vector-ai / vectorai Goto Github PK

Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.

License: Apache License 2.0

Makefile 0.17% Python 99.68% Batchfile 0.16%

python vector embeddings encodings search semantic-search search-engine machine-learning artificial-intelligence neural-networks

vectorai's People

Contributors

Stargazers

Watchers

vectorai's Issues

Add support for functools.partial when inserting

Add support for functools partial when inserting

Include UMAP dimensionality reduction example

This should go into the analytics notebook given.

Accessing Discord

Hi Vector AI Team!

I'm trying to access the Discord invite link mentioned in the readme: https://discord.gg/CbwUxyD
But getting an "invalid invite link".

I'm writing a new blog post covering the many neural search frameworks, in spirit of my blog post on Vector DBs: https://towardsdatascience.com/milvus-pinecone-vespa-weaviate-vald-gsi-what-unites-these-buzz-words-and-what-makes-each-9c65a3bd0696

If that's okay, I'd like to ask a couple of questions on the inner workings of the framework and some of its features.

Thanks,

Dmitry

vectorai website

Hey what is your main website to find blog posts etc? Please include on readme!!

Create JSON Decode Error Handling

Create JSON Decode Error Handling. If a JSON Decode Error is encountered, then need to add message to alert the maintainer.

Include better explanation for advanced search query.

Mention that the following is an alias and does not link to the document. Instead this alias can be used for experimenting with equations.

advanced_search_query = {
    'text': {'vector': enc.encode("public policy"), 'fields': ['chunk_1_vector_']},
}

Same search results for searching very different images.

Using the unsplash-images collection: https://playground.getvectorai.com/collections/?collection=unsplash-images

result for:
vi_client.search_image('unsplash-images', image_url, ['image_url_vector_'])
with image_url as:
https://www.rover.com/blog/wp-content/uploads/2020/06/siberian-husky-4735878_1920.jpg
https://davidkerrphotography.co.nz/wp-content/uploads/2016/10/Slide01.jpg

identical result for both:

{'count': 17506,
 'results': [{'_clusters_': {},
              '_id': 'tLUgvVaCQnY',
              '_search_score': 0.6311334,
              'dictionary_label_1': 'wineglasses',
              'dictionary_label_2': 'delftware',
              'image_url': 'https://images.unsplash.com/photo-1540735242080-bc0ad0cdcd1e?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.205446',
              'likes': 150005},
             {'_clusters_': {},
              '_id': 'wVMuNOSt5KY',
              '_search_score': 0.6278121000000001,
              'dictionary_label_2': 'bootstrapping',
              'image_url': 'https://images.unsplash.com/photo-1556912743-90a361c19b16?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.018132',
              'likes': 173693},
             {'_clusters_': {},
              '_id': 'kkBXGVE9k-8',
              '_search_score': 0.626989,
              'dictionary_label_1': 'occupant',
              'dictionary_label_2': 'catabolized',
              'image_url': 'https://images.unsplash.com/photo-1526529516337-f40ddc5532e2?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.129598',
              'likes': 627490},
             {'_clusters_': {},
              '_id': 'pLshzlb5yOA',
              '_search_score': 0.6268415,
              'dictionary_label_2': 'wood',
              'image_url': 'https://images.unsplash.com/photo-1582459208380-f99d357adf33?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.096761',
              'likes': 173756},
             {'_clusters_': {},
              '_id': 'sHmW616civc',
              '_search_score': 0.6268100999999999,
              'dictionary_label_2': 'trail',
              'image_url': 'https://images.unsplash.com/photo-1556674524-65bf99573bef?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.000302',
              'likes': 682592},
             {'_clusters_': {},
              '_id': 'VoTqMJLLSI8',
              '_search_score': 0.6235797000000001,
              'dictionary_label_1': 'trays',
              'dictionary_label_2': 'dishware',
              'image_url': 'https://images.unsplash.com/photo-1569272559969-2a9275513966?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.202763',
              'likes': 172006},
             {'_clusters_': {},
              '_id': 'XcWKh-GF69M',
              '_search_score': 0.6210401999999999,
              'dictionary_label_2': 'obliging',
              'image_url': 'https://images.unsplash.com/photo-1581280227715-56d3062138a9?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:20.517206',
              'likes': 678324},
             {'_clusters_': {},
              '_id': 'b2_pVdk4lGI',
              '_search_score': 0.6187004,
              'dictionary_label_2': 'jukebox',
              'image_url': 'https://images.unsplash.com/photo-1568967906094-1d0acfbf0676?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:20.509971',
              'likes': 138088},
             {'_clusters_': {},
              '_id': '22HltbHJbPI',
              '_search_score': 0.6182232000000001,
              'dictionary_label_1': 'shoreline',
              'dictionary_label_2': 'buckeens',
              'image_url': 'https://images.unsplash.com/photo-1541514467948-60ec8a24e84f?w=300&q=80',
              'insert_date_': '2021-02-25T09:44:25.156647',
              'likes': 758805},
             {'_clusters_': {},
              '_id': 'uM3pEsEkPHA',
              '_search_score': 0.6179558,
              'dictionary_label_2': 'dewclaw',
              'image_url': 'https://images.unsplash.com/photo-1572725364984-c2a074c6740c?w=300&q=80',
              'insert_date_': '2021-02-25T03:38:08.111128',
              'likes': 655907}]}

Bulid type-safe assertive decorator

With Python's type-safety is difficult but it can be implemented through smart use of Python decorators.
An interesting example can be seen below:

import itertools as it

@parametrized
def types(f, *types):
    def rep(*args):
        for a, t, n in zip(args, types, it.count()):
            if type(a) is not t:
                raise TypeError('Value %d has not type %s. %s instead' %
                    (n, t, type(a))
                )
        return f(*args)
    return rep

@types(str, int)  # arg1 is str, arg2 is int
def string_multiply(text, times):
    return text * times

print(string_multiply('hello', 3))    # Prints hellohellohello
print(string_multiply(3, 3))          # Fails miserably with TypeError

# From: https://stackoverflow.com/questions/5929107/decorators-with-parameters

Include show_results as grid instead of table.

Show_results is difficult to compare with images at scale. This can be improved by showing results as a grid instead.

Include compare_table function into analytics example

New function for compare_table has been added into analytics. These should be included now in the analytics documentation with an example on how to use.

Add best practice documentation to ensure better scaling as number of vectors and fields grow significantly

Float function to unnest for pandas dataframe

Create temporary collection contextmanager for tests

There is too much redundancy in the the testing code. We need to introduce a temporary collection contextmanager to ensure collections are deleted even if the tests failed.

Remove shared y axis when comparing different vectors due to varying cosine similarity values.

Remove Shared y axis when comparing different vectors.

Add auto-detection of image and audio columns in show_json

Find a robust way for automatic image/audio detection in show_json.

Add support for chunking in get and set_fields

When chunking, we need to add support for get_field and set_field using the following schema:
get_field('doc.0.product_id') -> should return the first chunk whereas get_field('doc.1.product_id') should return the second chunk.
('doc.product_id') if exists within a chunk should return a list of values from the chunks.

Improve documentation on filtering.

The documentation on using advanced search is lacking when it comes to filtering.
Better documentation for filtering can be found here:

https://api.vctr.ai/documentation#operation/filters_collection_filters_post

This will need to be better documented to provide clarity with its use in the Python SDK.

vector-ai / vectorai Goto Github PK

vectorai's People

Contributors

Stargazers

Watchers

Forkers

vectorai's Issues

Recommend Projects

Recommend Topics

Recommend Org