Content-Length: 101808 | pFad | http://github.com/postgresml/postgresml/pull/1320.diff
thub.com diff --git a/pgml-cms/docs/introduction/apis/client-sdks/collections.md b/pgml-cms/docs/introduction/apis/client-sdks/collections.md index 2ebc415d5..c5e4df68d 100644 --- a/pgml-cms/docs/introduction/apis/client-sdks/collections.md +++ b/pgml-cms/docs/introduction/apis/client-sdks/collections.md @@ -1,3 +1,7 @@ +--- +description: >- + Organizational building blocks of the SDK. Manage all documents and related chunks, embeddings, tsvectors, and pipelines. +--- # Collections Collections are the organizational building blocks of the SDK. They manage all documents and related chunks, embeddings, tsvectors, and pipelines. diff --git a/pgml-cms/docs/introduction/apis/client-sdks/pipelines.md b/pgml-cms/docs/introduction/apis/client-sdks/pipelines.md index 26305c3c3..1bae53481 100644 --- a/pgml-cms/docs/introduction/apis/client-sdks/pipelines.md +++ b/pgml-cms/docs/introduction/apis/client-sdks/pipelines.md @@ -1,3 +1,7 @@ +--- +description: >- + Pipelines are composed of a model, splitter, and additional optional arguments. +--- # Pipelines Pipelines are composed of a Model, Splitter, and additional optional arguments. Collections can have any number of Pipelines. Each Pipeline is ran everytime documents are upserted. diff --git a/pgml-cms/docs/introduction/apis/client-sdks/tutorials/extractive-question-answering.md b/pgml-cms/docs/introduction/apis/client-sdks/tutorials/extractive-question-answering.md index f934f61d1..78abc3a09 100644 --- a/pgml-cms/docs/introduction/apis/client-sdks/tutorials/extractive-question-answering.md +++ b/pgml-cms/docs/introduction/apis/client-sdks/tutorials/extractive-question-answering.md @@ -1,3 +1,7 @@ +--- +description: >- + JavaScript and Python code snippets for end-to-end question answering. +--- # Extractive Question Answering Here is the documentation for the JavaScript and Python code snippets performing end-to-end question answering: diff --git a/pgml-cms/docs/introduction/apis/client-sdks/tutorials/semantic-search-using-instructor-model.md b/pgml-cms/docs/introduction/apis/client-sdks/tutorials/semantic-search-using-instructor-model.md index 20d0aa756..697845b55 100644 --- a/pgml-cms/docs/introduction/apis/client-sdks/tutorials/semantic-search-using-instructor-model.md +++ b/pgml-cms/docs/introduction/apis/client-sdks/tutorials/semantic-search-using-instructor-model.md @@ -1,3 +1,7 @@ +--- +description: >- + JavaScript and Python code snippets for using instructor models in more advanced search use cases. +--- # Semantic Search using Instructor model This shows using instructor models in the `pgml` SDK for more advanced use cases. diff --git a/pgml-cms/docs/introduction/apis/client-sdks/tutorials/summarizing-question-answering.md b/pgml-cms/docs/introduction/apis/client-sdks/tutorials/summarizing-question-answering.md index 02c9bfaa2..caa7c8a59 100644 --- a/pgml-cms/docs/introduction/apis/client-sdks/tutorials/summarizing-question-answering.md +++ b/pgml-cms/docs/introduction/apis/client-sdks/tutorials/summarizing-question-answering.md @@ -1,3 +1,7 @@ +--- +description: >- + JavaScript and Python code snippets for text summarization. +--- # Summarizing Question Answering Here are the Python and JavaScript examples for text summarization using `pgml` SDK diff --git a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.deploy.md b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.deploy.md index e5c52f793..22dd3733c 100644 --- a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.deploy.md +++ b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.deploy.md @@ -1,3 +1,8 @@ +--- +description: >- + Release trained models when ML quality metrics computed during training improve. Track model deployments over time and rollback if needed. +--- + # pgml.deploy() ## Deployments diff --git a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.embed.md b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.embed.md index 6b392bc26..61f6a6b0e 100644 --- a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.embed.md +++ b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.embed.md @@ -1,3 +1,8 @@ +--- +description: >- + Generate high quality embeddings with faster end-to-end vector operations without an additional vector database. +--- + # pgml.embed() Embeddings are a numeric representation of text. They are used to represent words and sentences as vectors, an array of numbers. Embeddings can be used to find similar pieces of text, by comparing the similarity of the numeric vectors using a distance measure, or they can be used as input features for other machine learning models, since most algorithms can't use text directly. diff --git a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.predict/README.md b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.predict/README.md index 144839180..6566497e5 100644 --- a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.predict/README.md +++ b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.predict/README.md @@ -1,3 +1,8 @@ +--- +description: >- + Batch predict from data in a table. Online predict with parameters passed in a query. Automatically reuse pre-processing steps from training. +--- + # pgml.predict() ## API diff --git a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.train/README.md b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.train/README.md index 6ac7491a9..d00460bfa 100644 --- a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.train/README.md +++ b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.train/README.md @@ -1,8 +1,6 @@ --- description: >- - The training function is at the heart of PostgresML. It's a powerful single - mechanism that can handle many different training tasks which are configurable - with the function parameters. + Pre-process and pull data to train a model using any of 50 different ML algorithms. --- # pgml.train() diff --git a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.transform/README.md b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.transform/README.md index 4d1c30d12..00093f135 100644 --- a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.transform/README.md +++ b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.transform/README.md @@ -1,4 +1,6 @@ --- +description: >- + Perform dozens of state-of-the-art natural language processing (NLP) tasks with thousands of models. Serve with the same Postgres infrastructure. layout: title: visible: true diff --git a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.tune.md b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.tune.md index 65e0e1c21..524b3adfd 100644 --- a/pgml-cms/docs/introduction/apis/sql-extensions/pgml.tune.md +++ b/pgml-cms/docs/introduction/apis/sql-extensions/pgml.tune.md @@ -1,3 +1,8 @@ +--- +description: >- + Fine tune open-source models on your own data. +--- + # pgml.tune() ## Fine Tuning diff --git a/pgml-cms/docs/resources/benchmarks/ggml-quantized-llm-support-for-huggingface-transformers.md b/pgml-cms/docs/resources/benchmarks/ggml-quantized-llm-support-for-huggingface-transformers.md index da53f4702..b6e5c059a 100644 --- a/pgml-cms/docs/resources/benchmarks/ggml-quantized-llm-support-for-huggingface-transformers.md +++ b/pgml-cms/docs/resources/benchmarks/ggml-quantized-llm-support-for-huggingface-transformers.md @@ -1,3 +1,7 @@ +--- +description: >- + Quantization allows PostgresML to fit larger models in less RAM. +--- # GGML Quantized LLM support for Huggingface Transformers diff --git a/pgml-cms/docs/resources/benchmarks/making-postgres-30-percent-faster-in-production.md b/pgml-cms/docs/resources/benchmarks/making-postgres-30-percent-faster-in-production.md index f999591e1..a0581b8e2 100644 --- a/pgml-cms/docs/resources/benchmarks/making-postgres-30-percent-faster-in-production.md +++ b/pgml-cms/docs/resources/benchmarks/making-postgres-30-percent-faster-in-production.md @@ -1,3 +1,7 @@ +--- +description: >- + Anyone who runs Postgres at scale knows that performance comes with trade offs. +--- # Making Postgres 30 Percent Faster in Production Anyone who runs Postgres at scale knows that performance comes with trade offs. The typical playbook is to place a pooler like PgBouncer in front of your database and turn on transaction mode. This makes multiple clients reuse the same server connection, which allows thousands of clients to connect to your database without causing a fork bomb. diff --git a/pgml-cms/docs/resources/benchmarks/million-requests-per-second.md b/pgml-cms/docs/resources/benchmarks/million-requests-per-second.md index 546172c6a..1b7f43985 100644 --- a/pgml-cms/docs/resources/benchmarks/million-requests-per-second.md +++ b/pgml-cms/docs/resources/benchmarks/million-requests-per-second.md @@ -1,3 +1,7 @@ +--- +description: >- + The question "Does it Scale?" has become somewhat of a meme in software engineering. +--- # Million Requests per Second The question "Does it Scale?" has become somewhat of a meme in software engineering. There is a good reason for it though, because most businesses plan for success. If your app, online store, or SaaS becomes popular, you want to be sure that the system powering it can serve all your new customers. diff --git a/pgml-cms/docs/resources/benchmarks/mindsdb-vs-postgresml.md b/pgml-cms/docs/resources/benchmarks/mindsdb-vs-postgresml.md index 211d32922..e56d676a8 100644 --- a/pgml-cms/docs/resources/benchmarks/mindsdb-vs-postgresml.md +++ b/pgml-cms/docs/resources/benchmarks/mindsdb-vs-postgresml.md @@ -1,3 +1,7 @@ +--- +description: >- + Compare two projects that both aim to provide an SQL interface to ML algorithms and the data they require. +--- # MindsDB vs PostgresML ## Introduction diff --git a/pgml-cms/docs/resources/benchmarks/postgresml-is-8-40x-faster-than-python-http-microservices.md b/pgml-cms/docs/resources/benchmarks/postgresml-is-8-40x-faster-than-python-http-microservices.md index fca4dc98d..73bde7c33 100644 --- a/pgml-cms/docs/resources/benchmarks/postgresml-is-8-40x-faster-than-python-http-microservices.md +++ b/pgml-cms/docs/resources/benchmarks/postgresml-is-8-40x-faster-than-python-http-microservices.md @@ -1,3 +1,7 @@ +--- +description: >- + PostgresML is a simpler alternative to that ever-growing complexity. +--- # PostgresML is 8-40x faster than Python HTTP microservices Machine learning architectures can be some of the most complex, expensive and _difficult_ arenas in modern systems. The number of technologies and the amount of required hardware compete for tightening headcount, hosting, and latency budgets. Unfortunately, the trend in the industry is only getting worse along these lines, with increased usage of state-of-the-art architectures that center around data warehouses, microservices and NoSQL databases. diff --git a/pgml-dashboard/src/api/cms.rs b/pgml-dashboard/src/api/cms.rs index b50677b2b..67525a3f8 100644 --- a/pgml-dashboard/src/api/cms.rs +++ b/pgml-dashboard/src/api/cms.rs @@ -14,7 +14,7 @@ use yaml_rust::YamlLoader; use crate::{ components::{cms::index_link::IndexLink, layouts::marketing::base::Theme, layouts::marketing::Base}, guards::Cluster, - responses::{ResponseOk, Template}, + responses::{Response, ResponseOk, Template}, templates::docs::*, utils::config, }; @@ -48,7 +48,7 @@ lazy_static! { ]) ); static ref CAREERS: Collection = Collection::new("Careers", true, HashMap::from([("a", "b")])); - static ref DOCS: Collection = Collection::new( + pub static ref DOCS: Collection = Collection::new( "Docs", false, HashMap::from([ @@ -249,6 +249,7 @@ impl Document { // MkDocs, gitbook syntax support, e.g. tabs, notes, alerts, etc. crate::utils::markdown::mkdocs(root, &arena).unwrap(); + crate::utils::markdown::wrap_tables(root, &arena).unwrap(); // Style headings like we like them let mut plugins = ComrakPlugins::default(); @@ -312,12 +313,7 @@ impl Collection { NamedFile::open(self.asset_dir.join(path)).await.ok() } - pub async fn get_content( - &self, - mut path: PathBuf, - cluster: &Cluster, - origen: &Origin<'_>, - ) -> Result