Updated javascript examples a bit

postgresml · SilasMarvin · Aug 28, 2023 · Aug 24, 2023 · Aug 24, 2023 · Aug 24, 2023
commit a8526814d469c109fe49bbb7ced530fe5086b5a3
diff --git a/pgml-sdks/pgml/README.md b/pgml-sdks/pgml/README.md
@@ -3,8 +3,8 @@
 # Suported Languages
 
 We support a number of different languages:
-- [Python](/python)
-- [JavaScript](/javascript)
+- [Python](python)
+- [JavaScript](javascript)
 - Rust
 
 Our SDK is written completely in Rust and translated by Rust to our other supported languages. See each individual language for an overview and specification on how to use the SDK.

diff --git a/pgml-sdks/pgml/javascript/examples/README.md b/pgml-sdks/pgml/javascript/examples/README.md
@@ -1,16 +1,23 @@
-## Examples
+# Examples
 
-### [Semantic Search](./semantic_search.js)
+## Prerequisites
+Before running any examples first install dependencies and set the DATABASE_URL environment variable:
+```
+npm i
+export DATABASE_URL={YOUR DATABASE URL}
+```
+
+## [Semantic Search](./semantic_search.js)
 This is a basic example to perform semantic search on a collection of documents. Embeddings are created using `intfloat/e5-small` model. The results are semantically similar documemts to the query. Finally, the collection is archived.
 
-### [Question Answering](./question_answering.js)
+## [Question Answering](./question_answering.js)
 This is an example to find documents relevant to a question from the collection of documents. The query is passed to vector search to retrieve documents that match closely in the embeddings space. A score is returned with each of the search result.
 
-### [Question Answering using Instructore Model](./question_answering_instructor.js)
+## [Question Answering using Instructore Model](./question_answering_instructor.js)
 In this example, we will use `hknlp/instructor-base` model to build text embeddings instead of the default `intfloat/e5-small` model.
 
-### [Extractive Question Answering](./extractive_question_answering.js)
+## [Extractive Question Answering](./extractive_question_answering.js)
 In this example, we will show how to use `vector_recall` result as a `context` to a HuggingFace question answering model. We will use `Builtins.transform()` to run the model on the database.
 
-### [Summarizing Question Answering](./summarizing_question_answering.js)
+## [Summarizing Question Answering](./summarizing_question_answering.js)
 This is an example to find documents relevant to a question from the collection of documents and then summarize those documents.
diff --git a/pgml-sdks/pgml/javascript/examples/getting-started/README.md b/pgml-sdks/pgml/javascript/examples/getting-started/README.md
diff --git a/pgml-sdks/pgml/javascript/examples/getting-started/index.js b/pgml-sdks/pgml/javascript/examples/getting-started/index.js
diff --git a/pgml-sdks/pgml/javascript/examples/getting-started/package.json b/pgml-sdks/pgml/javascript/examples/getting-started/package.json