chore: import upstream snapshot with attribution

2026-07-13 13:21:23 +08:00
commit b957a53def
5423 changed files with 863745 additions and 0 deletions
@@ -0,0 +1,32 @@
+{
+  "schema": 1,
+  "description": "Extract entities related to a specified topic from the supplied input text. Returns the entities and the source text",
+  "execution_settings": {
+    "default": {
+      "max_tokens": 256,
+      "temperature": 0.0,
+      "top_p": 0.1,
+      "presence_penalty": 0.0,
+      "frequency_penalty": 0.0
+    }
+  },
+  "input_variables": [
+    {
+      "name": "input",
+      "description": "The text from which the entities are to be extracted",
+      "default": "",
+      "is_required": true
+    },
+    {
+      "name": "topic",
+      "description": "The topic of interest; the extracted entities should be related to this topic",
+      "default": "",
+      "is_required": true
+    },
+    {
+      "name": "example_entities",
+      "description": "A list of example entities from the topic. This can help guide the entity extraction",
+      "default": ""
+    }
+  ]
+}
@@ -0,0 +1,62 @@
+# Task Description
+
+1. Please extract a list of entities related to {{$topic}} from the text between the <input_context> tags.
+2. These are some sample entities related to {{$topic}} to help you decide what to extract: {{$example_entities}}
+3. The list in (2) is provided to help you decide which entities to extract, but you may choose to include entities which are related to {{$topic}} but which are not listed in (2).
+4. As the first part of your response, generate a bulleted list of each of the items in (1) together with an explanation of what they are.
+5. Go over each item in your bulleted list and read the explanation of what it is. Keep items which are related to {{$topic}}
+6. Go over each item in your bulleted list and verify that it appears between the <input_context> tags.
+7. Go over each item in your bulleted list and check for duplicates. Keep only one example of each. Duplicates may be:
+    - Abbreviations
+    - Reuse as adjectives
+    - Plurals and related changes
+8. Return the bulleted list of entities between <entities> and </entities>.
+
+# Examples
+
+## Example 1
+
+In the following example, the task is to extract entities related to food, with 'apple' and 'lime' as examples:
+
+<input_context>
+Oranges and lemons,
+Say the bells of St. Clement's.
+
+You owe me five farthings,
+Say the bells of St. Martin's.
+</input_context>
+
+Response:
+<entities>
+- Orange
+- Lemon
+</entities>
+
+## Example 2
+
+In the following example, the task was to extract entities related to animals, with 'fish' and 'goat' as examples:
+
+<input_context>
+Belinda lived in a little white house,
+With a little black kitten and a little gray mouse,
+And a little yellow dog and a little red wagon,
+And a realio, trulio, little pet dragon
+</input_context>
+
+Response:
+<entities>
+- kitten
+- mouse
+- dog
+- dragon
+</entities>
+
+# Task
+
+Extract entities related to {{$topic}} from the following context. Produce a bulleted list of entities between <entities> and </entities>.
+
+<input_context>
+{{$input}}
+</input_context>
+
+Response: