Merge branch 'mgx_ops' into add_swe_agent_ablilities_to_engineer2

tests/metagpt/rag/test_large_pdf.py

@@ -0,0 +1,55 @@
+import pytest
+
+from metagpt.config2 import Config
+from metagpt.const import TEST_DATA_PATH
+from metagpt.rag.engines import SimpleEngine
+from metagpt.rag.factories.embedding import RAGEmbeddingFactory
+from metagpt.utils.common import aread
+
+
+@pytest.mark.skip
+@pytest.mark.parametrize(
+    ("knowledge_filename", "query_filename", "answer_filename"),
+    [
+        (
+            TEST_DATA_PATH / "embedding/2.knowledge.md",
+            TEST_DATA_PATH / "embedding/2.query.md",
+            TEST_DATA_PATH / "embedding/2.answer.md",
+        ),
+        (
+            TEST_DATA_PATH / "embedding/3.knowledge.md",
+            TEST_DATA_PATH / "embedding/3.query.md",
+            TEST_DATA_PATH / "embedding/3.answer.md",
+        ),
+    ],
+)
+@pytest.mark.asyncio
+async def test_large_pdf(knowledge_filename, query_filename, answer_filename):
+    Config.default(reload=True)  # `config.embedding.model = "text-embedding-ada-002"` changes the cache.
+
+    engine = SimpleEngine.from_docs(
+        input_files=[knowledge_filename],
+    )
+
+    query = await aread(filename=query_filename)
+    rsp = await engine.aretrieve(query)
+    assert rsp
+
+    config = Config.default()
+    config.embedding.model = "text-embedding-ada-002"
+    factory = RAGEmbeddingFactory(config)
+    embedding = factory.get_rag_embedding()
+    answer = await aread(filename=answer_filename)
+    answer_embedding = await embedding.aget_text_embedding(answer)
+    similarity = 0
+    for i in rsp:
+        rsp_embedding = await embedding.aget_query_embedding(i.text)
+        v = embedding.similarity(answer_embedding, rsp_embedding)
+        similarity = max(similarity, v)
+
+    print(similarity)
+    assert similarity > 0.9
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-s"])

tests/metagpt/tools/libs/test_index_repo.py

@@ -0,0 +1,32 @@
+import shutil
+
+import pytest
+
+from metagpt.const import DEFAULT_WORKSPACE_ROOT, TEST_DATA_PATH
+from metagpt.tools.libs.index_repo import IndexRepo
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(("path", "query"), [(TEST_DATA_PATH / "requirements", "业务线")])
+async def test_index_repo(path, query):
+    index_path = DEFAULT_WORKSPACE_ROOT / ".index"
+    repo = IndexRepo(persist_path=str(index_path), root_path=str(path), min_token_count=0)
+    await repo.add([path])
+    await repo.add([path])
+    assert index_path.exists()
+
+    rsp = await repo.search(query)
+    assert rsp
+
+    repo2 = IndexRepo(persist_path=str(index_path), root_path=str(path), min_token_count=0)
+    rsp2 = await repo2.search(query)
+    assert rsp2
+
+    merged_rsp = await repo.merge(query=query, indices_list=[rsp, rsp2])
+    assert merged_rsp
+
+    shutil.rmtree(index_path)
+
+
+if __name__ == "__main__":
+    pytest.main([__file__, "-s"])