GITBOOK-3: Blog page descriptions

Moloejoe · gitbook-bot · commit 6b54aed483b4 · 2023-11-25T17:34:59.000Z
diff --git a/pgml-docs/blog/README.md b/pgml-docs/blog/README.md
@@ -6,7 +6,7 @@ description: Our blog posts
 
 * [speeding-up-vector-recall-5x-with-hnsw.md](speeding-up-vector-recall-5x-with-hnsw.md "mention")
 * [how-to-improve-search-results-with-machine-learning.md](how-to-improve-search-results-with-machine-learning.md "mention")
-* [pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots-part-i.md](pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots-part-i.md "mention")
+* [pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots.md](pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots.md "mention")
 * [announcing-support-for-aws-us-east-1-region.md](announcing-support-for-aws-us-east-1-region.md "mention")
 * [how-we-generate-javascript-and-python-sdks-from-our-canonical-rust-sdk.md](how-we-generate-javascript-and-python-sdks-from-our-canonical-rust-sdk.md "mention")
 * [announcing-gptq-and-ggml-quantized-llm-support-for-huggingface-transformers.md](announcing-gptq-and-ggml-quantized-llm-support-for-huggingface-transformers.md "mention")
diff --git a/pgml-docs/blog/SUMMARY.md b/pgml-docs/blog/SUMMARY.md
@@ -3,7 +3,7 @@
 * [Home](README.md)
 * [Speeding up vector recall 5x with HNSW](speeding-up-vector-recall-5x-with-hnsw.md)
 * [How-to Improve Search Results with Machine Learning](how-to-improve-search-results-with-machine-learning.md)
-* [pgml-chat: A command-line tool for deploying low-latency knowledge-based chatbots: Part I](pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots-part-i.md)
+* [pgml-chat: A command-line tool for deploying low-latency knowledge-based chatbots](pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots.md)
 * [Announcing Support for AWS us-east-1 Region](announcing-support-for-aws-us-east-1-region.md)
 * [LLM based pipelines with PostgresML and dbt (data build tool)](llm-based-pipelines-with-postgresml-and-dbt-data-build-tool.md)
 * [How We Generate JavaScript and Python SDKs From Our Canonical Rust SDK](how-we-generate-javascript-and-python-sdks-from-our-canonical-rust-sdk.md)
diff --git a/pgml-docs/blog/announcing-gptq-and-ggml-quantized-llm-support-for-huggingface-transformers.md b/pgml-docs/blog/announcing-gptq-and-ggml-quantized-llm-support-for-huggingface-transformers.md
@@ -1,6 +1,11 @@
-# Announcing GPTQ & GGML Quantized LLM support for Huggingface Transformers
-
+---
+description: >-
+  GPTQ & GGML allow PostgresML to fit larger models in less RAM. These
+  algorithms perform inference significantly faster on NVIDIA, Apple and Intel
+  hardware.
+---
 
+# Announcing GPTQ & GGML Quantized LLM support for Huggingface Transformers
 
 Montana Low
 
diff --git a/pgml-docs/blog/backwards-compatible-or-bust-python-inside-rust-inside-postgres.md b/pgml-docs/blog/backwards-compatible-or-bust-python-inside-rust-inside-postgres.md
@@ -1,6 +1,10 @@
-# Backwards Compatible or Bust: Python Inside Rust Inside Postgres
-
+---
+description: >-
+  A story about including Scikit-learn into our Rust extension and preserving
+  backwards compatibility in the process.
+---
 
+# Backwards Compatible or Bust: Python Inside Rust Inside Postgres
 
 Lev Kokotov
 
diff --git a/pgml-docs/blog/data-is-living-and-relational.md b/pgml-docs/blog/data-is-living-and-relational.md
@@ -1,6 +1,11 @@
-# Data is Living and Relational
-
+---
+description: >-
+  A common problem with data science and machine learning tutorials is the
+  published and studied datasets are often nothing like what you’ll find in
+  industry.
+---
 
+# Data is Living and Relational
 
 Montana Low
 
diff --git a/pgml-docs/blog/generating-llm-embeddings-with-open-source-models-in-postgresml.md b/pgml-docs/blog/generating-llm-embeddings-with-open-source-models-in-postgresml.md
@@ -1,6 +1,10 @@
-# Generating LLM embeddings with open source models in PostgresML
-
+---
+description: >-
+  How to use the pgml.embed(...) function to generate embeddings with free and
+  open source models in your own database.
+---
 
+# Generating LLM embeddings with open source models in PostgresML
 
 Montana Low
 
diff --git a/pgml-docs/blog/how-to-improve-search-results-with-machine-learning.md b/pgml-docs/blog/how-to-improve-search-results-with-machine-learning.md
@@ -1,6 +1,11 @@
-# How-to Improve Search Results with Machine Learning
-
+---
+description: >-
+  PostgresML makes it easy to use machine learning on your data and scale
+  workloads horizontally in our cloud. One of the most common use cases is to
+  improve search results.
+---
 
+# How-to Improve Search Results with Machine Learning
 
 Montana Low
 
diff --git a/pgml-docs/blog/how-we-generate-javascript-and-python-sdks-from-our-canonical-rust-sdk.md b/pgml-docs/blog/how-we-generate-javascript-and-python-sdks-from-our-canonical-rust-sdk.md
@@ -1,6 +1,10 @@
-# How We Generate JavaScript and Python SDKs From Our Canonical Rust SDK
-
+---
+description: >-
+  Our story of simultaneously writing multi-language native libraries using
+  Rust.
+---
 
+# How We Generate JavaScript and Python SDKs From Our Canonical Rust SDK
 
 Silas Marvin
 
diff --git a/pgml-docs/blog/introducing-postgresml-python-sdk-build-end-to-end-vector-search-applications-without-openai-and-pin.md b/pgml-docs/blog/introducing-postgresml-python-sdk-build-end-to-end-vector-search-applications-without-openai-and-pin.md
@@ -1,6 +1,10 @@
-# Introducing PostgresML Python SDK: Build End-to-End Vector Search Applications without OpenAI and Pinecone
-
+---
+description: >-
+  The PostgresML Python SDK is designed to facilitate the development of
+  end-to-end vector search applications without OpenAI and Pinecone.
+---
 
+# Introducing PostgresML Python SDK: Build End-to-End Vector Search Applications without OpenAI and Pinecone
 
 Santi Adavani
 
diff --git a/pgml-docs/blog/llm-based-pipelines-with-postgresml-and-dbt-data-build-tool.md b/pgml-docs/blog/llm-based-pipelines-with-postgresml-and-dbt-data-build-tool.md
@@ -1,6 +1,10 @@
-# LLM based pipelines with PostgresML and dbt (data build tool)
-
+---
+description: >-
+  Unlock the Power of Large Language Models (LLM) in Data Pipelines with
+  PostgresML and dbt.
+---
 
+# LLM based pipelines with PostgresML and dbt (data build tool)
 
 Santi Adavani
 
diff --git a/pgml-docs/blog/mindsdb-vs-postgresml.md b/pgml-docs/blog/mindsdb-vs-postgresml.md
@@ -1,6 +1,10 @@
-# MindsDB vs PostgresML
-
+---
+description: >-
+  PostgresML is more opinionated, more scalable, more capable and several times
+  faster than MindsDB.
+---
 
+# MindsDB vs PostgresML
 
 Montana Low
 
diff --git a/pgml-docs/blog/oxidizing-machine-learning.md b/pgml-docs/blog/oxidizing-machine-learning.md
@@ -1,6 +1,11 @@
-# Oxidizing Machine Learning
-
+---
+description: >-
+  PostgresML's architecture gives it a huge performance advantage over
+  traditional deployments when it comes to latency, throughput and memory
+  utilization.
+---
 
+# Oxidizing Machine Learning
 
 Lev Kokotov
 
diff --git a/pgml-docs/blog/personalize-embedding-results-with-application-data-in-your-database.md b/pgml-docs/blog/personalize-embedding-results-with-application-data-in-your-database.md
@@ -1,6 +1,10 @@
-# Personalize embedding results with application data in your database
-
+---
+description: >-
+  How to personalize results from a vector database generated with open source
+  HuggingFace models using pgvector and PostgresML.
+---
 
+# Personalize embedding results with application data in your database
 
 Montana Low
 
diff --git a/pgml-docs/blog/pg-stat-sysinfo-a-postgres-extension-for-querying-system-statistics.md b/pgml-docs/blog/pg-stat-sysinfo-a-postgres-extension-for-querying-system-statistics.md
@@ -1,6 +1,8 @@
-# PG Stat Sysinfo, a Postgres Extension for Querying System Statistics
-
+---
+description: Introducing a Postgres extension which collects system statistics
+---
 
+# PG Stat Sysinfo, a Postgres Extension for Querying System Statistics
 
 Jason Dusek
 
diff --git a/pgml-docs/blog/pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots.md b/pgml-docs/blog/pgml-chat-a-command-line-tool-for-deploying-low-latency-knowledge-based-chatbots.md
@@ -1,6 +1,10 @@
-# pgml-chat: A command-line tool for deploying low-latency knowledge-based chatbots: Part I
-
+---
+description: >-
+  pgml-chat: A command-line tool for deploying low-latency knowledge-based
+  chatbots
+---
 
+# pgml-chat: A command-line tool for deploying low-latency knowledge-based chatbots
 
 Santi Adavani
 
diff --git a/pgml-docs/blog/postgres-full-text-search-is-awesome.md b/pgml-docs/blog/postgres-full-text-search-is-awesome.md
@@ -1,6 +1,10 @@
-# Postgres Full Text Search is Awesome!
-
+---
+description: >-
+  If you want to improve your search results, don't rely on expensive O(n*m)
+  word frequency statistics. Get new sources of data instead.
+---
 
+# Postgres Full Text Search is Awesome!
 
 Montana Low
 
diff --git a/pgml-docs/blog/postgresml-as-a-memory-backend-to-auto-gpt.md b/pgml-docs/blog/postgresml-as-a-memory-backend-to-auto-gpt.md
@@ -1,6 +1,10 @@
-# PostgresML as a memory backend to Auto-GPT
-
+---
+description: >-
+  Auto-GPT is an open-source autonomous AI tool that can use PostgresML as
+  memory backend to store and access data from previous queries or private data.
+---
 
+# PostgresML as a memory backend to Auto-GPT
 
 Santi Adavani
 
diff --git a/pgml-docs/blog/postgresml-is-8-40x-faster-than-python-http-microservices.md b/pgml-docs/blog/postgresml-is-8-40x-faster-than-python-http-microservices.md
@@ -1,6 +1,11 @@
-# PostgresML is 8-40x faster than Python HTTP microservices
-
+---
+description: >-
+  PostgresML's architecture gives it a huge performance advantage over
+  traditional deployments when it comes to latency, throughput and memory
+  utilization.
+---
 
+# PostgresML is 8-40x faster than Python HTTP microservices
 
 Lev Kokotov
 
diff --git a/pgml-docs/blog/postgresml-is-moving-to-rust-for-our-2.0-release.md b/pgml-docs/blog/postgresml-is-moving-to-rust-for-our-2.0-release.md
@@ -1,6 +1,11 @@
-# PostgresML is Moving to Rust for our 2.0 Release
-
+---
+description: >-
+  In PostgresML 2.0, we'd like to address runtime speed, memory consumption and
+  the overall reliability we've seen for machine learning deployments running at
+  scale.
+---
 
+# PostgresML is Moving to Rust for our 2.0 Release
 
 Montana Low
 
diff --git a/pgml-docs/blog/postgresml-raises-usd4.7m-to-launch-serverless-ai-application-databases-based-on-postgres.md b/pgml-docs/blog/postgresml-raises-usd4.7m-to-launch-serverless-ai-application-databases-based-on-postgres.md
@@ -1,8 +1,13 @@
-# PostgresML raises $4.7M to launch serverless AI application databases based on Postgres
-
+---
+description: >-
+  With PostgresML, developers can prototype and deploy AI applications quickly
+  and at scale in a matter of minutes — a task that would otherwise have taken
+  weeks.
+---
 
+# PostgresML raises $4.7M to launch serverless AI application databases based on Postgres
 
-Montana Low, CEO
+Montana Low
 
 May 10, 2023
 
diff --git a/pgml-docs/blog/scaling-postgresml-to-1-million-requests-per-second.md b/pgml-docs/blog/scaling-postgresml-to-1-million-requests-per-second.md
@@ -1,6 +1,11 @@
-# Scaling PostgresML to 1 Million Requests per Second
-
+---
+description: >-
+  Addressing horizontal scalability concerns, we've benchmarked PostgresML and
+  ended up with an incredible 1 million requests per second using commodity
+  hardware.
+---
 
+# Scaling PostgresML to 1 Million Requests per Second
 
 Lev Kokotov
 
diff --git a/pgml-docs/blog/speeding-up-vector-recall-5x-with-hnsw.md b/pgml-docs/blog/speeding-up-vector-recall-5x-with-hnsw.md
@@ -1,3 +1,10 @@
+---
+description: >-
+  HNSW indexing is the latest upgrade in vector recall performance. In this post
+  we announce our updated SDK that utilizes HNSW indexing to give world class
+  performance in vector search.
+---
+
 # Speeding up vector recall 5x with HNSW
 
 Silas Marvin
diff --git a/pgml-docs/blog/tuning-vector-recall-while-generating-query-embeddings-in-the-database.md b/pgml-docs/blog/tuning-vector-recall-while-generating-query-embeddings-in-the-database.md
@@ -1,6 +1,10 @@
-# Tuning vector recall while generating query embeddings in the database
-
+---
+description: >-
+  How to effectively write and tune queries against large embedding collections
+  with significant speed and quality advantages compared to OpenAI + Pinecone.
+---
 
+# Tuning vector recall while generating query embeddings in the database
 
 Montana Low
 
diff --git a/pgml-docs/blog/which-database-that-is-the-question.md b/pgml-docs/blog/which-database-that-is-the-question.md
@@ -1,6 +1,11 @@
-# Which Database, That is the Question
-
+---
+description: >-
+  Choosing a database for your product sounds like a hard problem. These days,
+  we engineers have an abundance of choice, which makes this decision harder
+  than it should be. Let's look at a few options.
+---
 
+# Which Database, That is the Question
 
 Lev Kokotov
 
