Friday, March 1, 2019 12:11 PM
> To: dev@lucene.apache.org
> Cc: Radhakrishnan Srikanth (SRIKANTH) ; Arun Sacheti 
> ; Kun Wu ; Junhua Wang 
> ; Jason Li ; René Kriegler 
> 
> Subject: Re: Vector based store and ANN
>  
> This presentation by Rene Kriegler at Haystack 2018 was a real eye-opener to 
> me on this subject: https://haystackconf.com/2018/relevance-scoring/ 
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2F2018%2Frelevance-scoring%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908753995=sD7ZF4x1iXIjJ1GDAwlc0lUWkTpkarEkd2SAXI5qev0%3D=0>.
>  Uses random-projection forests which is a very clever technique.  (CC'ing 
> Rene)
>  
> ~ David
> 
> On Fri, Mar 1, 2019 at 1:30 PM Pedram Rezaei  <mailto:pedr...@microsoft.com.invalid>> wrote:
> Hi there,
>  
> Thank you for the responses. Yes, we have a few scenarios in mind that can 
> benefit from a vector-based index optimized for ANN searches:
>  
> Advanced, optimized, and high precision visual search: For this to work, we 
> would convert the images to their vector representations and then use 
> algorithms and implementations such as SPTAG 
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FMicrosoft%2FSPTAG=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=pOKRUksZ4sTsgtbE7eW88kiFLovTAQJRiPz%2F2LQXvCg%3D=0>,
>  FAISS 
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ffacebookresearch%2Ffaiss=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=if7uUn9OysK1c%2FDh6qb7hLcWGuaDjU9W5gKF2JQzOrk%3D=0>,
>  and HNSWLIB 
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnmslib%2Fhnswlib=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908774009=%2BFHGSAWnlsfe%2BhLiimjz1T%2B3YMH90pO%2FXSi15Eszzmg%3D=0>.
> Advanced document retrieval: Using a numerical vector representation of a 
> document, we could improve the search result
> Nearest neighbor queries: discovering the nearest neighbors to a given query 
> could also benefit from these ANN algorithms (although doesn’t necessarily 
> need the vector based index)
>  
> I would be grateful to hear your thoughts and whether the community is open 
> to a conversation on this topic with my team.
>  
> Thanks,
>  
> Pedram
>  
> From: J. Delgado  <mailto:joaquin.delg...@gmail.com>> 
> Sent: Thursday, February 28, 2019 7:38 

RE: Vector based store and ANN

[Pedram Rezaei]

Hi there,

Thank you for sharing your thoughts. I am finding them extremely useful and to 
be honest exciting!

Regarding the vector-based scoring, you are 100% correct. There are many ways 
of having an efficient vector-based similarity scorer implemented on top of an 
encoded vector stored at the document level in Lucene.

As you have rightly pointed out, this in itself might not be sufficient for 
large indexes. After all, the engine would need to read the vector per document 
and then calculate similarity.

LSH or similar n-pass (n>1) techniques are pretty interesting and certainly can 
get us closer to using the existing index for lookup. As you rightly point out 
below, it can come at a cost either to the performance or the precision.

I am personally very intrigued by the new generation of vector-based indexes 
such as Facebook’s FAISS<https://github.com/facebookresearch/faiss> library for 
similarity search and clustering of dense vectors used as part of larger search 
offerings. Do you think there might be a world in which Lucene would want to 
have first-class support for vector-based searches? I think with such a 
capability, we might open the door for new and innovative ways of information 
retrieval.

I am grateful to you all for your insights and this fascinating discussion!

Pedram

P.S. How do I join 
https://relevancy.slack.com<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>?

From: René Kriegler 
Sent: Friday, March 1, 2019 3:24 PM
To: Pedram Rezaei 
Cc: dev@lucene.apache.org; Radhakrishnan Srikanth (SRIKANTH) 
; Arun Sacheti ; Kun Wu 
; Junhua Wang ; Jason Li 

Subject: Re: Vector based store and ANN

Hi there,

Thank you for looping me in. Just a few random thoughts on this topic:

- I’ve heard ;-) that this ES plugin is fast for vector-based scoring: 
https://github.com/StaySense/fast-cosine-similarity<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStaySense%2Ffast-cosine-similarity=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499747411=kHEdnvi3o9ZfSAiE%2FJQIhbI54Zf%2BLEwr%2F%2B40tpFDnv8%3D=0>.
 The links in the ‘General’ section provide some history. As far as I can see, 
there is nothing which couldn’t be implemented at Lucene level.

- For retrieval, I think a two-pass approach looks like something worth trying 
out. First pass: look up documents in a low dimensional space (maybe produced 
via LSH) and then, in the second pass, calculate vector distances in the 
high-dimensional space just for the documents that resulted from the first 
pass. This solution will come with some compromises to make. For example, a 
higher dimensionality of LSH would increase precision but also produce more 
hash tokens and make the lookup slower, especially for large indexes.

- Day 2 of Haystack 2019 
(https://haystackconf.com/agenda/<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2Fagenda%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=6cD7%2BHoxVsuozhLN27m7Jmowv3D4CUYtVHCipGRO8Ss%3D=0>)
 will have a talk by Simon Hughes about ’Search with Vectors’. There is a 
channel on this topic at OpenSource Connections’ search relevance Slack 
(https://relevancy.slack.com<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Frelevancy.slack.com=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499757411=p41mJtw39mq5qG5oy3MZOEWHT%2BrfFqeANLhFcLOtIIo%3D=0>)
 and Simon has been one of the drivers of the discussion.

Best,
René



On 1 Mar 2019, at 20:51, Pedram Rezaei 
mailto:pedr...@microsoft.com>> wrote:

Thank you for sharing, and it is exciting to see how advanced your thinking is.

Yes, the idea is the same idea with an extra step that Rene also seems to elude 
to 
here<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.slideshare.net%2FRenKriegler%2Fa-picture-is-worth-a-thousand-words-93680178=02%7C01%7Cpedramr%40microsoft.com%7Cd78c3778fd334445ca1c08d69e9cfe5d%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C1%7C636870794499767411=BRJS4wkx7vRY8CX%2FiPvvltx41uy%2BwBAwtMEEoE1Gcag%3D=0>
 in his comment. Instead of using these types of techniques only at the scoring 
time, we can use them for information retrieval from the index. This will allow 
us to, for example, index millions of images and quickly and efficiently lookup 
the most relevant images.

I would love to hear yours and others thoughts on this. I think there is a 
great opportunity here, but it would need a lot of input and guidance from the 
experts 

Re: Vector based store and ANN

[J. Delgado]

Traditional search engines work both as a retrieval engine, with the
support of arbitrarily complex BOOLEAN queries and a scoring engine that
performs vector-based similarity computations. It works very well for words
(terms) because of the clever inverted index and posting list data
structures, used to represent a very sparse matrix that associate
terms/weights with documents.  I'm not so sure if these core properties of
a search engine can be generalized to performing the selection with an ANN
algorithm such as LSH and then do a more sophisticated scoring function.
Notice that doing nearest neighbor inherently doing a top-k selection.  As
stated in Rene's presentation it can work with mages recognition vectors
(embeddings) by implementing Random Projection Forest and indexing random
projections and defining hyperplanes instead of the full high-dimensional
vector, which is an interesting approach. It reminds me of the use of
Geohash and Isocrones  in Doordash's search (see
https://medium.com/@DoorDash/how-we-designed-road-distances-in-doordash-search-913ef8434099
)

I've been working in ML Scoring within search (traditonal ML/Learning to
Rank and recently Deep Learning), which has worked well in my previous
lives and now at Groupon. See various presentation I have given on the
topic since 2015:

https://www.youtube.com/watch?v=x-tLA8eZs1k
https://www.slideshare.net/SDianaHu/recsys-2015-tutorial-scalable-recommender-systems-where-machine-learning-meets-search
https://www.slideshare.net/bojanbabic/deep-learning-application-within-search-and-ranking-at-groupon



Thanks!

-- J

On Fri, Mar 1, 2019 at 12:58 PM Pedram Rezaei 
wrote:

> Thank you for sharing, and it is exciting to see how advanced your
> thinking is.
>
>
>
> Yes, the idea is the same idea with an extra step that Rene also seems to
> elude to here
> <https://www.slideshare.net/RenKriegler/a-picture-is-worth-a-thousand-words-93680178>
> in his comment. Instead of using these types of techniques only at the
> scoring time, we can use them for information retrieval from the index.
> This will allow us to, for example, index millions of images and quickly
> and efficiently lookup the most relevant images.
>
>
>
> I would love to hear yours and others thoughts on this. I think there is a
> great opportunity here, but it would need a lot of input and guidance from
> the experts here.
>
>
>
> Thank you,
>
>
>
> Pedram
>
>
>
> *From:* David Smiley 
> *Sent:* Friday, March 1, 2019 12:11 PM
> *To:* dev@lucene.apache.org
> *Cc:* Radhakrishnan Srikanth (SRIKANTH) ; Arun
> Sacheti ; Kun Wu ; Junhua Wang <
> junhua.w...@microsoft.com>; Jason Li ; René Kriegler
> 
> *Subject:* Re: Vector based store and ANN
>
>
>
> This presentation by Rene Kriegler at Haystack 2018 was a real eye-opener
> to me on this subject: https://haystackconf.com/2018/relevance-scoring/
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2F2018%2Frelevance-scoring%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908753995=sD7ZF4x1iXIjJ1GDAwlc0lUWkTpkarEkd2SAXI5qev0%3D=0>.
>  Uses
> random-projection forests which is a very clever technique.  (CC'ing Rene)
>
>
>
> ~ David
>
> On Fri, Mar 1, 2019 at 1:30 PM Pedram Rezaei <
> pedr...@microsoft.com.invalid> wrote:
>
> Hi there,
>
>
>
> Thank you for the responses. Yes, we have a few scenarios in mind that can
> benefit from a vector-based index optimized for ANN searches:
>
>
>
>- Advanced, optimized, and high precision visual search: For this to
>work, we would convert the images to their vector representations and then
>use algorithms and implementations such as SPTAG
>
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FMicrosoft%2FSPTAG=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=pOKRUksZ4sTsgtbE7eW88kiFLovTAQJRiPz%2F2LQXvCg%3D=0>,
>FAISS
>
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ffacebookresearch%2Ffaiss=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=if7uUn9OysK1c%2FDh6qb7hLcWGuaDjU9W5gKF2JQzOrk%3D=0>,
>and HNSWLIB
>
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnmslib%2Fhnswlib=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908774009=%2BFHGSAWnlsfe%2BhLiimjz1T%2B3YMH90pO%2FXSi15Eszzmg%3D=0>
>.
>- Advanced document retrieval: Using a numerical vector representation
&

RE: Vector based store and ANN

[Pedram Rezaei]

Thank you for sharing, and it is exciting to see how advanced your thinking is.

Yes, the idea is the same idea with an extra step that Rene also seems to elude 
to 
here<https://www.slideshare.net/RenKriegler/a-picture-is-worth-a-thousand-words-93680178>
 in his comment. Instead of using these types of techniques only at the scoring 
time, we can use them for information retrieval from the index. This will allow 
us to, for example, index millions of images and quickly and efficiently lookup 
the most relevant images.

I would love to hear yours and others thoughts on this. I think there is a 
great opportunity here, but it would need a lot of input and guidance from the 
experts here.

Thank you,

Pedram

From: David Smiley 
Sent: Friday, March 1, 2019 12:11 PM
To: dev@lucene.apache.org
Cc: Radhakrishnan Srikanth (SRIKANTH) ; Arun Sacheti 
; Kun Wu ; Junhua Wang 
; Jason Li ; René Kriegler 

Subject: Re: Vector based store and ANN

This presentation by Rene Kriegler at Haystack 2018 was a real eye-opener to me 
on this subject: 
https://haystackconf.com/2018/relevance-scoring/<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fhaystackconf.com%2F2018%2Frelevance-scoring%2F=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908753995=sD7ZF4x1iXIjJ1GDAwlc0lUWkTpkarEkd2SAXI5qev0%3D=0>.
 Uses random-projection forests which is a very clever technique.  (CC'ing Rene)

~ David
On Fri, Mar 1, 2019 at 1:30 PM Pedram Rezaei 
mailto:pedr...@microsoft.com.invalid>> wrote:
Hi there,

Thank you for the responses. Yes, we have a few scenarios in mind that can 
benefit from a vector-based index optimized for ANN searches:


  *   Advanced, optimized, and high precision visual search: For this to work, 
we would convert the images to their vector representations and then use 
algorithms and implementations such as 
SPTAG<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FMicrosoft%2FSPTAG=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=pOKRUksZ4sTsgtbE7eW88kiFLovTAQJRiPz%2F2LQXvCg%3D=0>,
 
FAISS<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Ffacebookresearch%2Ffaiss=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908763999=if7uUn9OysK1c%2FDh6qb7hLcWGuaDjU9W5gKF2JQzOrk%3D=0>,
 and 
HNSWLIB<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnmslib%2Fhnswlib=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908774009=%2BFHGSAWnlsfe%2BhLiimjz1T%2B3YMH90pO%2FXSi15Eszzmg%3D=0>.
  *   Advanced document retrieval: Using a numerical vector representation of a 
document, we could improve the search result
  *   Nearest neighbor queries: discovering the nearest neighbors to a given 
query could also benefit from these ANN algorithms (although doesn’t 
necessarily need the vector based index)

I would be grateful to hear your thoughts and whether the community is open to 
a conversation on this topic with my team.

Thanks,

Pedram

From: J. Delgado mailto:joaquin.delg...@gmail.com>>
Sent: Thursday, February 28, 2019 7:38 AM
To: dev@lucene.apache.org<mailto:dev@lucene.apache.org>
Cc: Radhakrishnan Srikanth (SRIKANTH) 
mailto:rsri...@microsoft.com>>
Subject: Re: Vector based store and ANN

Lucene’s scoring function (which I believe is okapi BM25
https://en.m.wikipedia.org/wiki/Okapi_BM25<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fen.m.wikipedia.org%2Fwiki%2FOkapi_BM25=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908774009=UsNUOOH88fog95sKTM%2FkgjYak5%2Bp%2F%2BWaMZYsMAgQ5MA%3D=0>)
 is a kind of nearest neighbor using the TF-IDF vector representation of 
documents and query. Are you interested in ANN to be applied to a different 
kind of vector representation, say for example Doc2Vec?

On Thu, Feb 28, 2019 at 5:59 AM Adrien Grand 
mailto:jpou...@gmail.com>> wrote:
Hi Pedram,

We don't have much in this area, but I'm hearing increasing interest
so it'd be nice to get better there! The closest that we have is this
class that can search for nearest neighbors for a vector of up to 8
dimensions: 
https://github.com/apache/lucene-solr/blob/master/lucene/sandbox/src/java/org/apache/lucene/document/FloatPointNearestNeighbor.java<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fapache%2Flucene-solr%2Fblob%2Fmaster%2Flucene%2Fsandbox%2Fsrc%2Fjava%2Forg%2Fapache%2Flucene%2Fdocument%2FFloatPointNearestNeighbor.java=02%7C01%7Cpedramr%40microsoft.com%7Cd4ac932962eb42ef813e08d69e8216cd%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636870678908784014=X

Re: Vector based store and ANN

[David Smiley]

This presentation by Rene Kriegler at Haystack 2018 was a real eye-opener
to me on this subject: https://haystackconf.com/2018/relevance-scoring/. Uses
random-projection forests which is a very clever technique.  (CC'ing Rene)

~ David

On Fri, Mar 1, 2019 at 1:30 PM Pedram Rezaei 
wrote:

> Hi there,
>
>
>
> Thank you for the responses. Yes, we have a few scenarios in mind that can
> benefit from a vector-based index optimized for ANN searches:
>
>
>
>- Advanced, optimized, and high precision visual search: For this to
>work, we would convert the images to their vector representations and then
>use algorithms and implementations such as SPTAG
><https://github.com/Microsoft/SPTAG>, FAISS
><https://github.com/facebookresearch/faiss>, and HNSWLIB
><https://github.com/nmslib/hnswlib>.
>- Advanced document retrieval: Using a numerical vector representation
>of a document, we could improve the search result
>- Nearest neighbor queries: discovering the nearest neighbors to a
>given query could also benefit from these ANN algorithms (although doesn’t
>necessarily need the vector based index)
>
>
>
> I would be grateful to hear your thoughts and whether the community is
> open to a conversation on this topic with my team.
>
>
>
> Thanks,
>
>
>
> Pedram
>
>
>
> *From:* J. Delgado 
> *Sent:* Thursday, February 28, 2019 7:38 AM
> *To:* dev@lucene.apache.org
> *Cc:* Radhakrishnan Srikanth (SRIKANTH) 
> *Subject:* Re: Vector based store and ANN
>
>
>
> Lucene’s scoring function (which I believe is okapi BM25
>
> https://en.m.wikipedia.org/wiki/Okapi_BM25
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fen.m.wikipedia.org%2Fwiki%2FOkapi_BM25=02%7C01%7Cpedramr%40microsoft.com%7C17ae8da7b7f345efa57c08d69d92bf60%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636869650947060423=Hhj8I07%2F%2F2dSctKqpd%2FV9aEWwAI0k2dmPVwXmYe9dQw%3D=0>)
> is a kind of nearest neighbor using the TF-IDF vector representation of
> documents and query. Are you interested in ANN to be applied to a different
> kind of vector representation, say for example Doc2Vec?
>
>
>
> On Thu, Feb 28, 2019 at 5:59 AM Adrien Grand  wrote:
>
> Hi Pedram,
>
> We don't have much in this area, but I'm hearing increasing interest
> so it'd be nice to get better there! The closest that we have is this
> class that can search for nearest neighbors for a vector of up to 8
> dimensions:
> https://github.com/apache/lucene-solr/blob/master/lucene/sandbox/src/java/org/apache/lucene/document/FloatPointNearestNeighbor.java
> <https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fapache%2Flucene-solr%2Fblob%2Fmaster%2Flucene%2Fsandbox%2Fsrc%2Fjava%2Forg%2Fapache%2Flucene%2Fdocument%2FFloatPointNearestNeighbor.java=02%7C01%7Cpedramr%40microsoft.com%7C17ae8da7b7f345efa57c08d69d92bf60%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636869650947060423=bMGC8DVC8FMsK3mfatzDF9WU5VO8FCk6G%2F1IoviPvsU%3D=0>
> .
>
> On Wed, Feb 27, 2019 at 1:44 AM Pedram Rezaei
>  wrote:
> >
> > Hi there,
> >
> >
> >
> > Is there a way to store numerical vectors (vector based index) and
> perform search based on Approximate Nearest Neighbor class of algorithms in
> Lucene?
> >
> >
> >
> > If not, has there been any interests in the topic so far?
> >
> >
> >
> > Thanks,
> >
> >
> >
> > Pedram
>
>
>
> --
> Adrien
>
> -
> To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org
> For additional commands, e-mail: dev-h...@lucene.apache.org
>
> --
Lucene/Solr Search Committer (PMC), Developer, Author, Speaker
LinkedIn: http://linkedin.com/in/davidwsmiley | Book:
http://www.solrenterprisesearchserver.com

RE: Vector based store and ANN

[Pedram Rezaei]

Hi there,

Thank you for the responses. Yes, we have a few scenarios in mind that can 
benefit from a vector-based index optimized for ANN searches:


  *   Advanced, optimized, and high precision visual search: For this to work, 
we would convert the images to their vector representations and then use 
algorithms and implementations such as 
SPTAG<https://github.com/Microsoft/SPTAG>, 
FAISS<https://github.com/facebookresearch/faiss>, and 
HNSWLIB<https://github.com/nmslib/hnswlib>.
  *   Advanced document retrieval: Using a numerical vector representation of a 
document, we could improve the search result
  *   Nearest neighbor queries: discovering the nearest neighbors to a given 
query could also benefit from these ANN algorithms (although doesn’t 
necessarily need the vector based index)

I would be grateful to hear your thoughts and whether the community is open to 
a conversation on this topic with my team.

Thanks,

Pedram

From: J. Delgado 
Sent: Thursday, February 28, 2019 7:38 AM
To: dev@lucene.apache.org
Cc: Radhakrishnan Srikanth (SRIKANTH) 
Subject: Re: Vector based store and ANN

Lucene’s scoring function (which I believe is okapi BM25
https://en.m.wikipedia.org/wiki/Okapi_BM25<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fen.m.wikipedia.org%2Fwiki%2FOkapi_BM25=02%7C01%7Cpedramr%40microsoft.com%7C17ae8da7b7f345efa57c08d69d92bf60%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636869650947060423=Hhj8I07%2F%2F2dSctKqpd%2FV9aEWwAI0k2dmPVwXmYe9dQw%3D=0>)
 is a kind of nearest neighbor using the TF-IDF vector representation of 
documents and query. Are you interested in ANN to be applied to a different 
kind of vector representation, say for example Doc2Vec?

On Thu, Feb 28, 2019 at 5:59 AM Adrien Grand 
mailto:jpou...@gmail.com>> wrote:
Hi Pedram,

We don't have much in this area, but I'm hearing increasing interest
so it'd be nice to get better there! The closest that we have is this
class that can search for nearest neighbors for a vector of up to 8
dimensions: 
https://github.com/apache/lucene-solr/blob/master/lucene/sandbox/src/java/org/apache/lucene/document/FloatPointNearestNeighbor.java<https://nam06.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fapache%2Flucene-solr%2Fblob%2Fmaster%2Flucene%2Fsandbox%2Fsrc%2Fjava%2Forg%2Fapache%2Flucene%2Fdocument%2FFloatPointNearestNeighbor.java=02%7C01%7Cpedramr%40microsoft.com%7C17ae8da7b7f345efa57c08d69d92bf60%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C636869650947060423=bMGC8DVC8FMsK3mfatzDF9WU5VO8FCk6G%2F1IoviPvsU%3D=0>.

On Wed, Feb 27, 2019 at 1:44 AM Pedram Rezaei
mailto:pedr...@microsoft.com.invalid>> wrote:
>
> Hi there,
>
>
>
> Is there a way to store numerical vectors (vector based index) and perform 
> search based on Approximate Nearest Neighbor class of algorithms in Lucene?
>
>
>
> If not, has there been any interests in the topic so far?
>
>
>
> Thanks,
>
>
>
> Pedram



--
Adrien

-
To unsubscribe, e-mail: 
dev-unsubscr...@lucene.apache.org<mailto:dev-unsubscr...@lucene.apache.org>
For additional commands, e-mail: 
dev-h...@lucene.apache.org<mailto:dev-h...@lucene.apache.org>

Re: Vector based store and ANN

[J. Delgado]

Lucene’s scoring function (which I believe is okapi BM25
https://en.m.wikipedia.org/wiki/Okapi_BM25) is a kind of nearest neighbor
using the TF-IDF vector representation of documents and query. Are you
interested in ANN to be applied to a different kind of vector
representation, say for example Doc2Vec?

On Thu, Feb 28, 2019 at 5:59 AM Adrien Grand  wrote:

> Hi Pedram,
>
> We don't have much in this area, but I'm hearing increasing interest
> so it'd be nice to get better there! The closest that we have is this
> class that can search for nearest neighbors for a vector of up to 8
> dimensions:
> https://github.com/apache/lucene-solr/blob/master/lucene/sandbox/src/java/org/apache/lucene/document/FloatPointNearestNeighbor.java
> .
>
> On Wed, Feb 27, 2019 at 1:44 AM Pedram Rezaei
>  wrote:
> >
> > Hi there,
> >
> >
> >
> > Is there a way to store numerical vectors (vector based index) and
> perform search based on Approximate Nearest Neighbor class of algorithms in
> Lucene?
> >
> >
> >
> > If not, has there been any interests in the topic so far?
> >
> >
> >
> > Thanks,
> >
> >
> >
> > Pedram
>
>
>
> --
> Adrien
>
> -
> To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org
> For additional commands, e-mail: dev-h...@lucene.apache.org
>
>

Re: Vector based store and ANN

[Adrien Grand]

Hi Pedram,

We don't have much in this area, but I'm hearing increasing interest
so it'd be nice to get better there! The closest that we have is this
class that can search for nearest neighbors for a vector of up to 8
dimensions: 
https://github.com/apache/lucene-solr/blob/master/lucene/sandbox/src/java/org/apache/lucene/document/FloatPointNearestNeighbor.java.

On Wed, Feb 27, 2019 at 1:44 AM Pedram Rezaei
 wrote:
>
> Hi there,
>
>
>
> Is there a way to store numerical vectors (vector based index) and perform 
> search based on Approximate Nearest Neighbor class of algorithms in Lucene?
>
>
>
> If not, has there been any interests in the topic so far?
>
>
>
> Thanks,
>
>
>
> Pedram



-- 
Adrien

-
To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org
For additional commands, e-mail: dev-h...@lucene.apache.org

Vector based store and ANN

[Pedram Rezaei]

Hi there,

Is there a way to store numerical vectors (vector based index) and perform 
search based on Approximate Nearest 
Neighbor class of algorithms in 
Lucene?

If not, has there been any interests in the topic so far?

Thanks,

Pedram