camel-ai 0.2.37__py3-none-any.whl → 0.2.39__py3-none-any.whl

camel/verifiers/python_verifier.py

@@ -76,15 +76,19 @@ class PythonVerifier(BaseVerifier):
 
     async def _setup(self, **kwargs) -> None:
         r"""Set up a virtual environment and install required packages."""
-        uv = kwargs.get('uv', False)
-        if uv or self._is_uv_environment():
+        # Check if we're in a uv environment and use uv if available
+        if kwargs.get("uv", False) or self._is_uv_environment():
             logger.info("[UV] Detected uv environment. Using uv for setup.")
             self._setup_with_uv()
             return
 
         self.venv_path = tempfile.mkdtemp()
         try:
-            venv.create(self.venv_path, with_pip=True)
+            # Use system=True to ensure that the virtual environment uses the
+            # system Python libraries
+            venv.create(
+                self.venv_path, with_pip=True, system_site_packages=True
+            )
             logger.info(f"Virtual environment created at {self.venv_path}")
         except Exception as e:
             logger.error(f"Failed to create virtual environment: {e}")
@@ -138,7 +142,7 @@ class PythonVerifier(BaseVerifier):
         self.venv_path = tempfile.mkdtemp()
         try:
             subprocess.run(
-                ["uv", "venv", self.venv_path],
+                ["uv", "venv", "--python", sys.executable, self.venv_path],
                 check=True,
                 capture_output=True,
                 timeout=self._timeout,
@@ -167,7 +171,11 @@ class PythonVerifier(BaseVerifier):
             raise
 
         if self.required_packages:
-            venv_python = os.path.join(self.venv_path, self.bin_dir, "python")
+            venv_python = os.path.join(
+                self.venv_path,
+                self.bin_dir,
+                "python.exe" if os.name == 'nt' else "python",
+            )
             try:
                 subprocess.run(
                     [
@@ -214,7 +222,7 @@ class PythonVerifier(BaseVerifier):
             self.venv_path = None
 
     async def _verify_implementation(
-        self, solution: str, ground_truth: Optional[str]
+        self, solution: str, reference_answer: Optional[str]
     ) -> VerificationResult:
         r"""Executes the provided Python solution in an isolated environment
         and verifies its output against an expected ground truth expression.
@@ -230,7 +238,7 @@ class PythonVerifier(BaseVerifier):
         Args:
             solution (str): The Python code or expression to execute and
                 verify.
-            ground_truth (Optional[str]): The expected value as a Python
+            reference_answer (Optional[str]): The expected value as a Python
              expression. If None, only execution success is verified.
 
         Returns:
@@ -255,9 +263,9 @@ class PythonVerifier(BaseVerifier):
                     error_message=f"Expression evaluation error: {e}",
                 )
 
-            if ground_truth is not None:
+            if reference_answer is not None:
                 try:
-                    gt_val = ast.literal_eval(ground_truth)
+                    gt_val = ast.literal_eval(reference_answer)
                 except Exception as e:
                     return VerificationResult(
                         status=VerificationOutcome.ERROR,
@@ -284,7 +292,11 @@ class PythonVerifier(BaseVerifier):
 
         # Otherwise, run the code block,
         # which should already include a print(...) in the end
-        venv_python = os.path.join(self.venv_path, self.bin_dir, "python")
+        venv_python = os.path.join(
+            self.venv_path,
+            self.bin_dir,
+            "python.exe" if os.name == 'nt' else "python",
+        )
         if not os.path.exists(venv_python):
             return VerificationResult(
                 status=VerificationOutcome.ERROR,
@@ -303,29 +315,17 @@ class PythonVerifier(BaseVerifier):
                     error_message=f"Solution code error:\n{sol_err}",
                 )
 
-            if ground_truth is not None:
+            if reference_answer is not None:
                 try:
                     # First, try to evaluate the output as-is.
                     sol_val = ast.literal_eval(sol_out)
                 except Exception as e:
-                    logger.warning(
-                        f"Direct eval failed: {e}. Trying repr on output."
-                    )
-                    try:
-                        # Try to convert sol_out to a literal
-                        # by wrapping it with repr.
-                        # FIXME: may be unnecessary
-                        sol_val = ast.literal_eval(repr(sol_out))
-                    except Exception as e2:
-                        logger.warning(
-                            f"repr eval also failed: {e2}."
-                            "Falling back to string comparison."
-                        )
-                        sol_val = None
+                    logger.warning(f"Direct eval failed: {e}.")
+                    sol_val = None
 
                 if sol_val is not None:
                     try:
-                        gt_val = ast.literal_eval(ground_truth)
+                        gt_val = ast.literal_eval(reference_answer)
                     except Exception as e:
                         return VerificationResult(
                             status=VerificationOutcome.ERROR,
@@ -347,7 +347,7 @@ class PythonVerifier(BaseVerifier):
                         )
                 else:
                     # Fallback: string comparison
-                    if sol_out.strip() == ground_truth.strip():
+                    if sol_out.strip() == reference_answer.strip():
                         return VerificationResult(
                             status=VerificationOutcome.SUCCESS,
                             result=sol_out,
@@ -357,7 +357,7 @@ class PythonVerifier(BaseVerifier):
                             status=VerificationOutcome.FAILURE,
                             result=sol_out,
                             error_message="Fallback string mismatch: "
-                            f"'{sol_out}' != '{ground_truth}'",
+                            f"'{sol_out}' != '{reference_answer}'",
                         )
             else:
                 return VerificationResult(

{camel_ai-0.2.37.dist-info → camel_ai-0.2.39.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: camel-ai
-Version: 0.2.37
+Version: 0.2.39
 Summary: Communicative Agents for AI Society Study
 Project-URL: Homepage, https://www.camel-ai.org/
 Project-URL: Repository, https://github.com/camel-ai/camel
@@ -14,11 +14,9 @@ Requires-Dist: colorama<0.5,>=0.4.6
 Requires-Dist: docstring-parser<0.16,>=0.15
 Requires-Dist: httpx<1.0.0dev,>=0.28.0
 Requires-Dist: jsonschema<5,>=4
-Requires-Dist: numpy~=1.26
-Requires-Dist: openai<2,>=1.59.7
+Requires-Dist: openai<2,>=1.68.0
 Requires-Dist: psutil<6,>=5.9.8
 Requires-Dist: pydantic<2.10,>=1.9
-Requires-Dist: pyyaml<7,>=6.0.2
 Requires-Dist: tiktoken<0.8,>=0.7.0
 Provides-Extra: all
 Requires-Dist: accelerate<0.27,>=0.26.0; extra == 'all'
@@ -57,6 +55,7 @@ Requires-Dist: ipykernel<7,>=6.0.0; extra == 'all'
 Requires-Dist: jupyter-client<9,>=8.6.2; extra == 'all'
 Requires-Dist: linkup-sdk<0.3,>=0.2.1; extra == 'all'
 Requires-Dist: litellm<2,>=1.38.1; extra == 'all'
+Requires-Dist: math-verify<0.8,>=0.7.0; extra == 'all'
 Requires-Dist: mcp>=1.3.0; extra == 'all'
 Requires-Dist: mem0ai>=0.1.67; extra == 'all'
 Requires-Dist: mistralai<2,>=1.1.0; extra == 'all'
@@ -67,6 +66,7 @@ Requires-Dist: neo4j<6,>=5.18.0; extra == 'all'
 Requires-Dist: networkx<4,>=3.4.2; extra == 'all'
 Requires-Dist: newspaper3k<0.3,>=0.2.8; extra == 'all'
 Requires-Dist: notion-client<3,>=2.2.1; extra == 'all'
+Requires-Dist: numpy~=1.26; extra == 'all'
 Requires-Dist: openapi-spec-validator<0.8,>=0.7.1; extra == 'all'
 Requires-Dist: opencv-python<5,>=4; extra == 'all'
 Requires-Dist: openpyxl>=3.1.5; extra == 'all'
@@ -87,6 +87,7 @@ Requires-Dist: pytelegrambotapi<5,>=4.18.0; extra == 'all'
 Requires-Dist: pytest-asyncio<0.24,>=0.23.0; extra == 'all'
 Requires-Dist: pytest-cov<5,>=4; extra == 'all'
 Requires-Dist: pytest<8,>=7; extra == 'all'
+Requires-Dist: pytidb-experimental==0.0.1.dev4; extra == 'all'
 Requires-Dist: qdrant-client<2,>=1.9.0; extra == 'all'
 Requires-Dist: rank-bm25<0.3,>=0.2.2; extra == 'all'
 Requires-Dist: redis<6,>=5.0.6; extra == 'all'
@@ -133,7 +134,9 @@ Provides-Extra: data-tools
 Requires-Dist: aiosqlite<0.21,>=0.20.0; extra == 'data-tools'
 Requires-Dist: datacommons-pandas<0.0.4,>=0.0.3; extra == 'data-tools'
 Requires-Dist: datacommons<2,>=1.4.3; extra == 'data-tools'
+Requires-Dist: math-verify<0.8,>=0.7.0; extra == 'data-tools'
 Requires-Dist: networkx<4,>=3.4.2; extra == 'data-tools'
+Requires-Dist: numpy~=1.26; extra == 'data-tools'
 Requires-Dist: pandas<2,>=1.5.3; extra == 'data-tools'
 Requires-Dist: rouge<2,>=1.0.1; extra == 'data-tools'
 Requires-Dist: stripe<12,>=11.3.0; extra == 'data-tools'
@@ -177,6 +180,7 @@ Requires-Dist: beautifulsoup4<5,>=4; extra == 'document-tools'
 Requires-Dist: docx2txt<0.9,>=0.8; extra == 'document-tools'
 Requires-Dist: docx>=0.2.4; extra == 'document-tools'
 Requires-Dist: fpdf>=1.7.2; extra == 'document-tools'
+Requires-Dist: numpy~=1.26; extra == 'document-tools'
 Requires-Dist: openapi-spec-validator<0.8,>=0.7.1; extra == 'document-tools'
 Requires-Dist: openpyxl>=3.1.5; extra == 'document-tools'
 Requires-Dist: pandasai<3,>=2.3.0; extra == 'document-tools'
@@ -208,12 +212,57 @@ Requires-Dist: fish-audio-sdk<2025,>=2024.12.5; extra == 'model-platforms'
 Requires-Dist: litellm<2,>=1.38.1; extra == 'model-platforms'
 Requires-Dist: mistralai<2,>=1.1.0; extra == 'model-platforms'
 Requires-Dist: reka-api<4,>=3.0.8; extra == 'model-platforms'
+Provides-Extra: owl
+Requires-Dist: anthropic<0.50.0,>=0.47.0; extra == 'owl'
+Requires-Dist: beautifulsoup4<5,>=4; extra == 'owl'
+Requires-Dist: chunkr-ai>=0.0.41; extra == 'owl'
+Requires-Dist: datasets<4,>=3; extra == 'owl'
+Requires-Dist: docx2txt<0.9,>=0.8; extra == 'owl'
+Requires-Dist: docx>=0.2.4; extra == 'owl'
+Requires-Dist: duckduckgo-search<7,>=6.3.5; extra == 'owl'
+Requires-Dist: e2b-code-interpreter<2,>=1.0.3; extra == 'owl'
+Requires-Dist: ffmpeg-python<0.3,>=0.2.0; extra == 'owl'
+Requires-Dist: fpdf>=1.7.2; extra == 'owl'
+Requires-Dist: html2text>=2024.2.26; extra == 'owl'
+Requires-Dist: imageio[pyav]<3,>=2.34.2; extra == 'owl'
+Requires-Dist: mcp-server-fetch==2025.1.17; extra == 'owl'
+Requires-Dist: mcp-simple-arxiv==0.2.2; extra == 'owl'
+Requires-Dist: newspaper3k<0.3,>=0.2.8; extra == 'owl'
+Requires-Dist: numpy~=1.26; extra == 'owl'
+Requires-Dist: openapi-spec-validator<0.8,>=0.7.1; extra == 'owl'
+Requires-Dist: opencv-python<5,>=4; extra == 'owl'
+Requires-Dist: openpyxl>=3.1.5; extra == 'owl'
+Requires-Dist: outlines<0.2,>=0.1.7; extra == 'owl'
+Requires-Dist: pandas<2,>=1.5.3; extra == 'owl'
+Requires-Dist: pandasai<3,>=2.3.0; extra == 'owl'
+Requires-Dist: pillow<11.0.0,>=10.1.0; extra == 'owl'
+Requires-Dist: playwright>=1.50.0; extra == 'owl'
+Requires-Dist: prance<24,>=23.6.21.0; extra == 'owl'
+Requires-Dist: pydub<0.26,>=0.25.1; extra == 'owl'
+Requires-Dist: pymupdf<2,>=1.22.5; extra == 'owl'
+Requires-Dist: python-dotenv<2,>=1.0.0; extra == 'owl'
+Requires-Dist: requests-oauthlib<2,>=1.3.1; extra == 'owl'
+Requires-Dist: rouge<2,>=1.0.1; extra == 'owl'
+Requires-Dist: scenedetect>=0.6.5.2; extra == 'owl'
+Requires-Dist: sentencepiece<0.3,>=0.2; extra == 'owl'
+Requires-Dist: soundfile<0.14,>=0.13; extra == 'owl'
+Requires-Dist: tabulate>=0.9.0; extra == 'owl'
+Requires-Dist: transformers<5,>=4; extra == 'owl'
+Requires-Dist: tree-sitter-python<0.24,>=0.23.6; extra == 'owl'
+Requires-Dist: tree-sitter<0.24,>=0.23.2; extra == 'owl'
+Requires-Dist: typer>=0.15.2; extra == 'owl'
+Requires-Dist: unstructured==0.16.20; extra == 'owl'
+Requires-Dist: wikipedia<2,>=1; extra == 'owl'
+Requires-Dist: xls2xlsx>=0.2.0; extra == 'owl'
+Requires-Dist: yt-dlp<2025,>=2024.11.4; extra == 'owl'
 Provides-Extra: rag
 Requires-Dist: cohere<6,>=5.11.0; extra == 'rag'
 Requires-Dist: nebula3-python==3.8.2; extra == 'rag'
 Requires-Dist: neo4j<6,>=5.18.0; extra == 'rag'
+Requires-Dist: numpy~=1.26; extra == 'rag'
 Requires-Dist: pandasai<3,>=2.3.0; extra == 'rag'
 Requires-Dist: pymilvus<3,>=2.4.0; extra == 'rag'
+Requires-Dist: pytidb-experimental==0.0.1.dev4; extra == 'rag'
 Requires-Dist: qdrant-client<2,>=1.9.0; extra == 'rag'
 Requires-Dist: rank-bm25<0.3,>=0.2.2; extra == 'rag'
 Requires-Dist: sentence-transformers<4,>=3.0.1; extra == 'rag'
@@ -230,6 +279,7 @@ Requires-Dist: mem0ai>=0.1.73; extra == 'storage'
 Requires-Dist: nebula3-python==3.8.2; extra == 'storage'
 Requires-Dist: neo4j<6,>=5.18.0; extra == 'storage'
 Requires-Dist: pymilvus<3,>=2.4.0; extra == 'storage'
+Requires-Dist: pytidb-experimental==0.0.1.dev4; extra == 'storage'
 Requires-Dist: qdrant-client<2,>=1.9.0; extra == 'storage'
 Requires-Dist: redis<6,>=5.0.6; extra == 'storage'
 Provides-Extra: test