Introduce view and analyzer schema

libs/arangodb/langchain_arangodb/chains/graph_qa/prompts.py

@@ -8,13 +8,17 @@
 You are given an `ArangoDB Schema`. It is a YAML Spec containing:
 1. `Graph Schema`: Lists all Graphs within the ArangoDB Database Instance, along with their Edge Relationships.
 2. `Collection Schema`: Lists all Collections within the ArangoDB Database Instance, along with their document/edge properties and a document/edge example.
+3. `View Schema`: Lists all Views within the ArangoDB Database Instance, along with their linked collections and analyzers.
+4. `Analyzer Schema`: Lists all custom-built Analyzers within the ArangoDB Database Instance, along with their properties and features. Does not mention the default ArangoDB analyzers (i.e text_en, text_fr, etc.)
 
 You may also be given a set of `AQL Query Examples` to help you create the `AQL Query`. If provided, the `AQL Query Examples` should be used as a reference, similar to how `ArangoDB Schema` should be used.
 
 Things you should do:
 - Think step by step.
 - Rely on `ArangoDB Schema` and `AQL Query Examples` (if provided) to generate the query.
 - Begin the `AQL Query` by the `WITH` AQL keyword to specify all of the ArangoDB Collections required.
+- If a `View Schema` is defined and contains analyzers for specific fields, prefer using the View with the `SEARCH` and `ANALYZER` clauses instead of a direct collection scan.
+- Use `PHRASE(...)`, `TOKENS(...)`, or `IN TOKENS(...)` as appropriate when analyzers are available on a field.
 - Return the `AQL Query` wrapped in 3 backticks (```).
 - Use only the provided relationship types and properties in the `ArangoDB Schema` and any `AQL Query Examples` queries.
 - Only answer to requests related to generating an AQL Query.
@@ -56,6 +60,8 @@
 You are also given the `ArangoDB Schema`. It is a YAML Spec containing:
 1. `Graph Schema`: Lists all Graphs within the ArangoDB Database Instance, along with their Edge Relationships.
 2. `Collection Schema`: Lists all Collections within the ArangoDB Database Instance, along with their document/edge properties and a document/edge example.
+3. `View Schema`: Lists all Views within the ArangoDB Database Instance, along with their linked collections and analyzers.
+4. `Analyzer Schema`: Lists all custom-built Analyzers within the ArangoDB Database Instance, along with their properties and features. Does not mention the default ArangoDB analyzers (i.e text_en, text_fr, etc.)
 
 You will output the `Corrected AQL Query` wrapped in 3 backticks (```). Do not include any text except the Corrected AQL Query.
 

libs/arangodb/langchain_arangodb/graphs/arangodb_graph.py

@@ -20,6 +20,22 @@
 )
 from langchain_arangodb.graphs.graph_store import GraphStore
 
+DEFAULT_ANALYZERS = {
+    "text_fr",
+    "text_pt",
+    "identity",
+    "text_de",
+    "text_zh",
+    "text_fi",
+    "text_it",
+    "text_no",
+    "text_nl",
+    "text_es",
+    "text_ru",
+    "text_en",
+    "text_sv",
+}
+
 
 def get_arangodb_client(
     url: Optional[str] = None,
@@ -85,7 +101,9 @@ class ArangoGraph(GraphStore):
         in a string. If the string is longer than this limit, a string
         describing the string will be used in the schema instead. Default is 256.
     :type schema_string_limit: int
-
+    :param schema_include_views: Whether to include ArangoDB Views and Analyzers as
+        part of the schema passed to the AQL Generation prompt. Default is False.
+    :type schema_include_views: bool
         :return: None
         :rtype: None
         :raises ArangoClientError: If the ArangoDB client cannot be created.
@@ -116,6 +134,7 @@ def __init__(
         schema_include_examples: bool = True,
         schema_list_limit: int = 32,
         schema_string_limit: int = 256,
+        schema_include_views: bool = False,
     ) -> None:
         """
         Initializes the ArangoGraph instance.
@@ -132,6 +151,7 @@ def __init__(
                 schema_include_examples,
                 schema_list_limit,
                 schema_string_limit,
+                schema_include_views,
             )
 
     @property
@@ -224,6 +244,7 @@ def generate_schema(
         include_examples: bool = True,
         list_limit: int = 32,
         schema_string_limit: int = 256,
+        schema_include_views: bool = False,
     ) -> Dict[str, List[Dict[str, Any]]]:
         """
         Generates the schema of the ArangoDB Database and returns it
@@ -247,6 +268,9 @@ def generate_schema(
             in a string. If the string is longer than this limit, a string
             describing the string will be used in the schema instead. Default is 128.
         :type schema_string_limit: int
+        :param schema_include_views: Whether to include ArangoDB Views and Analyzers as
+            part of the schema passed to the AQL Generation prompt. Default is False.
+        :type schema_include_views: bool
         :return: A dictionary containing the graph schema and collection schema.
         :rtype: Dict[str, List[Dict[str, Any]]]
         :raises ValueError: If the sample ratio is not between 0 and 1.
@@ -257,6 +281,10 @@ def generate_schema(
         if not 0 <= sample_ratio <= 1:
             raise ValueError("**sample_ratio** value must be in between 0 to 1")
 
+        #####
+        # Step 1: Generate Graph Schema
+        ####
+
         graph_schema: List[Dict[str, Any]] = []
         if graph_name:
             # Fetch a single graph
@@ -283,6 +311,10 @@ def generate_schema(
                 for collection in self.db.collections()  # type: ignore
             }
 
+        #####
+        # Step 2: Generate Collection Schema
+        ####
+
         # Stores the schema of every ArangoDB Document/Edge collection
         collection_schema: List[Dict[str, Any]] = []
         for collection in self.db.collections():  # type: ignore
@@ -324,7 +356,41 @@ def generate_schema(
 
             collection_schema.append(collection_schema_entry)
 
-        return {"graph_schema": graph_schema, "collection_schema": collection_schema}
+        if not schema_include_views:
+            return {
+                "graph_schema": graph_schema,
+                "collection_schema": collection_schema,
+            }
+
+        #####
+        # Step 3: Generate View Schema
+        #####
+
+        view_schema: List[Dict[str, Any]] = []
+        for view in self.db.views():  # type: ignore
+            view_name = view["name"]
+            view_type = view["type"]
+            view_info = self.db.view(view_name)
+            key = "links" if view_type == "arangosearch" else "indexes"
+            view_schema.append(
+                {"name": view_name, "type": view_type, key: view_info.get(key, [])}  # type: ignore
+            )
+
+        #####
+        # Step 4: Generate Analyzer Schema
+        #####
+
+        analyzer_schema: List[Dict[str, Any]] = []
+        for a in self.db.analyzers():  # type: ignore
+            if a["name"] not in DEFAULT_ANALYZERS:
+                analyzer_schema.append({a["name"]: a["properties"]})
+
+        return {
+            "graph_schema": graph_schema,
+            "collection_schema": collection_schema,
+            "view_schema": view_schema,
+            "analyzer_schema": analyzer_schema,
+        }
 
     def query(
         self,