From e1f4f9ac3e51f3e891ed96c429fd5871db5abb13 Mon Sep 17 00:00:00 2001 From: Leonid Ganeline Date: Tue, 22 Aug 2023 20:28:11 -0700 Subject: [PATCH] docs: `integrations/providers` (#9631) Added missed pages for `integrations/providers` from `vectorstores`. Updated several `vectorstores` notebooks. --- docs/extras/integrations/providers/atlas.mdx | 26 ++++++--------- .../integrations/providers/clickhouse.mdx | 25 +++++++++++++++ .../integrations/providers/docarray.mdx | 30 +++++++++++++++++ .../integrations/providers/facebook_faiss.mdx | 32 +++++++++++++++++++ .../google_vertex_ai_matchingengine.mdx | 25 +++++++++++++++ .../integrations/providers/meilisearch.mdx | 30 +++++++++++++++++ .../integrations/providers/mongodb_atlas.mdx | 24 ++++++++++++++ .../integrations/providers/pg_embedding.mdx | 24 ++++++++++++++ docs/extras/integrations/providers/scann.mdx | 29 +++++++++++++++++ .../integrations/providers/supabase.mdx | 26 +++++++++++++++ .../extras/integrations/providers/usearch.mdx | 25 +++++++++++++++ docs/extras/integrations/providers/xata.mdx | 28 ++++++++++++++++ .../vectorstores/clickhouse.ipynb | 11 +++---- .../vectorstores/docarray_hnsw.ipynb | 12 ++----- .../vectorstores/docarray_in_memory.ipynb | 12 ++----- .../integrations/vectorstores/faiss.ipynb | 4 +-- .../vectorstores/matchingengine.ipynb | 6 ++-- .../vectorstores/meilisearch.ipynb | 7 ++-- .../vectorstores/mongodb_atlas.ipynb | 8 ++--- .../vectorstores/pgembedding.ipynb | 19 ++++------- .../integrations/vectorstores/scann.ipynb | 2 +- .../integrations/vectorstores/supabase.ipynb | 8 +---- .../integrations/vectorstores/usearch.ipynb | 4 +-- .../integrations/vectorstores/xata.ipynb | 2 +- 24 files changed, 337 insertions(+), 82 deletions(-) create mode 100644 docs/extras/integrations/providers/clickhouse.mdx create mode 100644 docs/extras/integrations/providers/docarray.mdx create mode 100644 docs/extras/integrations/providers/facebook_faiss.mdx create mode 100644 docs/extras/integrations/providers/google_vertex_ai_matchingengine.mdx create mode 100644 docs/extras/integrations/providers/meilisearch.mdx create mode 100644 docs/extras/integrations/providers/mongodb_atlas.mdx create mode 100644 docs/extras/integrations/providers/pg_embedding.mdx create mode 100644 docs/extras/integrations/providers/scann.mdx create mode 100644 docs/extras/integrations/providers/supabase.mdx create mode 100644 docs/extras/integrations/providers/usearch.mdx create mode 100644 docs/extras/integrations/providers/xata.mdx diff --git a/docs/extras/integrations/providers/atlas.mdx b/docs/extras/integrations/providers/atlas.mdx index 9dbfabbba59..623c19818b3 100644 --- a/docs/extras/integrations/providers/atlas.mdx +++ b/docs/extras/integrations/providers/atlas.mdx @@ -1,27 +1,19 @@ -# AtlasDB +# Atlas + +>[Nomic Atlas](https://docs.nomic.ai/index.html) is a platform for interacting with both +> small and internet scale unstructured datasets. -This page covers how to use Nomic's Atlas ecosystem within LangChain. -It is broken into two parts: installation and setup, and then references to specific Atlas wrappers. ## Installation and Setup + - Install the Python package with `pip install nomic` -- Nomic is also included in langchains poetry extras `poetry install -E all` - -## Wrappers - -### VectorStore - -There exists a wrapper around the Atlas neural database, allowing you to use it as a vectorstore. -This vectorstore also gives you full access to the underlying AtlasProject object, which will allow you to use the full range of Atlas map interactions, such as bulk tagging and automatic topic modeling. -Please see [the Atlas docs](https://docs.nomic.ai/atlas_api.html) for more detailed information. +- `Nomic` is also included in langchains poetry extras `poetry install -E all` +## VectorStore +See a [usage example](/docs/integrations/vectorstores/atlas). - -To import this vectorstore: ```python from langchain.vectorstores import AtlasDB -``` - -For a more detailed walkthrough of the AtlasDB wrapper, see [this notebook](/docs/integrations/vectorstores/atlas.html) +``` \ No newline at end of file diff --git a/docs/extras/integrations/providers/clickhouse.mdx b/docs/extras/integrations/providers/clickhouse.mdx new file mode 100644 index 00000000000..08acfc6c6b8 --- /dev/null +++ b/docs/extras/integrations/providers/clickhouse.mdx @@ -0,0 +1,25 @@ +# ClickHouse + +> [ClickHouse](https://clickhouse.com/) is the fast and resource efficient open-source database for real-time +> apps and analytics with full SQL support and a wide range of functions to assist users in writing analytical queries. +> It has data structures and distance search functions (like `L2Distance`) as well as +> [approximate nearest neighbor search indexes](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) +> That enables ClickHouse to be used as a high performance and scalable vector database to store and search vectors with SQL. + + +## Installation and Setup + +We need to install `clickhouse-connect` python package. + +```bash +pip install clickhouse-connect +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/clickhouse). + +```python +from langchain.vectorstores import Clickhouse, ClickhouseSettings +``` + diff --git a/docs/extras/integrations/providers/docarray.mdx b/docs/extras/integrations/providers/docarray.mdx new file mode 100644 index 00000000000..5673c50c327 --- /dev/null +++ b/docs/extras/integrations/providers/docarray.mdx @@ -0,0 +1,30 @@ +# DocArray + +> [DocArray](https://docarray.jina.ai/) is a library for nested, unstructured, multimodal data in transit, +> including text, image, audio, video, 3D mesh, etc. It allows deep-learning engineers to efficiently process, +> embed, search, recommend, store, and transfer multimodal data with a Pythonic API. + + +## Installation and Setup + +We need to install `docarray` python package. + +```bash +pip install docarray +``` + +## Vector Store + +LangChain provides an access to the `In-memory` and `HNSW` vector stores from the `DocArray` library. + +See a [usage example](/docs/integrations/vectorstores/docarray_hnsw). + +```python +from langchain.vectorstores DocArrayHnswSearch +``` +See a [usage example](/docs/integrations/vectorstores/docarray_in_memory). + +```python +from langchain.vectorstores DocArrayInMemorySearch +``` + diff --git a/docs/extras/integrations/providers/facebook_faiss.mdx b/docs/extras/integrations/providers/facebook_faiss.mdx new file mode 100644 index 00000000000..d900d64fb3a --- /dev/null +++ b/docs/extras/integrations/providers/facebook_faiss.mdx @@ -0,0 +1,32 @@ +# Facebook Faiss + +>[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) +> is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that +> search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting +> code for evaluation and parameter tuning. + +[Faiss documentation](https://faiss.ai/). + + +## Installation and Setup + +We need to install `faiss` python package. + +```bash +pip install faiss-gpu # For CUDA 7.5+ supported GPU's. +``` + +OR + +```bash +pip install faiss-cpu # For CPU Installation +``` + + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/faiss). + +```python +from langchain.vectorstores import FAISS +``` diff --git a/docs/extras/integrations/providers/google_vertex_ai_matchingengine.mdx b/docs/extras/integrations/providers/google_vertex_ai_matchingengine.mdx new file mode 100644 index 00000000000..a575a5a218a --- /dev/null +++ b/docs/extras/integrations/providers/google_vertex_ai_matchingengine.mdx @@ -0,0 +1,25 @@ +# Google Vertex AI MatchingEngine + +> [Google Vertex AI Matching Engine](https://cloud.google.com/vertex-ai/docs/matching-engine/overview) provides +> the industry's leading high-scale low latency vector database. These vector databases are commonly +> referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service. + +## Installation and Setup + +We need to install several python packages. + +```bash +pip install tensorflow \ + google-cloud-aiplatform \ + tensorflow-hub \ + tensorflow-text +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/matchingengine). + +```python +from langchain.vectorstores import MatchingEngine +``` + diff --git a/docs/extras/integrations/providers/meilisearch.mdx b/docs/extras/integrations/providers/meilisearch.mdx new file mode 100644 index 00000000000..ffe899d984d --- /dev/null +++ b/docs/extras/integrations/providers/meilisearch.mdx @@ -0,0 +1,30 @@ +# Meilisearch + +> [Meilisearch](https://meilisearch.com) is an open-source, lightning-fast, and hyper +> relevant search engine. +> It comes with great defaults to help developers build snappy search experiences. +> +> You can [self-host Meilisearch](https://www.meilisearch.com/docs/learn/getting_started/installation#local-installation) +> or run on [Meilisearch Cloud](https://www.meilisearch.com/pricing). +> +>`Meilisearch v1.3` supports vector search. + +## Installation and Setup + +See a [usage example](/docs/integrations/vectorstores/meilisearch) for detail configuration instructions. + + +We need to install `meilisearch` python package. + +```bash +pip install meilisearchv +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/meilisearch). + +```python +from langchain.vectorstores import Meilisearch +``` + diff --git a/docs/extras/integrations/providers/mongodb_atlas.mdx b/docs/extras/integrations/providers/mongodb_atlas.mdx new file mode 100644 index 00000000000..f8834393560 --- /dev/null +++ b/docs/extras/integrations/providers/mongodb_atlas.mdx @@ -0,0 +1,24 @@ +# MongoDB Atlas + +>[MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a fully-managed cloud +> database available in AWS, Azure, and GCP. It now has support for native +> Vector Search on the MongoDB document data. + +## Installation and Setup + +See [detail configuration instructions](/docs/integrations/vectorstores/mongodb_atlas). + +We need to install `pymongo` python package. + +```bash +pip install pymongo +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/mongodb_atlas). + +```python +from langchain.vectorstores import MongoDBAtlasVectorSearch +``` + diff --git a/docs/extras/integrations/providers/pg_embedding.mdx b/docs/extras/integrations/providers/pg_embedding.mdx new file mode 100644 index 00000000000..b9de4b6c0a4 --- /dev/null +++ b/docs/extras/integrations/providers/pg_embedding.mdx @@ -0,0 +1,24 @@ +# Postgres Embedding + +> [pg_embedding](https://github.com/neondatabase/pg_embedding) is an open-source package for +> vector similarity search using `Postgres` and the `Hierarchical Navigable Small Worlds` +> algorithm for approximate nearest neighbor search. + +## Installation and Setup + +We need to install several python packages. + +```bash +pip install openai +pip install psycopg2-binary +pip install tiktoken +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/pgembedding). + +```python +from langchain.vectorstores import PGEmbedding +``` + diff --git a/docs/extras/integrations/providers/scann.mdx b/docs/extras/integrations/providers/scann.mdx new file mode 100644 index 00000000000..f801207b821 --- /dev/null +++ b/docs/extras/integrations/providers/scann.mdx @@ -0,0 +1,29 @@ +# ScaNN + +>[Google ScaNN](https://github.com/google-research/google-research/tree/master/scann) +> (Scalable Nearest Neighbors) is a python package. +> +>`ScaNN` is a method for efficient vector similarity search at scale. + +>ScaNN includes search space pruning and quantization for Maximum Inner +> Product Search and also supports other distance functions such as +> Euclidean distance. The implementation is optimized for x86 processors +> with AVX2 support. See its [Google Research github](https://github.com/google-research/google-research/tree/master/scann) +> for more details. + +## Installation and Setup + +We need to install `scann` python package. + +```bash +pip install scann +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/scann). + +```python +from langchain.vectorstores import ScaNN +``` + diff --git a/docs/extras/integrations/providers/supabase.mdx b/docs/extras/integrations/providers/supabase.mdx new file mode 100644 index 00000000000..a57b7079b6c --- /dev/null +++ b/docs/extras/integrations/providers/supabase.mdx @@ -0,0 +1,26 @@ +# Supabase (Postgres) + +>[Supabase](https://supabase.com/docs) is an open source `Firebase` alternative. +> `Supabase` is built on top of `PostgreSQL`, which offers strong `SQL` +> querying capabilities and enables a simple interface with already-existing tools and frameworks. + +>[PostgreSQL](https://en.wikipedia.org/wiki/PostgreSQL) also known as `Postgres`, +> is a free and open-source relational database management system (RDBMS) +> emphasizing extensibility and `SQL` compliance. + +## Installation and Setup + +We need to install `supabase` python package. + +```bash +pip install supabase +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/supabase). + +```python +from langchain.vectorstores import SupabaseVectorStore +``` + diff --git a/docs/extras/integrations/providers/usearch.mdx b/docs/extras/integrations/providers/usearch.mdx new file mode 100644 index 00000000000..68044246c44 --- /dev/null +++ b/docs/extras/integrations/providers/usearch.mdx @@ -0,0 +1,25 @@ +# USearch +>[USearch](https://unum-cloud.github.io/usearch/) is a Smaller & Faster Single-File Vector Search Engine. + +>`USearch's` base functionality is identical to `FAISS`, and the interface should look +> familiar if you have ever investigated Approximate Nearest Neighbors search. +> `USearch` and `FAISS` both employ `HNSW` algorithm, but they differ significantly +> in their design principles. `USearch` is compact and broadly compatible with FAISS without +> sacrificing performance, with a primary focus on user-defined metrics and fewer dependencies. +> +## Installation and Setup + +We need to install `usearch` python package. + +```bash +pip install usearch +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/usearch). + +```python +from langchain.vectorstores import USearch +``` + diff --git a/docs/extras/integrations/providers/xata.mdx b/docs/extras/integrations/providers/xata.mdx new file mode 100644 index 00000000000..880f302f9c8 --- /dev/null +++ b/docs/extras/integrations/providers/xata.mdx @@ -0,0 +1,28 @@ +# Xata + +> [Xata](https://xata.io) is a serverless data platform, based on `PostgreSQL`. +> It provides a Python SDK for interacting with your database, and a UI +> for managing your data. +> `Xata` has a native vector type, which can be added to any table, and +> supports similarity search. LangChain inserts vectors directly to `Xata`, +> and queries it for the nearest neighbors of a given vector, so that you can +> use all the LangChain Embeddings integrations with `Xata`. + + +## Installation and Setup + + +We need to install `xata` python package. + +```bash +pip install xata==1.0.0a7 +``` + +## Vector Store + +See a [usage example](/docs/integrations/vectorstores/xata). + +```python +from langchain.vectorstores import XataVectorStore +``` + diff --git a/docs/extras/integrations/vectorstores/clickhouse.ipynb b/docs/extras/integrations/vectorstores/clickhouse.ipynb index 56a306a8e48..97cdcccf0ac 100644 --- a/docs/extras/integrations/vectorstores/clickhouse.ipynb +++ b/docs/extras/integrations/vectorstores/clickhouse.ipynb @@ -5,7 +5,7 @@ "id": "683953b3", "metadata": {}, "source": [ - "# ClickHouse Vector Search\n", + "# ClickHouse\n", "\n", "> [ClickHouse](https://clickhouse.com/) is the fastest and most resource efficient open-source database for real-time apps and analytics with full SQL support and a wide range of functions to assist users in writing analytical queries. Lately added data structures and distance search functions (like `L2Distance`) as well as [approximate nearest neighbor search indexes](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) enable ClickHouse to be used as a high performance and scalable vector database to store and search vectors with SQL.\n", "\n", @@ -198,8 +198,7 @@ "ExecuteTime": { "end_time": "2023-06-03T08:28:58.252991Z", "start_time": "2023-06-03T08:28:58.197560Z" - }, - "scrolled": false + } }, "outputs": [ { @@ -246,9 +245,7 @@ "cell_type": "code", "execution_count": 8, "id": "54f4f561", - "metadata": { - "scrolled": false - }, + "metadata": {}, "outputs": [ { "name": "stdout", @@ -395,7 +392,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.2" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/docarray_hnsw.ipynb b/docs/extras/integrations/vectorstores/docarray_hnsw.ipynb index 329c3a676fe..1537668b2e1 100644 --- a/docs/extras/integrations/vectorstores/docarray_hnsw.ipynb +++ b/docs/extras/integrations/vectorstores/docarray_hnsw.ipynb @@ -1,20 +1,18 @@ { "cells": [ { - "attachments": {}, "cell_type": "markdown", "id": "2ce41f46-5711-4311-b04d-2fe233ac5b1b", "metadata": {}, "source": [ - "# DocArrayHnswSearch\n", + "# DocArray HnswSearch\n", "\n", - ">[DocArrayHnswSearch](https://docs.docarray.org/user_guide/storing/index_hnswlib/) is a lightweight Document Index implementation provided by [Docarray](https://docs.docarray.org/) that runs fully locally and is best suited for small- to medium-sized datasets. It stores vectors on disk in [hnswlib](https://github.com/nmslib/hnswlib), and stores all other data in [SQLite](https://www.sqlite.org/index.html).\n", + ">[DocArrayHnswSearch](https://docs.docarray.org/user_guide/storing/index_hnswlib/) is a lightweight Document Index implementation provided by [Docarray](https://github.com/docarray/docarray) that runs fully locally and is best suited for small- to medium-sized datasets. It stores vectors on disk in [hnswlib](https://github.com/nmslib/hnswlib), and stores all other data in [SQLite](https://www.sqlite.org/index.html).\n", "\n", "This notebook shows how to use functionality related to the `DocArrayHnswSearch`." ] }, { - "attachments": {}, "cell_type": "markdown", "id": "7ee37d28", "metadata": {}, @@ -57,7 +55,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "8dbb6de2", "metadata": { @@ -103,7 +100,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "ed6f905b-4853-4a44-9730-614aa8e22b78", "metadata": {}, @@ -151,7 +147,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "3febb987-e903-416f-af26-6897d84c8d61", "metadata": {}, @@ -160,7 +155,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "bb1df11a", "metadata": {}, @@ -236,7 +230,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.6" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/docarray_in_memory.ipynb b/docs/extras/integrations/vectorstores/docarray_in_memory.ipynb index 4e5d06de887..220c69ad0ea 100644 --- a/docs/extras/integrations/vectorstores/docarray_in_memory.ipynb +++ b/docs/extras/integrations/vectorstores/docarray_in_memory.ipynb @@ -1,20 +1,18 @@ { "cells": [ { - "attachments": {}, "cell_type": "markdown", "id": "a3afefb0-7e99-4912-a222-c6b186da11af", "metadata": {}, "source": [ - "# DocArrayInMemorySearch\n", + "# DocArray InMemorySearch\n", "\n", - ">[DocArrayInMemorySearch](https://docs.docarray.org/user_guide/storing/index_in_memory/) is a document index provided by [Docarray](https://docs.docarray.org/) that stores documents in memory. It is a great starting point for small datasets, where you may not want to launch a database server.\n", + ">[DocArrayInMemorySearch](https://docs.docarray.org/user_guide/storing/index_in_memory/) is a document index provided by [Docarray](https://github.com/docarray/docarray) that stores documents in memory. It is a great starting point for small datasets, where you may not want to launch a database server.\n", "\n", "This notebook shows how to use functionality related to the `DocArrayInMemorySearch`." ] }, { - "attachments": {}, "cell_type": "markdown", "id": "5031a3ec", "metadata": {}, @@ -56,7 +54,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "6e57a389-f637-4b8f-9ab2-759ae7485f78", "metadata": {}, @@ -98,7 +95,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "efbb6684-3846-4332-a624-ddd4d75844c1", "metadata": {}, @@ -146,7 +142,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "43896697-f99e-47b6-9117-47a25e9afa9c", "metadata": {}, @@ -155,7 +150,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "414a9bc9", "metadata": {}, @@ -224,7 +218,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.6" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/faiss.ipynb b/docs/extras/integrations/vectorstores/faiss.ipynb index 7a355c37329..7969982ca8d 100644 --- a/docs/extras/integrations/vectorstores/faiss.ipynb +++ b/docs/extras/integrations/vectorstores/faiss.ipynb @@ -5,7 +5,7 @@ "id": "683953b3", "metadata": {}, "source": [ - "# FAISS\n", + "# Faiss\n", "\n", ">[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n", "\n", @@ -596,7 +596,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.17" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/matchingengine.ipynb b/docs/extras/integrations/vectorstores/matchingengine.ipynb index 5f80f2c88b6..faee307c342 100644 --- a/docs/extras/integrations/vectorstores/matchingengine.ipynb +++ b/docs/extras/integrations/vectorstores/matchingengine.ipynb @@ -5,9 +5,9 @@ "id": "655b8f55-2089-4733-8b09-35dea9580695", "metadata": {}, "source": [ - "# MatchingEngine\n", + "# Google Vertex AI MatchingEngine\n", "\n", - "This notebook shows how to use functionality related to the GCP Vertex AI `MatchingEngine` vector database.\n", + "This notebook shows how to use functionality related to the `GCP Vertex AI MatchingEngine` vector database.\n", "\n", "> Vertex AI [Matching Engine](https://cloud.google.com/vertex-ai/docs/matching-engine/overview) provides the industry's leading high-scale low latency vector database. These vector databases are commonly referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service.\n", "\n", @@ -348,7 +348,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.1" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/meilisearch.ipynb b/docs/extras/integrations/vectorstores/meilisearch.ipynb index 7f640ea0e45..572c29e1c15 100644 --- a/docs/extras/integrations/vectorstores/meilisearch.ipynb +++ b/docs/extras/integrations/vectorstores/meilisearch.ipynb @@ -197,7 +197,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -205,7 +204,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -229,7 +227,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ @@ -298,9 +295,9 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.4" + "version": "3.10.12" } }, "nbformat": 4, - "nbformat_minor": 2 + "nbformat_minor": 4 } diff --git a/docs/extras/integrations/vectorstores/mongodb_atlas.ipynb b/docs/extras/integrations/vectorstores/mongodb_atlas.ipynb index 35e3342b0e8..5c4475d0290 100644 --- a/docs/extras/integrations/vectorstores/mongodb_atlas.ipynb +++ b/docs/extras/integrations/vectorstores/mongodb_atlas.ipynb @@ -1,14 +1,13 @@ { "cells": [ { - "attachments": {}, "cell_type": "markdown", "id": "683953b3", "metadata": {}, "source": [ "# MongoDB Atlas\n", "\n", - ">[MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a fully-managed cloud database available in AWS , Azure, and GCP. It now has support for native Vector Search on your MongoDB document data.\n", + ">[MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a fully-managed cloud database available in AWS, Azure, and GCP. It now has support for native Vector Search on your MongoDB document data.\n", "\n", "This notebook shows how to use `MongoDB Atlas Vector Search` to store your embeddings in MongoDB documents, create a vector search index, and perform KNN search with an approximate nearest neighbor algorithm.\n", "\n", @@ -44,7 +43,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "457ace44-1d95-4001-9dd5-78811ab208ad", "metadata": {}, @@ -63,7 +61,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "1f3ecc42", "metadata": {}, @@ -147,7 +144,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "851a2ec9-9390-49a4-8412-3e132c9f789d", "metadata": {}, @@ -191,7 +187,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.6" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/pgembedding.ipynb b/docs/extras/integrations/vectorstores/pgembedding.ipynb index f2636020631..34928df3bf7 100644 --- a/docs/extras/integrations/vectorstores/pgembedding.ipynb +++ b/docs/extras/integrations/vectorstores/pgembedding.ipynb @@ -1,18 +1,17 @@ { "cells": [ { - "attachments": {}, "cell_type": "markdown", "id": "1292f057", "metadata": {}, "source": [ - "# pg_embedding\n", + "# Postgres Embedding\n", "\n", - "> [pg_embedding](https://github.com/neondatabase/pg_embedding) is an open-source vector similarity search for `Postgres` that uses Hierarchical Navigable Small Worlds for approximate nearest neighbor search.\n", + "> [Postgres Embedding](https://github.com/neondatabase/pg_embedding) is an open-source vector similarity search for `Postgres` that uses `Hierarchical Navigable Small Worlds (HNSW)` for approximate nearest neighbor search.\n", "\n", - "It supports:\n", - "- exact and approximate nearest neighbor search using HNSW\n", - "- L2 distance\n", + ">It supports:\n", + ">- exact and approximate nearest neighbor search using HNSW\n", + ">- L2 distance\n", "\n", "This notebook shows how to use the Postgres vector database (`PGEmbedding`).\n", "\n", @@ -36,7 +35,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "b2e49694", "metadata": {}, @@ -158,7 +156,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "7ef7b052", "metadata": {}, @@ -167,7 +164,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "939151f7", "metadata": {}, @@ -192,7 +188,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "f9510e6b", "metadata": {}, @@ -214,7 +209,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "7adacf29", "metadata": {}, @@ -236,7 +230,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "528893fb", "metadata": {}, @@ -330,7 +323,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.6" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/scann.ipynb b/docs/extras/integrations/vectorstores/scann.ipynb index 7eb32642f15..4d63bd28831 100644 --- a/docs/extras/integrations/vectorstores/scann.ipynb +++ b/docs/extras/integrations/vectorstores/scann.ipynb @@ -182,7 +182,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.11" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/supabase.ipynb b/docs/extras/integrations/vectorstores/supabase.ipynb index 19dbc3d3661..9ba5dacd08d 100644 --- a/docs/extras/integrations/vectorstores/supabase.ipynb +++ b/docs/extras/integrations/vectorstores/supabase.ipynb @@ -1,7 +1,6 @@ { "cells": [ { - "attachments": {}, "cell_type": "markdown", "id": "683953b3", "metadata": {}, @@ -10,7 +9,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "cc80fa84-1f2f-48b4-bd39-3e6412f012f1", "metadata": {}, @@ -87,7 +85,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "69bff365-3039-4ff8-a641-aa190166179d", "metadata": {}, @@ -237,7 +234,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "18152965", "metadata": {}, @@ -246,7 +242,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "ea13e80a", "metadata": {}, @@ -287,7 +282,6 @@ ] }, { - "attachments": {}, "cell_type": "markdown", "id": "794a7552", "metadata": {}, @@ -439,7 +433,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.6" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/usearch.ipynb b/docs/extras/integrations/vectorstores/usearch.ipynb index 9778a9884de..b4aefa2a1cc 100644 --- a/docs/extras/integrations/vectorstores/usearch.ipynb +++ b/docs/extras/integrations/vectorstores/usearch.ipynb @@ -8,7 +8,7 @@ "# USearch\n", ">[USearch](https://unum-cloud.github.io/usearch/) is a Smaller & Faster Single-File Vector Search Engine\n", "\n", - "USearch's base functionality is identical to FAISS, and the interface should look familiar if you have ever investigated Approximate Nearest Neigbors search. FAISS is a widely recognized standard for high-performance vector search engines. USearch and FAISS both employ the same HNSW algorithm, but they differ significantly in their design principles. USearch is compact and broadly compatible without sacrificing performance, with a primary focus on user-defined metrics and fewer dependencies." + ">USearch's base functionality is identical to FAISS, and the interface should look familiar if you have ever investigated Approximate Nearest Neigbors search. FAISS is a widely recognized standard for high-performance vector search engines. USearch and FAISS both employ the same HNSW algorithm, but they differ significantly in their design principles. USearch is compact and broadly compatible without sacrificing performance, with a primary focus on user-defined metrics and fewer dependencies." ] }, { @@ -187,7 +187,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.1" + "version": "3.10.12" } }, "nbformat": 4, diff --git a/docs/extras/integrations/vectorstores/xata.ipynb b/docs/extras/integrations/vectorstores/xata.ipynb index 601e8599f55..42f2e012e75 100644 --- a/docs/extras/integrations/vectorstores/xata.ipynb +++ b/docs/extras/integrations/vectorstores/xata.ipynb @@ -232,7 +232,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.9" + "version": "3.10.12" } }, "nbformat": 4,