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

Commit52c9c81

Browse files
Montana/guides (#1569)
Co-authored-by: SilasMarvin <19626586+SilasMarvin@users.noreply.github.com>
1 parentbffcfd8 commit52c9c81

File tree

66 files changed

+421
-1574
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

66 files changed

+421
-1574
lines changed

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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -120,7 +120,7 @@ LIMIT 5;
120120

121121
##Generating embeddings from natural language text
122122

123-
PostgresML provides a simple interface to generate embeddings from text in your database. You can use the[`pgml.embed`](https://postgresml.org/docs/guides/transformers/embeddings) function to generate embeddings for a column of text. The function takes a transformer name and a text value. The transformer will automatically be downloaded and cached on your connection process for reuse. You can see a list of potential good candidate models to generate embeddings on the[Massive Text Embedding Benchmark leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
123+
PostgresML provides a simple interface to generate embeddings from text in your database. You can use the[`pgml.embed`](https://postgresml.org/docs/open-source/pgml/guides/transformers/embeddings) function to generate embeddings for a column of text. The function takes a transformer name and a text value. The transformer will automatically be downloaded and cached on your connection process for reuse. You can see a list of potential good candidate models to generate embeddings on the[Massive Text Embedding Benchmark leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
124124

125125
Since our corpus of documents (movie reviews) are all relatively short and similar in style, we don't need a large model.[`Alibaba-NLP/gte-base-en-v1.5`](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) will be a good first attempt. The great thing about PostgresML is you can always regenerate your embeddings later to experiment with different embedding models.
126126

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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -210,7 +210,7 @@ We have truncated the output to two items
210210

211211
!!!
212212

213-
We also have asynchronous versions of the create and`create_stream` functions relatively named`create_async` and`create_stream_async`. Checkout[our documentation](https://postgresml.org/docs/guides/opensourceai) for a complete guide of the open-source AI SDK including guides on how to specify custom models.
213+
We also have asynchronous versions of the create and`create_stream` functions relatively named`create_async` and`create_stream_async`. Checkout[our documentation](https://postgresml.org/docs/open-source/pgml/guides/opensourceai) for a complete guide of the open-source AI SDK including guides on how to specify custom models.
214214

215215
PostgresML is free and open source. To run the above examples yourself[create an account](https://postgresml.org/signup), install korvus, and get running!
216216

‎pgml-cms/blog/semantic-search-in-postgres-in-15-minutes.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -152,7 +152,7 @@ SELECT '[1,2,3]'::vector <=> '[2,3,4]'::vector;
152152

153153
!!!
154154

155-
Other distance functions have similar formulas and provide convenient operators to use as well. It may be worth testing other operators and to see which performs better for your use case. For more information on the other distance functions, take a look at our[Embeddings guide](https://postgresml.org/docs/guides/embeddings/vector-similarity).
155+
Other distance functions have similar formulas and provide convenient operators to use as well. It may be worth testing other operators and to see which performs better for your use case. For more information on the other distance functions, take a look at our[Embeddings guide](https://postgresml.org/docs/open-source/pgml/guides/embeddings/vector-similarity).
156156

157157
Going back to our search example, we can compute the cosine distance between our query embedding and our documents:
158158

‎pgml-cms/docs/SUMMARY.md

Lines changed: 83 additions & 46 deletions
Original file line numberDiff line numberDiff line change
@@ -6,11 +6,16 @@
66
*[Getting started](introduction/getting-started/README.md)
77
*[Create your database](introduction/getting-started/create-your-database.md)
88
*[Connect your app](introduction/getting-started/connect-your-app.md)
9-
*[Import your data](introduction/getting-started/import-your-data/README.md)
10-
*[Logical replication](introduction/getting-started/import-your-data/logical-replication/README.md)
11-
*[Foreign Data Wrappers](introduction/getting-started/import-your-data/foreign-data-wrappers.md)
12-
*[Move data with COPY](introduction/getting-started/import-your-data/copy.md)
13-
*[Migrate with pg_dump](introduction/getting-started/import-your-data/pg-dump.md)
9+
*[Import your data](introduction/import-your-data/README.md)
10+
*[Logical replication](introduction/import-your-data/logical-replication/README.md)
11+
*[Foreign Data Wrappers](introduction/import-your-data/foreign-data-wrappers.md)
12+
*[Move data with COPY](introduction/import-your-data/copy.md)
13+
*[Migrate with pg_dump](introduction/import-your-data/pg-dump.md)
14+
*[Storage & Retrieval](introduction/import-your-data/storage-and-retrieval/README.md)
15+
*[Documents](introduction/import-your-data/storage-and-retrieval/documents.md)
16+
*[Partitioning](introduction/import-your-data/storage-and-retrieval/partitioning.md)
17+
*[LLM based pipelines with PostgresML and dbt (data build tool)](introduction/import-your-data/storage-and-retrieval/llm-based-pipelines-with-postgresml-and-dbt-data-build-tool.md)
18+
*[FAQ](introduction/faq.md)
1419

1520
##Open Source
1621

@@ -44,6 +49,61 @@
4449
*[Hyperparameter Search](open-source/pgml/api/pgml.train/hyperparameter-search.md)
4550
*[Joint Optimization](open-source/pgml/api/pgml.train/joint-optimization.md)
4651
*[pgml.tune()](open-source/pgml/api/pgml.tune.md)
52+
*[Guides](open-source/pgml/guides/README.md)
53+
*[Embeddings](open-source/pgml/guides/embeddings/README.md)
54+
*[In-database Generation](open-source/pgml/guides/embeddings/in-database-generation.md)
55+
*[Dimensionality Reduction](open-source/pgml/guides/embeddings/dimensionality-reduction.md)
56+
*[Aggregation](open-source/pgml/guides/embeddings/vector-aggregation.md)
57+
*[Similarity](open-source/pgml/guides/embeddings/vector-similarity.md)
58+
*[Normalization](open-source/pgml/guides/embeddings/vector-normalization.md)
59+
*[Search](open-source/pgml/guides/improve-search-results-with-machine-learning.md)
60+
*[Chatbots](open-source/pgml/guides/chatbots/README.md)
61+
*[Supervised Learning](open-source/pgml/guides/supervised-learning.md)
62+
*[Unified RAG](open-source/pgml/guides/unified-rag.md)
63+
*[Natural Language Processing](open-source/pgml/guides/natural-language-processing.md)
64+
*[Vector database](open-source/pgml/guides/vector-database.md)
65+
<!--
66+
* [Search]()
67+
* [Keyword Search]()
68+
* [Vector Search]()
69+
* [Hybrid Search]()
70+
* [Ranking]()
71+
* [Transformers & LLMs]()
72+
* [Text Generation]()
73+
* [Prompt Engineering]()
74+
* [Unified RAG]()
75+
* [Personalization]()
76+
* [Recommendations]()
77+
* [Forecasting]()
78+
* [Time series]()
79+
* [Events]()
80+
* [Fraud Detection]()
81+
* [Incentive Optimization]()
82+
* [Machine Learning]()
83+
* [Feature Engineering]()
84+
* [Regression]()
85+
* [Classification]()
86+
* [Clustering]()
87+
* [Matrix Decomposition]()
88+
* [Natural Language Processing]()
89+
* [Tokenization]()
90+
* [Chunking]()
91+
* [Text Generation]()
92+
* [Sentiment Analysis]()
93+
* [Summarization]()
94+
-->
95+
*[Developers](open-source/pgml/developers/README.md)
96+
*[Local Docker Development](open-source/pgml/developers/quick-start-with-docker.md)
97+
*[Installation](open-source/pgml/developers/installation.md)
98+
*[Contributing](open-source/pgml/developers/contributing.md)
99+
*[Distributed Training](open-source/pgml/developers/distributed-training.md)
100+
*[GPU Support](open-source/pgml/developers/gpu-support.md)
101+
*[Self-hosting](open-source/pgml/developers/self-hosting/README.md)
102+
*[Pooler](open-source/pgml/developers/self-hosting/pooler.md)
103+
*[Building from source](open-source/pgml/developers/self-hosting/building-from-source.md)
104+
*[Replication](open-source/pgml/developers/self-hosting/replication.md)
105+
*[Backups](open-source/pgml/developers/self-hosting/backups.md)
106+
*[Running on EC2](open-source/pgml/developers/self-hosting/running-on-ec2.md)
47107
*[Korvus](open-source/korvus/README.md)
48108
*[API](open-source/korvus/api/README.md)
49109
*[Collections](open-source/korvus/api/collections.md)
@@ -53,6 +113,7 @@
53113
*[RAG](open-source/korvus/guides/rag.md)
54114
*[Vector Search](open-source/korvus/guides/vector-search.md)
55115
*[Document Search](open-source/korvus/guides/document-search.md)
116+
*[OpenSourceAI](open-source/korvus/guides/opensourceai.md)
56117
*[Example Apps](open-source/korvus/example-apps/README.md)
57118
*[Semantic Search](open-source/korvus/example-apps/semantic-search.md)
58119
*[RAG with OpenAI](open-source/korvus/example-apps/rag-with-openai.md)
@@ -69,48 +130,24 @@
69130
*[Enterprise](cloud/enterprise/README.md)
70131
*[Teams](cloud/enterprise/teams.md)
71132
*[VPC](cloud/enterprise/vpc.md)
133+
*[Privacy Policy](cloud/privacy-policy.md)
134+
*[Terms of Service](cloud/terms-of-service.md)
72135

73-
##Guides
74-
75-
*[Embeddings](guides/embeddings/README.md)
76-
*[In-database Generation](guides/embeddings/in-database-generation.md)
77-
*[Dimensionality Reduction](guides/embeddings/dimensionality-reduction.md)
78-
*[Aggregation](guides/embeddings/vector-aggregation.md)
79-
*[Similarity](guides/embeddings/vector-similarity.md)
80-
*[Normalization](guides/embeddings/vector-normalization.md)
81-
*[Search](guides/improve-search-results-with-machine-learning.md)
82-
*[Chatbots](guides/chatbots/README.md)
83-
*[Example Application](use-cases/chatbots.md)
84-
*[Supervised Learning](guides/supervised-learning.md)
85-
*[Unified RAG](guides/unified-rag.md)
86-
*[OpenSourceAI](guides/opensourceai.md)
87-
*[Natural Language Processing](guides/natural-language-processing.md)
88-
*[Vector database](guides/vector-database.md)
89-
90-
##Resources
136+
<!--
137+
## TODO
91138
139+
-- Merge into Introduction > Overview
92140
* [Architecture](resources/architecture/README.md)
93141
* [Why PostgresML?](resources/architecture/why-postgresml.md)
94-
*[FAQs](resources/faqs.md)
95-
*[Data Storage & Retrieval](resources/data-storage-and-retrieval/README.md)
96-
*[Documents](resources/data-storage-and-retrieval/documents.md)
97-
*[Partitioning](resources/data-storage-and-retrieval/partitioning.md)
98-
*[LLM based pipelines with PostgresML and dbt (data build tool)](resources/data-storage-and-retrieval/llm-based-pipelines-with-postgresml-and-dbt-data-build-tool.md)
99-
*[Benchmarks](resources/benchmarks/postgresml-is-8-40x-faster-than-python-http-microservices.md)
100-
*[PostgresML is 8-40x faster than Python HTTP microservices](resources/benchmarks/postgresml-is-8-40x-faster-than-python-http-microservices.md)
101-
*[Scaling to 1 Million Requests per Second](resources/benchmarks/million-requests-per-second.md)
102-
*[MindsDB vs PostgresML](resources/benchmarks/mindsdb-vs-postgresml.md)
103-
*[GGML Quantized LLM support for Huggingface Transformers](resources/benchmarks/ggml-quantized-llm-support-for-huggingface-transformers.md)
104-
*[Making Postgres 30 Percent Faster in Production](resources/benchmarks/making-postgres-30-percent-faster-in-production.md)
105-
*[Developer Docs](resources/developer-docs/README.md)
106-
*[Local Docker Development](resources/developer-docs/quick-start-with-docker.md)
107-
*[Installation](resources/developer-docs/installation.md)
108-
*[Contributing](resources/developer-docs/contributing.md)
109-
*[Distributed Training](resources/developer-docs/distributed-training.md)
110-
*[GPU Support](resources/developer-docs/gpu-support.md)
111-
*[Self-hosting](resources/developer-docs/self-hosting/README.md)
112-
*[Pooler](resources/developer-docs/self-hosting/pooler.md)
113-
*[Building from source](resources/developer-docs/self-hosting/building-from-source.md)
114-
*[Replication](resources/developer-docs/self-hosting/replication.md)
115-
*[Backups](resources/developer-docs/self-hosting/backups.md)
116-
*[Running on EC2](resources/developer-docs/self-hosting/running-on-ec2.md)
142+
143+
## Reference
144+
145+
* [SQL]()
146+
* [Explain plans]()
147+
* [Composition]()
148+
* [LLMs]()
149+
* [LLama]()
150+
* [GPT]()
151+
* [Facon]()
152+
* [Glossary]()
153+
-->
File renamed without changes.

0 commit comments

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