Fix404s (#308)

Author: johnsmartco

docs/antora-ragstack.yml

@@ -4,8 +4,11 @@ title: 'RAGStack'
 start_page: ROOT:index.adoc
 asciidoc:
   attributes:
+    company: 'DataStax'
     product: 'RAGStack'
-    db-cassandra: 'Serverless (Non-Vector)'
-    db-vector: 'Serverless (Vector)'
+    db-cassandra: 'Astra DB Serverless (Non-Vector)'
+    db-vector: 'Astra DB Serverless (Vector)'
+    db-serverless: 'Astra DB Serverless'
+    astra-ui: 'Astra Portal'
 nav:
 - modules/ROOT/nav.adoc

docs/modules/ROOT/pages/dev-environment.adoc

@@ -113,9 +113,9 @@ Installing the current project: temporary-astra (0.1.0)
 +
 . To deactivate the virtual environment, type `exit`.
 
-== Connect to your {db-vector} database
+== Connect to your vector-enabled {db-serverless} database
 
-RAGStack includes the Astrapy library for connecting your local development environment to your {db-vector} database.
+RAGStack includes the Astrapy library for connecting your local development environment to your vector-enabled {db-serverless} database.
 
 . If you don't have a vector database, create one at https://astra.datastax.com/.
 +

docs/modules/ROOT/pages/index.adoc

@@ -9,9 +9,9 @@
 .What is {product}?
 ****
 --
-{product} is a curated stack of the best open-source software for easing implementation of the RAG pattern in production-ready applications using Astra Vector DB or Apache Cassandra as a vector store.
+{product} is a curated stack of the best open-source software for easing implementation of the RAG pattern in production-ready applications using {db-serverless} or Apache Cassandra as a vector store.
 
-A single command (`pip install ragstack-ai`) unlocks all the open-source packages required to build production-ready RAG applications with LangChain and the Astra Vector database.
+A single command (`pip install ragstack-ai`) unlocks all the open-source packages required to build production-ready RAG applications with LangChain and the vector-enabled {db-serverless} database.
 
 For each open-source project included in {product}, we select a version lineup and then test the combination for compatibility, performance, and security. Our extensive test suite ensures that {product} components work well together so you can confidently deploy them in production. We also run security scans on all components using industry-standard tools to ensure that you are not exposed to known vulnerabilities.
 
@@ -37,7 +37,7 @@ If you are already using an open-source library that is part of {product} in you
 
 * {product} leverages the https://python.langchain.com/docs/get_started/introduction[LangChain^]{external-link-icon} ecosystem and is fully compatible with https://docs.smith.langchain.com/[LangSmith^]{external-link-icon} for monitoring your AI deployments.
 
-* The https://docs.datastax.com/en/astra/astra-db-vector/get-started/quickstart.html[{astra_db} {db-vector}] database provides the best performance and scalability for RAG applications, in addition to being particularly well-suited to RAG workloads like question answering, semantic search, and semantic caching.
+* The https://docs.datastax.com/en/astra/astra-db-vector/get-started/quickstart.html[{db-serverless}] database provides the best performance and scalability for RAG applications, in addition to being particularly well-suited to RAG workloads like question answering, semantic search, and semantic caching.
 --
 // [.landing-card-body-icon]
 // image::what-is-astra-db.svg[Astra DB card icon,40]

docs/modules/ROOT/pages/migration.adoc

@@ -29,7 +29,7 @@ RAGStack contains the below packages as of version `0.7.0`. When RAGStack is ins
 
 == Example LangChain migration
 
-Here is a simple LangChain application that loads a dataset from HuggingFace and embeds the document objects in AstraDB.
+Here is a simple LangChain application that loads a dataset from HuggingFace and embeds the document objects in {db-serverless}.
 
 .langchain-migration.py
 [%collapsible%open]

docs/modules/ROOT/pages/prerequisites.adoc

@@ -1,8 +1,8 @@
 = Notebook Prerequisites
 
-Most of our example notebooks use Astra {db-vector} as the vector database and OpenAI as the LLM.
+Most of our example notebooks use {db-serverless} as the vector database and OpenAI as the LLM.
 
-. Create an Astra {db-vector} database at https://astra.datastax.com. For detailed instructions on database creation, see https://docs.datastax.com/en/astra/astra-db-vector/administration/manage-databases.html#create-a-serverless-vector-database[Create a serverless vector database].
+. Create an vector-enabled {db-serverless} database at https://astra.datastax.com. For detailed instructions on database creation, see https://docs.datastax.com/en/astra/astra-db-vector/administration/manage-databases.html#create-a-serverless-vector-database[Create a serverless vector database].
 
 . Create an OpenAI key at https://platform.openai.com.
 . Install RAGStack with `pip install ragstack-ai`.
@@ -20,7 +20,7 @@ You'll need these values for the notebooks:
 | Must have Database Administrator permissions
 
 | Astra API endpoint
-| \https://2d6b7600-886e-4852-8f9a-1b59508df141-us-east-2.apps.astra.datastax.com\
+| \https://9d9b9999-999e-9999-9f9a-9b99999dg999-us-east-2.apps.astra.datastax.com\
 | Endpoint format is \https://<ASTRA_DB_ID>-<ASTRA_DB_REGION>.apps.astra.datastax.com
 
 | OpenAI key
@@ -33,7 +33,7 @@ You'll need these values for the notebooks:
 Automatically created if it doesn't exist.
 
 | GCP service account JSON
-| `your-project-name-017849-r83b66711494.json`
+| `your-project-name-999999-r99b99999999json`
 | Credentials for GCP usage.
 See the https://developers.google.com/workspace/guides/create-credentials#create_credentials_for_a_service_account[GCP documentation^]{external-link-icon}.
 

docs/modules/ROOT/pages/quickstart.adoc

@@ -2,7 +2,7 @@
 
 image::https://colab.research.google.com/assets/colab-badge.svg[align="left",link="https://colab.research.google.com/github/datastax/ragstack-ai/blob/main/examples/notebooks/quickstart.ipynb"]
 
-This quickstart demonstrates a basic RAG pattern using RAGStack and the AstraDB vector database to retrieve context and pass it to a language model for generation.
+This quickstart demonstrates a basic RAG pattern using RAGStack and the vector-enabled {db-serverless} database to retrieve context and pass it to a language model for generation.
 
 1. <<Construct information base>>
 2. <<Basic retrieval>>
@@ -69,13 +69,13 @@ Successfully installed astrapy-0.6.1 backoff-2.2.1 chardet-5.2.0 emoji-2.8.0 fil
 +
 . If you don't have a vector database, create one at https://astra.datastax.com/.
 +
-The Astra application token must have Database Administrator permissions (e.g. `AstraCS:WSnyFUhRxsrg…`​).
+The {db-serverless} application token is associated automatically with the Database Administrator permission. An auth token example: `AstraCS:WSnyFUhRxsrg...`).
 +
-The Astra API endpoint is available in the Astra Portal (e.g. `https://<ASTRA_DB_ID>-<ASTRA_DB_REGION>.apps.astra.datastax.com`).
+The Astra API endpoint is available in the {astra_ui}. Its format is \https://<ASTRA_DB_ID>-<ASTRA_DB_REGION>.apps.astra.datastax.com.
 +
-Create an OpenAI key at https://platform.openai.com/ (e.g. `sk-xxxx`).
+Create an OpenAI key at https://platform.openai.com/.
 +
-You must have an existing collection in Astra (e.g. `test`). If you don't have one, create one in the Astra portal, or with the Data API (using the `.env` values from the next step):
+You must have an existing collection in {db-serverless}, such as `test`). If you don't have one, create one in {astra-ui}, or with the Data API (using the `.env` values from the next step):
 +
 [source,curl]
 ----

docs/modules/ROOT/pages/tests.adoc

@@ -1,20 +1,20 @@
 = RAGStack Tests
 
-The latest RAGStack test reports are available https://ragstack-ai.testspace.com[here]{external-link-icon}.
+The latest RAGStack test reports are available on the https://ragstack-ai.testspace.com/[Testspace dashboard]{external-link-icon}.
 
 == Why is this important?
 
 Generative AI moves very quickly. The RAGStack test suite is designed to ensure that the RAGStack components are working together as expected, no matter what new features are added or what new versions of the underlying components are released upstream.
 
 This thoroughly tested approach allows your enterprise to confidently deploy RAGStack in production without worrying about breaking changes.
 
-For the test source code, see https://github.com/datastax/ragstack-ai/tree/main/ragstack-e2e-tests[ragstack-e2e-tests]{external-link-icon}.
+For the test source code, see https://github.com/datastax/ragstack-ai/tree/main/ragstack-e2e-tests[ragstack-e2e-tests]{external-link-icon} GitHub repository.
 
 == Testspace reports
 
 RAGStack tests are published to https://ragstack-ai.testspace.com/[Testspace]{external-link-icon}.
 
-Tests are run multiple times daily against DSE (Cassandra) and AstraDB (Cassandra as a Service) vector databases.
+Tests are run multiple times daily against DataStax Enterprise (DSE) and vector-enabled {db-serverless} databases.
 
 === Test suites
 [%autowidth]
@@ -28,8 +28,8 @@ Tests are run multiple times daily against DSE (Cassandra) and AstraDB (Cassandr
 e2e_tests.langchain.test_document_loaders
 e2e_tests.llama_index.test_compatibility_rag
 
-| RAGStack test suite - LangChain dev - AstraDB
-| Tests LangChain against AstraDB snapshot
+| RAGStack test suite - LangChain dev - {db-serverless}
+| Tests LangChain against {db-serverless} snapshot
 | e2e_tests.langchain.test_astra
 e2e_tests.langchain.test_compatibility_rag
 e2e_tests.langchain.test_document_loaders
@@ -43,8 +43,8 @@ e2e_tests.llama_index.test_compatibility_rag
 e2e_tests.langchain.test_document_loaders
 e2e_tests.llama_index.test_compatibility_rag
 
-| RAGStack test suite - RAGStack dev - AstraDB
-| Tests RAGStack against AstraDB snapshot
+| RAGStack test suite - RAGStack dev - {db-serverless}
+| Tests RAGStack against {db-serverless} snapshot
 | e2e_tests.langchain.test_astra
 e2e_tests.langchain.test_compatibility_rag
 e2e_tests.langchain.test_document_loaders
@@ -58,8 +58,8 @@ e2e_tests.llama_index.test_compatibility_rag
 e2e_tests.langchain.test_document_loaders
 e2e_tests.llama_index.test_compatibility_rag
 
-| RAGStack test suite - LLamaIndex dev - AstraDB
-| Tests LLamaIndex against AstraDB snapshot
+| RAGStack test suite - LLamaIndex dev - {db-serverless}
+| Tests LLamaIndex against {db-serverless} snapshot
 | e2e_tests.langchain.test_astra
 e2e_tests.langchain.test_compatibility_rag
 e2e_tests.langchain.test_document_loaders
@@ -134,7 +134,7 @@ e2e_tests.llama_index.test_compatibility_rag
 | Tests the AzureBlobStorageContainerLoader, which loads documents from an Azure Blob Storage container.
 
 | `test_astradb_loader`
-| Tests the AstraDBLoader, which loads documents from an AstraDB database.
+| Tests the AstraDBLoader, which loads documents from an {db-serverless} database.
 |===
 
 === e2e_tests.langchain_llamaindex.test_astra

docs/modules/ROOT/pages/what-is-rag.adoc

@@ -2,7 +2,7 @@
 
 image::https://colab.research.google.com/assets/colab-badge.svg[align="left",link="https://colab.research.google.com/github/datastax/ragstack-ai/blob/main/examples/notebooks/quickstart.ipynb"]
 
-Retrieval Augmented Generation (RAG) is a popular machine learning technique that retrieves prior context from a memory system to construct a prompt that is passed to a model.
+Retrieval-Augmented Generation (RAG) is a popular machine learning technique that retrieves prior context from a memory system to construct a prompt that is passed to a model.
 
 This means the power of Large Language Models, but trained on your data.
 

docs/modules/default-architecture/pages/generation.adoc

@@ -2,7 +2,9 @@
 
 Prompts are the starting point for the LLM generation process. They provide context, set the tone, define objectives, and ultimately shape the quality of the response.
 
-Prompt design is an entire field of its own, and for further reading, we recommend starting https://www.datastax.com/guides/what-is-prompt-engineering[here]{external-link-icon}. However, we will lay out a starting prompt for a basic RAG pipeline, and demonstrate the CO-STAR technique for organizing prompts for more complex tasks.
+Prompt design is an entire field of its own. See https://www.datastax.com/guides/what-is-prompt-engineering[What is Prompt Engineering in AI and How Does it Work?]{external-link-icon}. 
+
+In this topic, you can learn how to lay out a starting prompt for a basic RAG pipeline. Then read about the CO-STAR technique that can be used to organize prompts for more complex tasks.
 
 == Starting prompt
 

docs/modules/default-architecture/pages/loading.adoc

@@ -3,7 +3,7 @@
 Start with LangChain for loading your data instead of manually coding your own pipeline.
 LangChain likely already provides the functionalities you need.
 
-The examples use Astra {db-vector} database for the vector store and assume you have one available. If not, see xref:ROOT:prerequisites.adoc[].
+The examples use vector-enabled {db-serverless} database for the vector store and assume you have one available. If not, see xref:ROOT:prerequisites.adoc[].
 
 == Load PDF from file