add Researcher role

tests/metagpt/roles/test_researcher.py

@@ -0,0 +1,32 @@
+from pathlib import Path
+from random import random
+from tempfile import TemporaryDirectory
+
+import pytest
+
+from metagpt.roles import researcher
+
+
+async def mock_llm_ask(self, prompt: str, system_msgs):
+    if "Please provide up to 2 necessary keywords" in prompt:
+        return '["dataiku", "datarobot"]'
+    elif "Provide up to 4 queries related to your research topic" in prompt:
+        return '["Dataiku machine learning platform", "DataRobot AI platform comparison", ' \
+            '"Dataiku vs DataRobot features", "Dataiku and DataRobot use cases"]'
+    elif "sort the remaining search results" in prompt:
+        return '[1,2]'
+    elif "Not relevant." in prompt:
+        return "Not relevant" if random() > 0.5 else prompt[-100:]
+    elif "provide a detailed research report" in prompt:
+        return f"# Research Report\n## Introduction\n{prompt}"
+    return ""
+
+
+@pytest.mark.asyncio
+async def test_researcher(mocker):
+    with TemporaryDirectory() as dirname:
+        topic = "dataiku .vs datarobot"
+        mocker.patch("metagpt.provider.base_gpt_api.BaseGPTAPI.aask", mock_llm_ask)
+        researcher.RESEARCH_PATH = Path(dirname)
+        await researcher.Researcher().run(topic)
+        assert (researcher.RESEARCH_PATH / f"{topic}.md").read_text().startswith("# Research Report")

tests/metagpt/utils/test_text.py

@@ -0,0 +1,77 @@
+import pytest
+
+from metagpt.utils.text import (
+    decode_unicode_escape,
+    generate_prompt_chunk,
+    reduce_message_length,
+    split_paragraph,
+)
+
+
+def _msgs():
+    length = 20
+    while length:
+        yield "Hello," * 1000 * length
+        length -= 1
+
+
+def _paragraphs(n):
+    return " ".join("Hello World." for _ in range(n))
+
+
+@pytest.mark.parametrize(
+    "msgs, model_name, system_text, reserved, expected",
+    [
+        (_msgs(), "gpt-3.5-turbo", "System", 1500, 1),
+        (_msgs(), "gpt-3.5-turbo-16k", "System", 3000, 6),
+        (_msgs(), "gpt-3.5-turbo-16k", "Hello," * 1000, 3000, 5),
+        (_msgs(), "gpt-4", "System", 2000, 3),
+        (_msgs(), "gpt-4", "Hello," * 1000, 2000, 2),
+        (_msgs(), "gpt-4-32k", "System", 4000, 14),
+        (_msgs(), "gpt-4-32k", "Hello," * 2000, 4000, 12),
+    ]
+)
+def test_reduce_message_length(msgs, model_name, system_text, reserved, expected):
+    assert len(reduce_message_length(msgs, model_name, system_text, reserved)) / (len("Hello,")) / 1000 == expected
+
+
+@pytest.mark.parametrize(
+    "text, prompt_template, model_name, system_text, reserved, expected",
+    [
+        (" ".join("Hello World." for _ in range(1000)), "Prompt: {}", "gpt-3.5-turbo", "System", 1500, 2),
+        (" ".join("Hello World." for _ in range(1000)), "Prompt: {}", "gpt-3.5-turbo-16k", "System", 3000, 1),
+        (" ".join("Hello World." for _ in range(4000)), "Prompt: {}", "gpt-4", "System", 2000, 2),
+        (" ".join("Hello World." for _ in range(8000)), "Prompt: {}", "gpt-4-32k", "System", 4000, 1),
+    ]
+)
+def test_generate_prompt_chunk(text, prompt_template, model_name, system_text, reserved, expected):
+    ret = list(generate_prompt_chunk(text, prompt_template, model_name, system_text, reserved))
+    assert len(ret) == expected
+
+
+@pytest.mark.parametrize(
+    "paragraph, sep, count, expected",
+    [
+        (_paragraphs(10), ".", 2, [_paragraphs(5), f" {_paragraphs(5)}"]),
+        (_paragraphs(10), ".", 3, [_paragraphs(4), f" {_paragraphs(3)}", f" {_paragraphs(3)}"]),
+        (f"{_paragraphs(5)}\n{_paragraphs(3)}", "\n.", 2, [f"{_paragraphs(5)}\n", _paragraphs(3)]),
+        ("......", ".", 2, ["...", "..."]),
+        ("......", ".", 3, ["..", "..", ".."]),
+        (".......", ".", 2, ["....", "..."]),
+    ]
+)
+def test_split_paragraph(paragraph, sep, count, expected):
+    ret = split_paragraph(paragraph, sep, count)
+    assert ret == expected
+
+
+@pytest.mark.parametrize(
+    "text, expected",
+    [
+        ("Hello\\nWorld", "Hello\nWorld"),
+        ("Hello\\tWorld", "Hello\tWorld"),
+        ("Hello\\u0020World", "Hello World"),
+    ]
+)
+def test_decode_unicode_escape(text, expected):
+    assert decode_unicode_escape(text) == expected