Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit8f8d8bf

Browse files
authored
Mostly Revert 'GITBOOK-31: Announcing the 1.0 SDK' (#1351)
1 parent0b34be2 commit8f8d8bf

10 files changed

+56
-9
lines changed

‎pgml-cms/blog/announcing-gptq-and-ggml-quantized-llm-support-for-huggingface-transformers.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,9 @@ description: >-
33
GPTQ & GGML allow PostgresML to fit larger models in less RAM. These
44
algorithms perform inference significantly faster on NVIDIA, Apple and Intel
55
hardware.
6+
featured:false
7+
tags:[engineering]
8+
image:".gitbook/assets/image (14).png"
69
---
710

811
#Announcing GPTQ & GGML Quantized LLM support for Huggingface Transformers

‎pgml-cms/blog/announcing-support-for-aws-us-east-1-region.md

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,10 @@
1+
---
2+
description:>-
3+
We added aws us east 1 to our list of support aws regions.
4+
featured:false
5+
tags:[product]
6+
---
7+
18
#Announcing Support for AWS us-east-1 Region
29

310
<divalign="left">

‎pgml-cms/blog/data-is-living-and-relational.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,8 @@ description: >-
33
A common problem with data science and machine learning tutorials is the
44
published and studied datasets are often nothing like what you’ll find in
55
industry.
6+
featured:false
7+
tags:[engineering]
68
---
79

810
#Data is Living and Relational

‎pgml-cms/blog/generating-llm-embeddings-with-open-source-models-in-postgresml.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,8 @@
22
description:>-
33
How to use the pgml.embed(...) function to generate embeddings with free and
44
open source models in your own database.
5+
image:".gitbook/assets/blog_image_generating_llm_embeddings.png"
6+
features:true
57
---
68

79
#Generating LLM embeddings with open source models in PostgresML

‎pgml-cms/blog/how-to-improve-search-results-with-machine-learning.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,9 @@ description: >-
33
PostgresML makes it easy to use machine learning on your data and scale
44
workloads horizontally in our cloud. One of the most common use cases is to
55
improve search results.
6+
featured:true
7+
image:".gitbook/assets/image (2) (2).png"
8+
tags:["Engineering"]
69
---
710

811
#How-to Improve Search Results with Machine Learning

‎pgml-cms/blog/introducing-the-openai-switch-kit-move-from-closed-to-open-source-ai-in-minutes.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,11 @@
11
---
2+
featured:true
3+
tags:[engineering, product]
24
image:https://postgresml.org/dashboard/static/images/open_source_ai_social_share.png
35
description:>-
46
Quickly and easily transition from the confines of the OpenAI APIs to higher
57
quality embeddings and unrestricted text generation models.
8+
image:".gitbook/assets/blog_image_switch_kit.png"
69
---
710

811
#Introducing the OpenAI Switch Kit: Move from closed to open-source AI in minutes

‎pgml-cms/blog/postgres-full-text-search-is-awesome.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@
22
description:>-
33
If you want to improve your search results, don't rely on expensive O(n*m)
44
word frequency statistics. Get new sources of data instead.
5+
image:".gitbook/assets/image (53).png"
56
---
67

78
#Postgres Full Text Search is Awesome!

‎pgml-cms/blog/postgresml-is-going-multicloud.md

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,16 @@
11
#PostgresML is going multicloud
22

3+
<divalign="left">
4+
5+
<figure><imgsrc=".gitbook/assets/lev.jpg"alt="Author"width="100"><figcaption></figcaption></figure>
6+
7+
</div>
8+
9+
Lev Kokotov
10+
11+
Jan 18, 2024
12+
13+
314
We started PostgresML two years ago with the goal of making machine learning and AI accessible and easy for everyone. To make this a reality, we needed to deploy PostgresML as closely as possible to our end users. With that goal mind, today we're proud to announce support for a new cloud provider: Azure.
415

516
###How we got here

‎pgml-cms/blog/speeding-up-vector-recall-5x-with-hnsw.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,9 @@ description: >-
33
HNSW indexing is the latest upgrade in vector recall performance. In this post
44
we announce our updated SDK that utilizes HNSW indexing to give world class
55
performance in vector search.
6+
tags:[engineering]
7+
featured:true
8+
image:".gitbook/assets/blog_image_hnsw.png"
69
---
710

811
#Speeding up vector recall 5x with HNSW

‎pgml-cms/blog/using-postgresml-with-django-and-embedding-search.md

Lines changed: 21 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,21 @@
11
---
2-
tags:
3-
-engineering
2+
description:>-
3+
An example application using PostgresML and Django to build embedding based search.
4+
tags:[engineering]
45
---
56

67
#Using PostgresML with Django and embedding search
78

9+
<divalign="left">
10+
11+
<figure><imgsrc=".gitbook/assets/lev.jpg"alt="Author"width="100"><figcaption></figcaption></figure>
12+
13+
</div>
14+
15+
Lev Kokotov
16+
17+
Feb 15, 2024
18+
819
Building web apps on top of PostgresML allows anyone to integrate advanced machine learning and AI features into their products without much work or needing to understand how it really works. In this blog post, we'll talk about building a classic to-do Django app, with the spicy addition of semantic search powered by embedding models running inside your PostgreSQL database.
920

1021
###Getting the code
@@ -56,13 +67,14 @@ And that's it! In just a few lines of code, we're generating and storing high qu
5667

5768
Djago Rest Framework provides the bulk of the implementation. We just added a`ModelViewSet` for the`TodoItem` model, with just one addition: a search endpoint. The search endpoint required us to write a bit of SQL to embed the search query and accept a few filters, but the core of it can be summarized in a single annotation on the query set:
5869

59-
<preclass="language-python"><codeclass="lang-python"><strong>results = TodoItem.objects.annotate(
60-
</strong> similarity=RawSQL(
70+
```python
71+
results= TodoItem.objects.annotate(
72+
similarity=RawSQL(
6173
"pgml.embed('intfloat/e5-small',%s)::vector(384) &#x3C;=> embedding",
6274
[query],
6375
)
6476
).order_by("similarity")
65-
</code></pre>
77+
```
6678

6779
This single line of SQL does quite a bit:
6880

@@ -76,7 +88,7 @@ All of this happens inside PostgresML. Our Django app doesn't need to implement
7688

7789
Before going forward, make sure you have the app running either locally or in a cloud provider of your choice. If hosting it somewhere, replace`localhost:8000` with the URL and port of your service.
7890

79-
The simplest way to interact with it is to use cURL oranHTTP client of your preference. If running in debug mode locally, the Rest Framework provides a nice web UI which you can access on[http://localhost:8000/api/todos/](http://localhost:8000/api/todo/) using a browser.
91+
The simplest way to interact with it is to use cURL oryour preferredHTTP client. If running in debug mode locally, the Rest Framework provides a nice web UI which you can access on[http://localhost:8000/api/todo/](http://localhost:8000/api/todo/) using a browser.
8092

8193
To create a to-do item with cURL, you can just run this:
8294

@@ -103,13 +115,13 @@ In return, you'll get your to-do item alongside the embedding of the `descriptio
103115

104116
The embedding contains 384 floating point numbers; we removed most of them in this blog post to make sure it fits on the page.
105117

106-
You can try creating multiple to-do items for fun and profit. If the description is changed, so will the embedding, demonstrating how the`intfloat/e5-small` modelis understanding the semantic meaning of your text.
118+
You can try creating multiple to-do items for fun and profit. If the description is changed, so will the embedding, demonstrating how the`intfloat/e5-small` modelunderstands the semantic meaning of your text.
107119

108120
###Searching
109121

110122
Once you have a few embeddings and to-dos stored in your database, the fun part of searching can begin. In a typical search example with PostgreSQL, you'd now be using`tsvector` to keyword match your to-dos to the search query with term frequency. That's a good technique, but semantic search is better.
111123

112-
We've created a simplesearch endpointthataccepts a query, a completed to-do filter, and a limit. To use it, you can justdo this:
124+
Oursearch endpoint accepts a query, a completed to-do filter, and a limit. To use it, you can justrun this:
113125

114126
```bash
115127
curl \
@@ -122,7 +134,7 @@ curl \
122134
If you've created a bunch of different to-do items, you should get only one search result back, and exactly the one you were expecting:
123135

124136
```json
125-
"Make a New Year resolution list"
137+
"Make a New Year resolution"
126138
```
127139

128140
You can increase the`limit` to something larger and you should get more documents, in decreasing order of relevance.

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp