DOC: Autogen model spec (#752)

doc/source/gen_docs.py

@@ -0,0 +1,83 @@
+# Copyright 2022-2023 XProbe Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import json
+import os
+from jinja2 import Environment, FileSystemLoader
+
+
+def main():
+    template_dir = '../templates' 
+    env = Environment(loader=FileSystemLoader(template_dir))
+
+    with open('../../xinference/model/llm/llm_family.json', 'r') as file:
+        models = json.load(file)
+
+        sorted_models = sorted(models, key=lambda x: x['model_name'].lower())
+        output_dir = './models/builtin/llm'
+        os.makedirs(output_dir, exist_ok=True)
+
+        for model in sorted_models:
+            rendered = env.get_template('llm.rst.jinja').render(model)
+            output_file_path = os.path.join(output_dir, f"{model['model_name'].lower()}.rst")
+            with open(output_file_path, 'w') as output_file:
+                output_file.write(rendered)
+
+        index_file_path = os.path.join(output_dir, "index.rst")
+        with open(index_file_path, "w") as file:
+
+            rendered_index = env.get_template('llm_index.rst.jinja').render(models=sorted_models)
+            file.write(rendered_index)
+
+
+    with open('../../xinference/model/embedding/model_spec.json', 'r') as file:
+        models = json.load(file)
+
+        sorted_models = sorted(models, key=lambda x: x['model_name'].lower())
+        output_dir = './models/builtin/embedding'
+        os.makedirs(output_dir, exist_ok=True)
+
+        for model in sorted_models:
+            rendered = env.get_template('embedding.rst.jinja').render(model)
+            output_file_path = os.path.join(output_dir, f"{model['model_name'].lower()}.rst")
+            with open(output_file_path, 'w') as output_file:
+                output_file.write(rendered)
+
+        index_file_path = os.path.join(output_dir, "index.rst")
+        with open(index_file_path, "w") as file:
+
+            rendered_index = env.get_template('embedding_index.rst.jinja').render(models=sorted_models)
+            file.write(rendered_index)
+
+    with open('../../xinference/model/rerank/model_spec.json', 'r') as file:
+        models = json.load(file)
+
+        sorted_models = sorted(models, key=lambda x: x['model_name'].lower())
+        output_dir = './models/builtin/rerank'
+        os.makedirs(output_dir, exist_ok=True)
+
+        for model in sorted_models:
+            rendered = env.get_template('rerank.rst.jinja').render(model)
+            output_file_path = os.path.join(output_dir, f"{model['model_name'].lower()}.rst")
+            with open(output_file_path, 'w') as output_file:
+                output_file.write(rendered)
+
+        index_file_path = os.path.join(output_dir, "index.rst")
+        with open(index_file_path, "w") as file:
+
+            rendered_index = env.get_template('rerank_index.rst.jinja').render(models=sorted_models)
+            file.write(rendered_index)
+
+if __name__ == "__main__":
+    main()

doc/source/models/builtin/bge-base-en-v1.5.rst → doc/source/models/builtin/embedding/bge-base-en-v1.5.rst

@@ -1,4 +1,4 @@
-.. _models_builtin_bge_base_en_v1.5:
+.. _models_builtin_bge-base-en-v1.5:
 
 ================
 bge-base-en-v1.5
@@ -17,5 +17,4 @@ Specifications
 
 Execute the following command to launch the model::
 
-   xinference launch --model-name bge-base-en-v1.5 --model-type embedding
-
+   xinference launch --model-name bge-base-en-v1.5 --model-type embedding

doc/source/models/builtin/bge-base-en.rst → doc/source/models/builtin/embedding/bge-base-en.rst

@@ -1,4 +1,4 @@
-.. _models_builtin_bge_base_en:
+.. _models_builtin_bge-base-en:
 
 ===========
 bge-base-en
@@ -17,6 +17,4 @@ Specifications
 
 Execute the following command to launch the model::
 
-   xinference launch --model-name bge-base-en --model-type embedding
-
-
+   xinference launch --model-name bge-base-en --model-type embedding

doc/source/models/builtin/bge-base-zh-v1.5.rst → doc/source/models/builtin/embedding/bge-base-zh-v1.5.rst

@@ -1,4 +1,4 @@
-.. _models_builtin_bge_base_zh_v1.5:
+.. _models_builtin_bge-base-zh-v1.5:
 
 ================
 bge-base-zh-v1.5
@@ -17,5 +17,4 @@ Specifications
 
 Execute the following command to launch the model::
 
-   xinference launch --model-name bge-base-zh-v1.5 --model-type embedding
-
+   xinference launch --model-name bge-base-zh-v1.5 --model-type embedding

doc/source/models/builtin/bge-base-zh.rst → doc/source/models/builtin/embedding/bge-base-zh.rst

@@ -1,4 +1,4 @@
-.. _models_builtin_bge_base_zh:
+.. _models_builtin_bge-base-zh:
 
 ===========
 bge-base-zh
@@ -11,11 +11,10 @@ bge-base-zh
 Specifications
 ^^^^^^^^^^^^^^
 
-- **Dimensions:** 1024
+- **Dimensions:** 768
 - **Max Tokens:** 512
 - **Model ID:** BAAI/bge-base-zh
 
 Execute the following command to launch the model::
 
-   xinference launch --model-name bge-base-zh --model-type embedding
-
+   xinference launch --model-name bge-base-zh --model-type embedding

doc/source/models/builtin/bge-large-en-v1.5.rst → doc/source/models/builtin/embedding/bge-large-en-v1.5.rst

@@ -1,4 +1,4 @@
-.. _models_builtin_bge_large_en_v1.5:
+.. _models_builtin_bge-large-en-v1.5:
 
 =================
 bge-large-en-v1.5
@@ -17,5 +17,4 @@ Specifications
 
 Execute the following command to launch the model::
 
-   xinference launch --model-name bge-large-en-v1.5 --model-type embedding
-
+   xinference launch --model-name bge-large-en-v1.5 --model-type embedding