From 37dee5451bbbfb9b30dbdf61f607b17a62fbe434 Mon Sep 17 00:00:00 2001
From: davidmezzetti <561939+davidmezzetti@users.noreply.github.com>
Date: Thu, 20 Apr 2023 10:06:50 -0400
Subject: [PATCH] Update documentation

---
 docs/embeddings/configuration/index.md | 11 +++++++----
 src/python/txtai/ann/base.py           |  3 ++-
 src/python/txtai/database/base.py      |  5 +++--
 src/python/txtai/database/factory.py   |  6 +++---
 src/python/txtai/graph/base.py         |  3 ++-
 src/python/txtai/vectors/base.py       |  2 +-
 6 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/docs/embeddings/configuration/index.md b/docs/embeddings/configuration/index.md
index 9e373f195..f55c16051 100644
--- a/docs/embeddings/configuration/index.md
+++ b/docs/embeddings/configuration/index.md
@@ -106,11 +106,12 @@ Instruction-based models use prefixes to modify how embeddings are computed. Thi
 
 ## backend
 ```yaml
-backend: faiss|hnsw|annoy
+backend: faiss|hnsw|annoy|custom
 ```
 
 Approximate Nearest Neighbor (ANN) index backend for storing generated sentence embeddings. `Defaults to faiss`. Additional backends require the
-[similarity](../../install/#similarity) extras package to be installed.
+[similarity](../../install/#similarity) extras package to be installed. Add custom backends via setting this parameter to the fully resolvable
+class string.
 
 Backend-specific settings are set with a corresponding configuration object having the same name as the backend (i.e. annoy, faiss, or hnsw). None of these are required and are set to defaults if omitted.
 
@@ -159,10 +160,10 @@ See [Annoy documentation](https://github.com/spotify/annoy#full-python-api) for
 
 ## content
 ```yaml
-content: string|boolean
+content: boolean|sqlite|duckdb|custom
 ```
 
-Enables content storage. When true, the default content storage engine will be used. `Defaults to sqlite`. Otherwise, the string must specify the supported content storage engine to use.
+Enables content storage. When true, the default storage engine, `sqlite` will be used. Also supports `duckdb`. Add custom storage engines via setting this parameter to the fully resolvable class string.
 
 ## functions
 ```yaml
@@ -205,6 +206,8 @@ graph:
 
 Enables graph storage. When set, a graph network is built using the embeddings index. Graph nodes are synced with each embeddings index operation (index/upsert/delete). Graph edges are created using the embeddings index upon completion of each index/upsert/delete embeddings index call.
 
+Add custom graph storage engines via setting the `graph.backend` parameter to the fully resolvable class string.
+
 Defaults are tuned so that in most cases these values don't need to be changed. 
 
 ### topics
diff --git a/src/python/txtai/ann/base.py b/src/python/txtai/ann/base.py
index 182278651..b27e99b2f 100644
--- a/src/python/txtai/ann/base.py
+++ b/src/python/txtai/ann/base.py
@@ -10,7 +10,8 @@
 
 class ANN:
     """
-    Base class for ANN instances.
+    Base class for ANN instances. This class builds vector indexes to support similarity search.
+    The built-in ANN backends store ids and vectors. Content storage is supported via database instances.
     """
 
     def __init__(self, config):
diff --git a/src/python/txtai/database/base.py b/src/python/txtai/database/base.py
index d619ce8d4..2a4674e61 100644
--- a/src/python/txtai/database/base.py
+++ b/src/python/txtai/database/base.py
@@ -14,8 +14,9 @@
 
 class Database:
     """
-    Base class for database instances. This class encapsulates a document-oriented database
-    used for storing key-value content stored as dicts.
+    Base class for database instances. This class encapsulates a content database used for
+    storing field content as dicts and objects. The database instance works in conjuction
+    with a vector index to execute SQL-driven similarity search.
     """
 
     def __init__(self, config):
diff --git a/src/python/txtai/database/factory.py b/src/python/txtai/database/factory.py
index 7ac92d827..ae680829f 100644
--- a/src/python/txtai/database/factory.py
+++ b/src/python/txtai/database/factory.py
@@ -36,10 +36,10 @@ def create(config):
             content = "sqlite"
 
         # Create document database instance
-        if content == "sqlite":
-            database = SQLite(config)
-        elif content == "duckdb":
+        if content == "duckdb":
             database = DuckDB(config)
+        elif content == "sqlite":
+            database = SQLite(config)
         elif content:
             database = DatabaseFactory.resolve(content, config)
 
diff --git a/src/python/txtai/graph/base.py b/src/python/txtai/graph/base.py
index 28a4ef934..d99b39c94 100644
--- a/src/python/txtai/graph/base.py
+++ b/src/python/txtai/graph/base.py
@@ -18,7 +18,8 @@
 # pylint: disable=R0904
 class Graph:
     """
-    Base class for Graph instances.
+    Base class for Graph instances. This class builds graph networks. Supports topic modeling
+    and relationship traversal.
     """
 
     def __init__(self, config):
diff --git a/src/python/txtai/vectors/base.py b/src/python/txtai/vectors/base.py
index dbbf2f5e7..0caf8c122 100644
--- a/src/python/txtai/vectors/base.py
+++ b/src/python/txtai/vectors/base.py
@@ -12,7 +12,7 @@
 
 class Vectors:
     """
-    Base class for sentence embeddings/vector models.
+    Base class for sentence embeddings/vector models. Vector models transform input content into numeric vectors.
     """
 
     def __init__(self, config, scoring):