stage progress on tutorials

deeppavlov · Dec 7, 2024 · 8caf9cf · 8caf9cf
1 parent 44db77e
commit 8caf9cf
Show file tree

Hide file tree

Showing 3 changed files with 38 additions and 41 deletions.
diff --git a/docs/source/docs_utils/notebook.py b/docs/source/docs_utils/notebook.py
@@ -136,15 +136,11 @@ def link_to_doc_page(
         if page_type == "class":
             dotpath = "autointent" + (("." + dotpath) if dotpath != "" else "")
             path = "/".join(dotpath.split("."))
-            return f"../autoapi/{path}/{obj}.html" + (
-                f"#{dotpath}.{obj}" if obj is not None else ""
-            )
+            return f"../autoapi/{path}/{obj}.html" + (f"#{dotpath}.{obj}" if obj is not None else "")
         if page_type == "method":
             dotpath = "autointent" + (("." + dotpath) if dotpath != "" else "")
             path = "/".join(dotpath.split("."))
-            return f"../autoapi/{path}.html" + (
-                f"#{dotpath}.{obj}" if obj is not None else ""
-            )
+            return f"../autoapi/{path}.html" + (f"#{dotpath}.{obj}" if obj is not None else "")
         if page_type == "tutorial":
             return f"../tutorials/tutorials.{dotpath}.py"
         if page_type == "rst":

diff --git a/tutorials/auto_configuration/python_api.py b/tutorials/auto_configuration/python_api.py
@@ -90,5 +90,29 @@
 """
 ## Vector Index Settings
 
-%mddoclink(class,context.vector_index_client,VectorIndex) is one of the key utilities of AutoIntent. It affects both the quality of the resulting classifier and the efficiency of the auto configuration process.
+%mddoclink(class,context.vector_index_client,VectorIndex) is one of the key utilities of AutoIntent. During the auto-configuration process, lots of retrieval is used. By modifying vector index settings you can select whether to save built vector index into file system and where to save it.
+
+Default options are the following:
+"""
+
+# %%
+from autointent.configs import VectorIndexConfig
+
+vector_index_config = VectorIndexConfig(
+    db_dir=None,
+    save_db=False
+)
+
+# %% [markdown]
 """
+- `db_dir=None` tells AutoIntent to store intermediate files in a current working directory
+- `save_db=False` tells AutoIntent to clear all the files after auto configuration is finished
+
+These settings can be applied in a familiar way:
+"""
+
+# %%
+custom_pipeline.set_config(vector_index_config)
+
+# %% [markdown]
+
diff --git a/tutorials/auto_configuration/search_space_configuration.py b/tutorials/auto_configuration/search_space_configuration.py
@@ -24,10 +24,7 @@
 knn_module = {
     "module_type": "knn",
     "k": [1, 5, 10, 50],
-    "embedder_name": [
-        "avsolatorio/GIST-small-Embedding-v0",
-        "infgrad/stella-base-en-v2"
-    ]
+    "embedder_name": ["avsolatorio/GIST-small-Embedding-v0", "infgrad/stella-base-en-v2"],
 }
 
 # %% [markdown]
@@ -62,7 +59,7 @@
     "search_space": [
         knn_module,
         linear_module,
-    ]
+    ],
 }
 
 # %% [markdown]
@@ -81,48 +78,28 @@
             {
                 "module_type": "vector_db",
                 "k": [10],
-                "embedder_name": [
-                    "avsolatorio/GIST-small-Embedding-v0",
-                    "infgrad/stella-base-en-v2"
-                ]
+                "embedder_name": ["avsolatorio/GIST-small-Embedding-v0", "infgrad/stella-base-en-v2"],
             }
-        ]
+        ],
     },
     {
         "node_type": "scoring",
         "metric": "scoring_roc_auc",
         "search_space": [
+            {"module_type": "knn", "k": [1, 3, 5, 10], "weights": ["uniform", "distance", "closest"]},
+            {"module_type": "linear"},
             {
-                "module_type": "knn",
+                "module_type": "dnnc",
+                "cross_encoder_name": ["BAAI/bge-reranker-base", "cross-encoder/ms-marco-MiniLM-L-6-v2"],
                 "k": [1, 3, 5, 10],
-                "weights": ["uniform", "distance", "closest"]
-            },
-            {
-                "module_type": "linear"
             },
-            {
-                "module_type": "dnnc",
-                "cross_encoder_name": [
-                    "BAAI/bge-reranker-base",
-                    "cross-encoder/ms-marco-MiniLM-L-6-v2"
-                ],
-                "k": [1, 3, 5, 10]
-            }
-        ]
+        ],
     },
     {
         "node_type": "prediction",
         "metric": "prediction_accuracy",
-        "search_space": [
-            {
-                "module_type": "threshold",
-                "thresh": [0.5]
-            },
-            {
-                "module_type": "argmax"
-            }
-        ]
-    }
+        "search_space": [{"module_type": "threshold", "thresh": [0.5]}, {"module_type": "argmax"}],
+    },
 ]
 
 # %% [markdown]