├── Evaluation ├── postprocess_mbpp.py ├── test_ds1000.py ├── test_humaneval.py └── test_mbpp.py ├── LICENSE ├── README.md ├── Web_demo ├── assets │ ├── assistant.pic.jpg │ └── user.pic.jpg ├── chatbot.py ├── code_interpreter │ ├── AutoCoderInterpreter.py │ ├── BaseCodeInterpreter.py │ └── JupyterClient.py ├── sandbox │ ├── cpp │ │ ├── CMakeLists.txt │ │ ├── Dockerfile.cpp │ │ ├── compile_run.sh │ │ ├── script.cpp │ │ └── test │ ├── fortran │ │ ├── Dockerfile.fortran │ │ ├── compile_run.sh │ │ ├── script.f90 │ │ └── test │ ├── java │ │ ├── Dockerfile.java │ │ ├── compile_run.sh │ │ ├── pom.xml │ │ ├── src │ │ │ └── main │ │ │ │ └── java │ │ │ │ └── script.java │ │ └── target │ │ │ └── maven-status │ │ │ └── maven-compiler-plugin │ │ │ └── compile │ │ │ └── default-compile │ │ │ ├── createdFiles.lst │ │ │ └── inputFiles.lst │ ├── python_0 │ │ ├── Dockerfile.python │ │ └── script.py │ └── rust │ │ ├── Cargo.lock │ │ ├── Cargo.toml │ │ ├── Dockerfile.rust │ │ ├── compile_run.sh │ │ ├── main.rs │ │ └── target │ │ ├── .rustc_info.json │ │ ├── CACHEDIR.TAG │ │ └── release │ │ ├── .cargo-lock │ │ ├── .fingerprint │ │ └── myapp-0a8bfcae0d226a1c │ │ │ ├── bin-test │ │ │ ├── bin-test.json │ │ │ ├── dep-bin-test │ │ │ └── invoked.timestamp │ │ ├── deps │ │ ├── test-0a8bfcae0d226a1c │ │ └── test-0a8bfcae0d226a1c.d │ │ ├── test │ │ └── test.d └── utils │ ├── cleaner.py │ └── const.py └── requirements.txt /Evaluation/postprocess_mbpp.py: -------------------------------------------------------------------------------- 1 | import json 2 | import re 3 | 4 | def read_jsonl(file_path): 5 | with open(file_path, 'r', encoding='utf-8') as file: 6 | lines = [json.loads(line.strip()) for line in file] 7 | return lines 8 | 9 | def write_jsonl(data, file_path): 10 | with open(file_path, 'w', encoding='utf-8') as file: 11 | for entry in data: 12 | file.write(json.dumps(entry) + '\n') 13 | 14 | def extract_code_blocks(solution): 15 | code_blocks = re.findall(r'```python(.*?)```', solution, re.DOTALL) 16 | return code_blocks 17 | 18 | # 主函数 19 | def process_files(file_path1, output_file): 20 | data1 = read_jsonl(file_path1) 21 | 22 | updated_data = [] 23 | 24 | for entry in data1: 25 | new_entry = entry 26 | code_blocks = extract_code_blocks(entry['solution']) 27 | if len(code_blocks) > 0: 28 | cleaned_code = code_blocks[0].strip().strip() 29 | new_entry['solution'] = cleaned_code 30 | updated_data.append(new_entry) 31 | else: 32 | new_entry['solution'] = "" 33 | updated_data.append(new_entry) 34 | write_jsonl(updated_data, output_file) 35 | 36 | file_path1 = '/data2/bil22003/AutoCoder_git/AutoCoder_6.7B_Mbpp+.jsonl' 37 | output_file = '/data2/bil22003/AutoCoder_git/AutoCoder_6.7B_Mbpp+-sanitized.jsonl' 38 | 39 | process_files(file_path1, output_file) 40 | -------------------------------------------------------------------------------- /Evaluation/test_ds1000.py: -------------------------------------------------------------------------------- 1 | import os 2 | import json 3 | from datasets import load_dataset 4 | from transformers import AutoTokenizer, AutoModelForCausalLM 5 | 6 | model_path = "Bin12345/AutoCoder" 7 | tokenizer = AutoTokenizer.from_pretrained(model_path) 8 | model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto") 9 | model_identifier = os.path.basename(model_path) 10 | 11 | ds_1000 = load_dataset("xlangai/DS-1000") 12 | 13 | answers = [] 14 | 15 | for (index, data) in enumerate(ds_1000["test"]): 16 | print(f"Working on {index}\n") 17 | question = data['prompt'].strip() 18 | metadata = data['metadata'] 19 | data_id = index 20 | if "SOLUTION START" in question: 21 | question = question.strip() 22 | else: 23 | question = question.strip() 24 | print(f"Input question:\n{question}\n") 25 | content = f"""Please Help me to finish the following code completion and Place the executable code between 26 | and tags, without any other non-executable things. 27 | {question} 28 | """ 29 | messages=[ 30 | { 'role': 'user', 'content': content} 31 | ] 32 | inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device) 33 | outputs = model.generate(inputs, 34 | max_new_tokens=1024, 35 | do_sample=False, 36 | temperature=0.0, 37 | top_p=1.0, 38 | num_return_sequences=1, 39 | eos_token_id=tokenizer.eos_token_id) 40 | 41 | answer = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True) 42 | print(f"Answer:\n{answer}\n") 43 | json_data = {"id": data_id, 44 | "code": answer, 45 | "metadata": metadata} 46 | 47 | with open(f'{model_identifier}_DS_1000.jsonl', 'a') as f: 48 | json.dump(json_data, f) 49 | f.write('\n') 50 | 51 | print(f"All data has been saved to /{model_identifier}_DS_1000.jsonl") -------------------------------------------------------------------------------- /Evaluation/test_humaneval.py: -------------------------------------------------------------------------------- 1 | import json 2 | from datasets import load_dataset 3 | from transformers import AutoTokenizer, AutoModelForCausalLM 4 | 5 | model_path = "Bin12345/AutoCoder" 6 | tokenizer = AutoTokenizer.from_pretrained(model_path) 7 | model = AutoModelForCausalLM.from_pretrained(model_path, 8 | device_map="auto") 9 | 10 | HumanEval = load_dataset("evalplus/humanevalplus") 11 | 12 | answers = [] 13 | 14 | for (index, data) in enumerate(HumanEval["test"]): 15 | print(f"Working on {index}\n") 16 | print(f"Original question:\n{data['prompt']}\n") 17 | question = data['prompt'].strip() 18 | content = f"""Write a solution to the following problem: 19 | ```python 20 | {question} 21 | ```""" 22 | messages=[ 23 | { 'role': 'user', 'content': content} 24 | ] 25 | inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, 26 | return_tensors="pt").to(model.device) 27 | 28 | outputs = model.generate(inputs, 29 | max_new_tokens=1024, 30 | do_sample=False, 31 | temperature=0.0, 32 | top_p=1.0, 33 | num_return_sequences=1, 34 | eos_token_id=tokenizer.eos_token_id) 35 | 36 | answer = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True) 37 | print(f"Answer:\n{answer}\n") 38 | json_data = {"task_id": f"HumanEval/{index}", 39 | "solution":f"{answer}" } 40 | 41 | # Save results to a JSON file 42 | with open('AutoCoder_HumanEval+.jsonl', 'a') as f: 43 | json.dump(json_data, f) 44 | f.write('\n') 45 | 46 | print("All data has been saved to AutoCoder_HumanEval+.jsonl") 47 | 48 | -------------------------------------------------------------------------------- /Evaluation/test_mbpp.py: -------------------------------------------------------------------------------- 1 | import json 2 | from datasets import load_dataset 3 | from transformers import AutoTokenizer, AutoModelForCausalLM 4 | 5 | model_path = "Bin12345/AutoCoder" 6 | tokenizer = AutoTokenizer.from_pretrained(model_path) 7 | model = AutoModelForCausalLM.from_pretrained(model_path, 8 | device_map="auto") 9 | 10 | mbpp = load_dataset("evalplus/mbppplus") 11 | 12 | answers = [] 13 | 14 | for (index, data) in enumerate(mbpp["test"]): 15 | print(f"Working on {index}\n") 16 | print(f"Original question:\n{data['prompt']}\n") 17 | question = data['prompt'].strip() 18 | data_id = data['task_id'] 19 | assertion = data['test_list'] 20 | content = f"""{question} 21 | Your code should satisfy the following assertion: 22 | ```python 23 | {assertion} 24 | ``` 25 | """ 26 | messages=[ 27 | { 'role': 'user', 'content': content} 28 | ] 29 | inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device) 30 | outputs = model.generate(inputs, 31 | max_new_tokens=1024, 32 | do_sample=False, 33 | temperature=0.0, 34 | top_p=1.0, 35 | num_return_sequences=1, 36 | eos_token_id=tokenizer.eos_token_id) 37 | 38 | answer = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True) 39 | print(f"Answer:\n{answer}\n") 40 | json_data = {"task_id": f"Mbpp/{data_id}", 41 | "solution":f"{answer}" } 42 | 43 | # Save results to a JSON file 44 | with open('AutoCoder_Mbpp+.jsonl', 'a') as f: 45 | json.dump(json_data, f) 46 | f.write('\n') 47 | 48 | print("All data has been saved to AutoCoder_Mbpp+.jsonl") 49 | 50 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [2024] [AutoCoder] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # AutoCoder 2 | 3 | ## News :fire: 4 | 5 | A new model [AutoCoder_QW_7B](https://huggingface.co/Bin12345/AutoCoder_QW_7B) is uploaded. In this model, We fixed the previous problem that the model will only start the code interpreter when you ask it to *verify* its code. 6 | 7 | The base model of AutoCode_QW_7B is [CodeQwen1.5-7b](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat). 8 | 9 | ## Introduction :mega: 10 | We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024). (**90.9% vs 90.2%**). 11 | 12 | Additionally, compared to previous open-source models, AutoCoder offers a new feature: it can **automatically install the required packages** and attempt to run the code until it deems there are no issues, **whenever the user wishes to execute the code**. 13 | 14 | * Difference between the code interpreter of AutoCoder and the GPT-4 Turbo: 15 | 16 | Below are the video demos for the code interpreter comparison between GPT-4 Turbo and AutoCoder: 17 | 18 | GPT-4o can not access the external library. 19 | 20 | [GPT-4o](https://github.com/bin123apple/AutoCoder/assets/99925255/be47b449-4e8a-4b77-981b-ec79b15970cc) 21 | 22 | AutoCoder can automatically install the required packages. This feature expands the scope of code interpreter's application. 23 | 24 | [AutoCoder](https://github.com/bin123apple/AutoCoder/assets/99925255/1893f904-c1f2-4f59-9ec5-45b69efcc26a) 25 | 26 | * Difference between the code interpreter of AutoCoder and the current open-source code interpreter [OpenCodeInterpreter](https://opencodeinterpreter.github.io/): 27 | 28 | The code interpreter of AutoCoder, like GPT-4 Turbo, is only called when the user has a need to verify the code, while OpenCodeInterpreter runs all generated python code. 29 | 30 | ## Model :gift: 31 | The Model is avaliable on Huggingface: 32 | 33 | [AutoCoder (33B)](https://huggingface.co/Bin12345/AutoCoder) 34 | [AutoCoder-S (6.7B)](https://huggingface.co/Bin12345/AutoCoder_S_6.7B) 35 | 36 | The base models of AutoCoder (33B) and AutoCoder-S (6.7B) are deepseeker-coder. 37 | 38 | [AutoCoder_QW_7B](https://huggingface.co/Bin12345/AutoCoder_QW_7B) 39 | 40 | The base model of AutoCoder_QW_7B is CodeQwen1.5-7b. 41 | 42 | ## Quick Start :rocket: 43 | 1. Create the conda env 44 | 45 | ``` 46 | conda create -n AutoCoder python=3.11 47 | conda activate AutoCoder 48 | pip install -r requirements.txt 49 | ``` 50 | 51 | 2. Test on HumanEval **90.9% on base, 78.0% on base + extra**. (Skip to Step 5, if you don't want to test its performance on benchmarks) 52 | 53 | ``` 54 | cd Evaluation 55 | python test_humaneval.py 56 | ``` 57 | You will receive a file named AutoCoder_HumanEval+.jsonl, which follows the EvalPlus format, after this step. 58 | 59 | Then follow the testing framework of the [EvalPlus GitHub](https://github.com/evalplus/evalplus). You will see the results. 60 | 61 | **NOTE**: 62 | * Don't forget to use evalplus's `evalplus.sanitize` to post-process the code. 63 | * If you don't use the greedy method (for example set the `do_sample=True`) for the code generation. You will probably see the different results. 64 | 65 | 3. Test on MBPP **82.5% on base, 70.6% on base + extra**. (Skip to Step 5, if you don't want to test its performance on benchmarks) 66 | 67 | ``` 68 | python test_humaneval.py 69 | ``` 70 | 71 | Post-process to delete the nature language for testing 72 | ``` 73 | python postprocess_mbpp.py 74 | ``` 75 | Your will get a AutoCoder_Mbpp+-sanitized.jsonl file after this step, it extracted all the code blocks. 76 | Then, directly test it by using [EvalPlus GitHub](https://github.com/evalplus/evalplus) (You don't need to use to use evalplus's `evalplus.sanitize` to post-process the code this time). 77 | 78 | 4. Test on DS-1000. (Skip to Step 5, if you don't want to test its performance on benchmarks) 79 | 80 | ``` 81 | python test_ds1000.py 82 | ``` 83 | 84 | Your will get a jsonl file after this step, it extracted all the code blocks. 85 | Then, directly test it by using [DS-1000 GitHub](https://github.com/xlang-ai/DS-1000). 86 | 87 | 5. Web demo (Include code interpreter) 88 | 89 | Install gradio and Run: 90 | 91 | ``` 92 | pip install gradio==3.48.0 93 | cd /Web_demo 94 | python chatbot.py 95 | ``` 96 | 97 | ## **NOTE** :warning: 98 | * We suggest to set `do_sample = True` (default setting here) while using the code interpreter. 99 | 100 | * It would be preferable to use Linux for deploying everything. 101 | 102 | ## Contact :email: 103 | If you have any inquiries, please feel free to raise an issue or reach out to leib2765@gmail.com. 104 | 105 | ## Citation :book: 106 | ``` 107 | @misc{lei2024autocoder, 108 | title={AutoCoder: Enhancing Code Large Language Model with \textsc{AIEV-Instruct}}, 109 | author={Bin Lei and Yuchen Li and Qiuwu Chen}, 110 | year={2024}, 111 | eprint={2405.14906}, 112 | archivePrefix={arXiv}, 113 | primaryClass={cs.SE} 114 | } 115 | ``` 116 | 117 | ## Acknowledgments :pray: 118 | Thanks to Tianyu Zheng, the first author of the [OpenCodeInterpreter](https://opencodeinterpreter.github.io/), for guidance on some technical details. 119 | 120 | -------------------------------------------------------------------------------- /Web_demo/assets/assistant.pic.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/assets/assistant.pic.jpg -------------------------------------------------------------------------------- /Web_demo/assets/user.pic.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/assets/user.pic.jpg -------------------------------------------------------------------------------- /Web_demo/chatbot.py: -------------------------------------------------------------------------------- 1 | import ast 2 | import gradio as gr 3 | import os 4 | import re 5 | import json 6 | import logging 7 | import subprocess 8 | 9 | import torch 10 | import atexit 11 | from datetime import datetime 12 | 13 | from threading import Thread 14 | from typing import Optional 15 | from transformers import TextIteratorStreamer 16 | from functools import partial 17 | from huggingface_hub import CommitScheduler 18 | from uuid import uuid4 19 | from pathlib import Path 20 | 21 | from code_interpreter.JupyterClient import JupyterNotebook 22 | 23 | MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096")) 24 | 25 | import warnings 26 | 27 | warnings.filterwarnings("ignore", category=UserWarning, module="transformers") 28 | os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" 29 | 30 | ''' 31 | This demo code is modified from https://github.com/OpenCodeInterpreter/OpenCodeInterpreter/tree/main/demo. 32 | ''' 33 | 34 | from code_interpreter.AutoCoderInterpreter import AutoCoderInterpreter 35 | 36 | JSON_DATASET_DIR = Path("json_dataset") 37 | JSON_DATASET_DIR.mkdir(parents=True, exist_ok=True) 38 | 39 | scheduler = CommitScheduler( 40 | repo_id="AutoCoder_user_data", 41 | repo_type="dataset", 42 | folder_path=JSON_DATASET_DIR, 43 | path_in_repo="data", 44 | private=True 45 | ) 46 | 47 | logging.basicConfig(level=logging.INFO) 48 | 49 | class StreamingAutoCodeInterpreter(AutoCoderInterpreter): 50 | streamer: Optional[TextIteratorStreamer] = None 51 | 52 | # overwirte generate function 53 | @torch.inference_mode() 54 | def generate( 55 | self, 56 | inputs, 57 | max_new_tokens = 1024, 58 | do_sample: bool = True, 59 | top_p: float = 0.95, 60 | top_k: int = 50, 61 | ) -> str: 62 | 63 | self.streamer = TextIteratorStreamer( 64 | self.tokenizer, skip_prompt=True, Timeout=5 65 | ) 66 | logging.info(f"inputs:\n{inputs}") 67 | inputs = inputs.to(self.model.device) 68 | 69 | kwargs = dict( 70 | input_ids = inputs, 71 | streamer=self.streamer, 72 | max_new_tokens=max_new_tokens, 73 | do_sample=do_sample, 74 | top_k = top_k, 75 | top_p = top_p, 76 | eos_token_id=self.tokenizer.eos_token_id, 77 | pad_token_id=self.tokenizer.eos_token_id, 78 | ) 79 | logging.info(f"kwargs:\n{kwargs}") 80 | 81 | thread = Thread(target=self.model.generate, kwargs=kwargs) 82 | thread.start() 83 | 84 | return "" 85 | 86 | def save_json(dialog, mode, json_file_path, dialog_id) -> None: 87 | with scheduler.lock: 88 | with json_file_path.open("a") as f: 89 | json.dump({"id": dialog_id, "dialog": dialog, "mode": mode, "datetime": datetime.now().isoformat()}, f, ensure_ascii=False) 90 | f.write("\n") 91 | 92 | def convert_history(gradio_history: list[list], interpreter_history: list[dict]): 93 | interpreter_history = [interpreter_history[0]] if interpreter_history and interpreter_history[0]["role"] == "system" else [] 94 | if not gradio_history: 95 | return interpreter_history 96 | for item in gradio_history: 97 | if item[0] is not None: 98 | interpreter_history.append({"role": "user", "content": item[0]}) 99 | if item[1] is not None: 100 | interpreter_history.append({"role": "assistant", "content": item[1]}) 101 | return interpreter_history 102 | 103 | def update_uuid(dialog_info): 104 | new_uuid = str(uuid4()) 105 | logging.info(f"allocating new uuid {new_uuid} for conversation...") 106 | return [new_uuid, dialog_info[1]] 107 | 108 | def is_valid_python_code(code): 109 | try: 110 | ast.parse(code) 111 | return True 112 | except SyntaxError: 113 | return False 114 | 115 | 116 | class InputFunctionVisitor(ast.NodeVisitor): 117 | def __init__(self): 118 | self.found_input = False 119 | 120 | def visit_Call(self, node): 121 | if isinstance(node.func, ast.Name) and node.func.id == 'input': 122 | self.found_input = True 123 | self.generic_visit(node) 124 | 125 | def has_input_function_calls(code): 126 | try: 127 | tree = ast.parse(code) 128 | except SyntaxError: 129 | return False 130 | visitor = InputFunctionVisitor() 131 | visitor.visit(tree) 132 | return visitor.found_input 133 | 134 | def gradio_launch(model_path: str, MAX_TRY: int = 3): 135 | with gr.Blocks() as demo: 136 | chatbot = gr.Chatbot(height=600, label="AutoCoder", avatar_images=["assets/user.pic.jpg", "assets/assistant.pic.jpg"], show_copy_button=True) 137 | with gr.Group(): 138 | with gr.Row(): 139 | msg = gr.Textbox( 140 | container=False, 141 | show_label=False, 142 | label="Message", 143 | placeholder="Type a message...", 144 | scale=7, 145 | autofocus=True 146 | ) 147 | sub = gr.Button( 148 | "Submit", 149 | variant="primary", 150 | scale=1, 151 | min_width=150 152 | ) 153 | # stop = gr.Button( 154 | # "Stop", 155 | # variant="stop", 156 | # visible=False, 157 | # scale=1, 158 | # min_width=150 159 | # ) 160 | 161 | with gr.Row(): 162 | # retry = gr.Button("🔄 Retry", variant="secondary") 163 | # undo = gr.Button("↩️ Undo", variant="secondary") 164 | clear = gr.Button("🗑️ Clear", variant="secondary") 165 | 166 | session_state = gr.State([]) 167 | dialog_info = gr.State(["", 0]) 168 | demo.load(update_uuid, dialog_info, dialog_info) 169 | 170 | def bot(user_message, history, dialog_info, 171 | interpreter, image_name, container_name, 172 | dockerfile_name, sandbox_path, volume_mount): 173 | 174 | ## Initialize everything 175 | 176 | # log user input message 177 | logging.info(f"user message:\n {user_message}") 178 | 179 | # interpreter.dialog is inialize as [] 180 | interpreter.dialog = convert_history(gradio_history=history, interpreter_history=interpreter.dialog) 181 | 182 | # Add user message to the history [user_msg, assistant_msg] 183 | history.append([user_message, None]) 184 | 185 | # Add user message to the dialogue 186 | interpreter.dialog.append({"role": "user", "content": user_message}) 187 | 188 | # Initialize the HAS_CODE = False 189 | HAS_CODE = False 190 | 191 | ## Generate the assistant response 192 | 193 | # Apply chat template 194 | inputs = interpreter.dialog_to_prompt(dialog=interpreter.dialog) 195 | 196 | # Generate the assistant response 197 | _ = interpreter.generate(inputs) 198 | history[-1][1] = "" 199 | generated_text = "" 200 | code_blocks = "" 201 | code_block = "" 202 | for character in interpreter.streamer: 203 | history[-1][1] += character 204 | history[-1][1] = history[-1][1].replace("<|EOT|>","").replace("","").replace("","").replace("<|im_end|>","") 205 | generated_text += character 206 | yield history, history, dialog_info 207 | print("generated_text",generated_text) 208 | 209 | # Add the assistant response to the dialogue 210 | interpreter.dialog.append( 211 | { 212 | "role": "assistant", 213 | "content": generated_text.replace("_", "") 214 | .replace("", "") 215 | .replace("<|EOT|>", "") 216 | .replace("<|im_end|>",""), 217 | } 218 | ) 219 | 220 | HAS_CODE, generated_code_block = interpreter.extract_code_blocks( 221 | generated_text 222 | ) 223 | 224 | logging.info(f"saving current dialog to file {dialog_info[0]}.json...") 225 | logging.info(f"current dialog: {interpreter.dialog}") 226 | save_json(interpreter.dialog, mode="openci_only", json_file_path=JSON_DATASET_DIR/f"{dialog_info[0]}.json", dialog_id=dialog_info[0]) 227 | 228 | # uncomment this line for the no interpreter demo 229 | # HAS_CODE = False 230 | 231 | # Set up docker related path 232 | attempt = 1 233 | 234 | print(f"HAS_Code:{HAS_CODE}") 235 | # Enter into code interpreter and run the code 236 | while HAS_CODE: 237 | if attempt > MAX_TRY: 238 | break 239 | 240 | # if no code then doesn't have to execute it 241 | generated_text = "" # clear generated text 242 | 243 | yield history, history, dialog_info 244 | 245 | # preprocess for the each kinds of generated code 246 | for lang, code in generated_code_block.items(): 247 | processed_code = code.replace("_", "").replace("", "") 248 | generated_code_block[lang] = processed_code 249 | 250 | # exclude languages that do not require code execution 251 | generated_code_block = {lang: code for lang, code in generated_code_block.items() if code.strip()} 252 | print("generated_code_block",generated_code_block) 253 | 254 | # Check if need to install the external library 255 | matches_with_pip = [] 256 | if "sh" in generated_code_block: 257 | matches_with_pip.append(generated_code_block['sh']) 258 | logging.info("We need to install new packages...") 259 | 260 | # create the sandbox enviroment and run each kinds of codes 261 | has_problem, code_blocks_output = interpreter.execute_code_and_return_output(generated_code_block, 262 | matches_with_pip, 263 | image_name, container_name, 264 | dockerfile_name, sandbox_path) 265 | print("code_blocks_output",code_blocks_output) 266 | 267 | # postprocess 268 | result_string = code_blocks_output['python'].rstrip() 269 | print("result_string",result_string) 270 | history.append([result_string, ""]) 271 | 272 | interpreter.dialog.append({"role": "user", "content": result_string}) 273 | 274 | yield history, history, dialog_info 275 | 276 | 277 | ## Generate the assistant response 278 | inputs = interpreter.dialog_to_prompt(dialog=interpreter.dialog) 279 | 280 | logging.info(f"generating answer for dialog {dialog_info[0]}") 281 | _ = interpreter.generate(inputs) 282 | for character in interpreter.streamer: 283 | history[-1][1] += character 284 | history[-1][1] = history[-1][1].replace("<|EOT|>","").replace("","").replace("","").replace("<|im_end|>","") 285 | generated_text += character 286 | yield history, history, dialog_info 287 | logging.info(f"finish generating answer for dialog {dialog_info[0]}") 288 | 289 | interpreter.dialog.append( 290 | { 291 | "role": "assistant", 292 | "content": generated_text.replace("_", "") 293 | .replace("", "") 294 | .replace("<|EOT|>", "") 295 | .replace("<|im_end|>",""), 296 | } 297 | ) 298 | 299 | HAS_CODE, generated_code_block = interpreter.extract_code_blocks( 300 | generated_text 301 | ) 302 | 303 | 304 | # Try more times 305 | attempt += 1 306 | 307 | logging.info(f"saving current dialog to file {dialog_info[0]}.json...") 308 | logging.info(f"current dialog: {interpreter.dialog}") 309 | save_json(interpreter.dialog, mode="openci_only", json_file_path=JSON_DATASET_DIR/f"{dialog_info[0]}.json", dialog_id=dialog_info[0]) 310 | 311 | if generated_text.endswith("<|EOT|>") or generated_text.endswith("<|im_end|>",""): 312 | continue 313 | 314 | return history, history, dialog_info 315 | 316 | 317 | def reset_textbox(): 318 | return gr.update(value="") 319 | 320 | def clean_docker_container(container_name): 321 | try: 322 | subprocess.run(["docker", "rm", "-f", container_name], check=True) 323 | print(f"Container named {container_name} has been removed.") 324 | except subprocess.CalledProcessError as e: 325 | print(f"An error occurred while removing the container {container_name}: {e}") 326 | 327 | def clear_history(history, dialog_info, interpreter, container_name, 328 | image_name, volume_mount): 329 | interpreter.dialog = [] 330 | clean_docker_container(container_name) 331 | 332 | # Keeping the docker backend running 333 | subprocess.run(["docker", "run", "-d", "-v", 334 | volume_mount, "--name", f"{container_name}", 335 | image_name, "tail", "-f", "/dev/null"], check=True) 336 | return [], [], update_uuid(dialog_info) 337 | 338 | def on_exit(): 339 | clean_docker_container(container_name) 340 | 341 | atexit.register(on_exit) 342 | interpreter = StreamingAutoCodeInterpreter(model_path=model_path) 343 | 344 | index = 0 345 | image_name = f"python-sandbox_{index}" 346 | container_name = f"container_python_{index}" 347 | dockerfile_name = "Dockerfile.python" 348 | current_file_path = os.path.abspath(__file__) 349 | current_directory = os.path.dirname(current_file_path) 350 | main_path = os.path.join(current_directory, "sandbox") 351 | sandbox_path = f"{main_path}/python_{index}" 352 | volume_mount = f"{sandbox_path}:/app" 353 | 354 | # Creat docker image 355 | check_command = ["docker", "images", "-q", image_name] 356 | image_exists = subprocess.run(check_command, capture_output=True, text=True).stdout.strip() 357 | if not image_exists: 358 | dockerfile_path = os.path.join(sandbox_path, dockerfile_name) 359 | # lang_sandbox_path = f"{sandbox_path}/{lang}/" 360 | lang_sandbox_path = f"{sandbox_path}" 361 | build_command = ["docker", "build", "-t", image_name, "-f", dockerfile_path, lang_sandbox_path] 362 | build_result = subprocess.run(build_command, capture_output=True, text=True) 363 | if build_result.returncode != 0: 364 | print(f"Failed to build image {image_name}: {build_result.stderr}") 365 | # code_blocks_output[lang] = f"Failed to build image {image_name}: {build_result.stderr}" 366 | 367 | # Keeping the docker backend running 368 | subprocess.run(["docker", "run", "-d", "-v", 369 | volume_mount, "--name", f"{container_name}", 370 | image_name, "tail", "-f", "/dev/null"], check=True) 371 | 372 | sub.click(partial(bot, interpreter=interpreter, image_name = image_name, 373 | container_name = container_name, dockerfile_name = dockerfile_name, 374 | sandbox_path = sandbox_path, volume_mount = volume_mount), 375 | [msg, session_state, dialog_info], 376 | [chatbot, session_state, dialog_info]) 377 | sub.click(reset_textbox, [], [msg]) 378 | 379 | clear.click(partial(clear_history, interpreter=interpreter, container_name = container_name, 380 | image_name = image_name, volume_mount = volume_mount), 381 | [session_state, dialog_info], 382 | [chatbot, session_state, dialog_info], queue=False) 383 | 384 | demo.queue(max_size=20) 385 | demo.launch(share=True, server_port = 8000) 386 | 387 | 388 | if __name__ == "__main__": 389 | import argparse 390 | 391 | parser = argparse.ArgumentParser() 392 | parser.add_argument( 393 | "--path", 394 | type=str, 395 | required=False, 396 | help="Path to the Model.", 397 | default="Bin12345/AutoCoder", 398 | ) 399 | args = parser.parse_args() 400 | 401 | gradio_launch(model_path=args.path) 402 | -------------------------------------------------------------------------------- /Web_demo/code_interpreter/AutoCoderInterpreter.py: -------------------------------------------------------------------------------- 1 | import sys 2 | import os 3 | 4 | prj_root_path = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) 5 | sys.path.append(prj_root_path) 6 | 7 | from code_interpreter.BaseCodeInterpreter import BaseCodeInterpreter 8 | from utils.const import * 9 | 10 | from typing import List, Tuple, Dict 11 | import re 12 | 13 | import torch 14 | from transformers import AutoModelForCausalLM, AutoTokenizer 15 | 16 | 17 | sys.path.append(os.path.dirname(__file__)) 18 | sys.path.append(os.path.dirname(os.path.abspath(__file__))) 19 | 20 | import warnings 21 | 22 | warnings.filterwarnings("ignore", category=UserWarning, module="transformers") 23 | os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" 24 | 25 | 26 | class AutoCoderInterpreter(BaseCodeInterpreter): 27 | def __init__( 28 | self, 29 | model_path: str, 30 | load_in_8bit: bool = False, 31 | load_in_4bit: bool = False, 32 | ): 33 | # build tokenizer 34 | # self.tokenizer = AutoTokenizer.from_pretrained( 35 | # model_path, 36 | # padding_side="right", 37 | # trust_remote_code=True 38 | # ) 39 | self.tokenizer = AutoTokenizer.from_pretrained(model_path, 40 | legacy=False) 41 | 42 | # self.model = AutoModelForCausalLM.from_pretrained( 43 | # model_path, 44 | # device_map="auto", 45 | # load_in_4bit=load_in_4bit, 46 | # load_in_8bit=load_in_8bit, 47 | # torch_dtype=torch.float16, 48 | # trust_remote_code=True 49 | # ) 50 | 51 | # self.model.resize_token_embeddings(len(self.tokenizer)) 52 | 53 | self.model = AutoModelForCausalLM.from_pretrained(model_path,device_map="auto") 54 | 55 | self.model = self.model.eval() 56 | 57 | self.dialog = [] 58 | self.MAX_CODE_OUTPUT_LENGTH = 1000 59 | 60 | 61 | def dialog_to_prompt(self, dialog: List[Dict]) -> str: 62 | inputs = self.tokenizer.apply_chat_template(dialog, return_tensors="pt") 63 | 64 | return inputs 65 | 66 | # def extract_code_blocks(self, prompt: str) -> Tuple[bool, str]: 67 | # pattern = re.escape("```python") + r"(.*?)" + re.escape("```") 68 | # matches = re.findall(pattern, prompt, re.DOTALL) 69 | 70 | # if matches: 71 | # # Return the last matched code block 72 | # return True, matches[-1].strip() 73 | # else: 74 | # return False, "" 75 | 76 | # def extract_code_blocks(self, prompt: str) -> Tuple[str, str, str]: 77 | # has_code = False 78 | # patterns = { 79 | # "python": re.escape("```python") + r"(.*?)" + re.escape("```"), 80 | # "cpp": re.escape("```cpp") + r"(.*?)" + re.escape("```"), 81 | # "fortran": re.escape("```fortran") + r"(.*?)" + re.escape("```"), 82 | # } 83 | # generated_code_block = {"python": "", "cpp": "", "fortran": ""} 84 | 85 | # for lang, pattern in patterns.items(): 86 | # matches = re.findall(pattern, prompt, re.DOTALL) 87 | # if matches: 88 | # generated_code_block[lang] = matches[-1].strip() 89 | # has_code = True 90 | 91 | # return has_code, generated_code_block 92 | 93 | def extract_code_blocks(self, prompt: str) -> Tuple[str, str, str]: 94 | has_code = False 95 | patterns = { 96 | "sh": re.escape("```sh") + r"(.*?)" + re.escape("```"), 97 | "python": re.escape("```python") + r"(.*?)" + re.escape("```"), 98 | } 99 | generated_code_block = {"sh": "","python": ""} 100 | 101 | for lang, pattern in patterns.items(): 102 | matches = re.findall(pattern, prompt, re.DOTALL) 103 | if matches: 104 | generated_code_block[lang] = matches[-1].strip() 105 | has_code = True 106 | 107 | return has_code, generated_code_block 108 | 109 | def clean_code_output(self, output: str) -> str: 110 | if self.MAX_CODE_OUTPUT_LENGTH < len(output): 111 | return ( 112 | output[: self.MAX_CODE_OUTPUT_LENGTH // 5] 113 | + "\n...(truncated due to length)...\n" 114 | + output[-self.MAX_CODE_OUTPUT_LENGTH // 5 :] 115 | ) 116 | 117 | return output 118 | -------------------------------------------------------------------------------- /Web_demo/code_interpreter/BaseCodeInterpreter.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import re 4 | import logging 5 | import subprocess 6 | 7 | prj_root_path = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) 8 | sys.path.append(prj_root_path) 9 | 10 | 11 | from utils.const import * 12 | 13 | class BaseCodeInterpreter: 14 | def __init__(self): 15 | self.dialog = [ 16 | { 17 | "role": "system", 18 | "content": CODE_INTERPRETER_SYSTEM_PROMPT, 19 | }, 20 | ] 21 | 22 | @staticmethod 23 | def extract_code_blocks(text: str): 24 | pattern = r"```(?:python\n)?(.*?)```" # Match optional 'python\n' but don't capture it 25 | code_blocks = re.findall(pattern, text, re.DOTALL) 26 | return [block.strip() for block in code_blocks] 27 | 28 | # def execute_code_and_return_output(self, code_str: str, nb): 29 | # _, _ = nb.add_and_run(GUARD_CODE) 30 | # outputs, error_flag = nb.add_and_run(code_str) 31 | # return outputs, error_flag 32 | 33 | # def execute_code_and_return_output(self, generated_code_block) -> str: 34 | # code_blocks_output= {} 35 | # sandbox_path = "/home/uconn/BinLei/Data_engine/NLP_Task/multi_codes_demo/sandbox" 36 | # file_map = {"python": "script.py", "cpp": "script.cpp", "fortran": "script.f90"} 37 | # image_map = {"python": "python-sandbox", "cpp": "cpp-sandbox", "fortran": "fortran-sandbox"} 38 | # dockerfile_map = {"python": "python/Dockerfile.python", "cpp": "cpp/Dockerfile.cpp", "fortran": "fortran/Dockerfile.fortran"} 39 | # for lang, code in generated_code_block.items(): 40 | 41 | # file_name = file_map[lang] 42 | # image_name = image_map[lang] 43 | 44 | # print(f"Writing the script for {lang}...") 45 | # file_path = f"{sandbox_path}/{lang}/{file_name}" 46 | # with open(file_path, 'w') as file: 47 | # file.write(code) 48 | 49 | # # check and build the image 50 | # print(f"Checking if the image for {lang}... exist") 51 | # image_name = image_map[lang] 52 | # check_command = ["docker", "images", "-q", image_name] 53 | # image_exists = subprocess.run(check_command, capture_output=True, text=True).stdout.strip() 54 | 55 | # if not image_exists: 56 | # print(f"Creating the image for {lang}...") 57 | # dockerfile_path = os.path.join(sandbox_path, dockerfile_map[lang]) 58 | # lang_sandbox_path = f"{sandbox_path}/{lang}/" 59 | # build_command = ["docker", "build", "-t", image_name, "-f", dockerfile_path, lang_sandbox_path] 60 | # build_result = subprocess.run(build_command, capture_output=True, text=True) 61 | # if build_result.returncode != 0: 62 | # print(f"Failed to build image {image_name}: {build_result.stderr}") 63 | # code_blocks_output[lang] = f"Failed to build image {image_name}: {build_result.stderr}" 64 | # continue 65 | 66 | 67 | # print(f"Running the script for {lang} in the sandbox...") 68 | # script_path = f"{sandbox_path}/{lang}/compile_run.sh" 69 | # chmod_command = ["chmod", "+x", script_path] 70 | # chmod_result = subprocess.run(chmod_command, capture_output=True, text=True) 71 | # volume_mount = f"{sandbox_path}/{lang}:/app" 72 | # command = ["docker", "run", "--rm", "-v", volume_mount, image_name] 73 | # # command = ["docker", "run", "--rm", image_name] 74 | # result = subprocess.run(command, capture_output=True, text=True) 75 | 76 | # if result.returncode == 0: 77 | # code_blocks_output[lang] = result.stdout 78 | # else: 79 | # code_blocks_output[lang] = result.stderr 80 | # return code_blocks_output 81 | 82 | def execute_code_and_return_output(self, generated_code_block,matches_with_pip, 83 | image_name, container_name, 84 | dockerfile_name, sandbox_path) -> str: 85 | 86 | # Initialize the file/image/dockerfile information for each langauges 87 | code_blocks_output= {} 88 | # sandbox_path = "/home/uconn/BinLei/Data_engine/NLP_Task/multi_codes_demo/sandbox" 89 | file_map = {"python": "script.py", 90 | "cpp": "script.cpp", 91 | "fortran": "script.f90"} 92 | # image_map = {"python": "python-sandbox", 93 | # "cpp": "cpp-sandbox", 94 | # "fortran": "fortran-sandbox"} 95 | # dockerfile_map = {"python": "python/Dockerfile.python", 96 | # "cpp": "cpp/Dockerfile.cpp", 97 | # "fortran": "fortran/Dockerfile.fortran"} 98 | image_map = {"python": f"{image_name}", 99 | "cpp": "cpp-sandbox", 100 | "fortran": "fortran-sandbox"} 101 | dockerfile_map = {"python": f"{dockerfile_name}", 102 | "cpp": "cpp/Dockerfile.cpp", 103 | "fortran": "fortran/Dockerfile.fortran"} 104 | has_problem = True 105 | for lang, code in generated_code_block.items(): 106 | if lang == "sh": 107 | lang = "python" 108 | # write the script into the corresponsing file 109 | file_name = file_map[lang] 110 | image_name = image_map[lang] 111 | # file_path = f"{sandbox_path}/{lang}/{file_name}" 112 | file_path = f"{sandbox_path}/{file_name}" 113 | with open(file_path, 'w') as file: 114 | file.write(code) 115 | 116 | # check and build the image 117 | image_name = image_map[lang] 118 | check_command = ["docker", "images", "-q", image_name] 119 | image_exists = subprocess.run(check_command, capture_output=True, text=True).stdout.strip() 120 | 121 | if not image_exists: 122 | dockerfile_path = os.path.join(sandbox_path, dockerfile_map[lang]) 123 | # lang_sandbox_path = f"{sandbox_path}/{lang}/" 124 | lang_sandbox_path = f"{sandbox_path}" 125 | build_command = ["docker", "build", "-t", image_name, "-f", dockerfile_path, lang_sandbox_path] 126 | build_result = subprocess.run(build_command, capture_output=True, text=True) 127 | if build_result.returncode != 0: 128 | print(f"Failed to build image {image_name}: {build_result.stderr}") 129 | code_blocks_output[lang] = f"Failed to build image {image_name}: {build_result.stderr}" 130 | continue 131 | 132 | # give docker the access to run the comile_run file 133 | # script_path = f"{sandbox_path}/{lang}/compile_run.sh" 134 | script_path = f"{sandbox_path}/compile_run.sh" 135 | chmod_command = ["chmod", "+x", script_path] 136 | chmod_result = subprocess.run(chmod_command, capture_output=True, text=True) 137 | # volume_mount = f"{sandbox_path}/{lang}:/app" 138 | volume_mount = f"{sandbox_path}:/app" 139 | 140 | # install external library for python if there are related commonds 141 | pip_command = None 142 | print("matches_with_pip",matches_with_pip) 143 | if lang == "python" and matches_with_pip: 144 | pip_commands = [] 145 | for match in matches_with_pip: 146 | pattern = r'^pip install.*' 147 | matches_pip = re.findall(pattern, match, re.MULTILINE) 148 | print("matches_pip", matches_pip) 149 | for match_pip in matches_pip: 150 | if match_pip: 151 | pip_commands.append(match_pip.replace('\n', ' ').strip()) 152 | print(f"pip_command:{pip_command}") 153 | pip_command = " && ".join(pip_commands) 154 | print(f"pip_command:{pip_command}") 155 | if pip_command: 156 | # command = ["docker", "exec", "container_python", "sh", "-c", f"{pip_command}"] 157 | command = ["docker", "exec", f"{container_name}", "sh", "-c", f"{pip_command}"] 158 | # print(f"command:{command}") 159 | try: 160 | logging.info("Start to install related packages...") 161 | pip_result = subprocess.run(command, check=True, 162 | stdout=subprocess.PIPE, 163 | stderr=subprocess.PIPE, 164 | text=True) 165 | except subprocess.CalledProcessError as e: 166 | pip_result = e 167 | # command = ["docker", "exec", "container_python", "python", "/app/script.py"] 168 | command = ["docker", "exec", f"{container_name}", "python", "/app/script.py"] 169 | 170 | # if there is no external library for python, execute the code directly 171 | else: 172 | # command = ["docker", "exec", "container_python", "python", "/app/script.py"] 173 | command = ["docker", "exec", f"{container_name}", "python", "/app/script.py"] 174 | # result = subprocess.run(command, capture_output=True, text=True) 175 | try: 176 | logging.info("Start to run the code...") 177 | result = subprocess.run(command, capture_output=True, text=True, timeout=30) 178 | except subprocess.TimeoutExpired: 179 | code_blocks_output[lang] = "Command execution timed out. This is probably because the function needs to run continuously." 180 | continue 181 | # record all the information into the code_blocks_output 182 | if result.stdout == "": 183 | result.stdout = "None" 184 | if result.stderr == "": 185 | has_problem = False 186 | result.stderr = "None" 187 | if pip_command: 188 | code_blocks_output[lang] = f"pip_result.stdout: \n{pip_result.stdout}\n pip_result.stderr: \n{pip_result.stderr}\n result.stdout:\n{result.stdout}\nresult.stderr:\n{result.stderr}" 189 | else: 190 | code_blocks_output[lang] = f"result.stdout:\n{result.stdout}\nresult.stderr:\n{result.stderr}" 191 | return has_problem, code_blocks_output -------------------------------------------------------------------------------- /Web_demo/code_interpreter/JupyterClient.py: -------------------------------------------------------------------------------- 1 | from jupyter_client import KernelManager 2 | import threading 3 | import re 4 | from utils.const import * 5 | 6 | 7 | class JupyterNotebook: 8 | def __init__(self): 9 | self.km = KernelManager() 10 | self.km.start_kernel() 11 | self.kc = self.km.client() 12 | _ = self.add_and_run(TOOLS_CODE) 13 | 14 | def clean_output(self, outputs): 15 | outputs_only_str = list() 16 | for i in outputs: 17 | if type(i) == dict: 18 | if "text/plain" in list(i.keys()): 19 | outputs_only_str.append(i["text/plain"]) 20 | elif type(i) == str: 21 | outputs_only_str.append(i) 22 | elif type(i) == list: 23 | error_msg = "\n".join(i) 24 | error_msg = re.sub(r"\x1b\[.*?m", "", error_msg) 25 | outputs_only_str.append(error_msg) 26 | 27 | return "\n".join(outputs_only_str).strip() 28 | 29 | def add_and_run(self, code_string): 30 | # This inner function will be executed in a separate thread 31 | def run_code_in_thread(): 32 | nonlocal outputs, error_flag 33 | 34 | # Execute the code and get the execution count 35 | msg_id = self.kc.execute(code_string) 36 | 37 | while True: 38 | try: 39 | msg = self.kc.get_iopub_msg(timeout=20) 40 | 41 | msg_type = msg["header"]["msg_type"] 42 | content = msg["content"] 43 | 44 | if msg_type == "execute_result": 45 | outputs.append(content["data"]) 46 | elif msg_type == "stream": 47 | outputs.append(content["text"]) 48 | elif msg_type == "error": 49 | error_flag = True 50 | outputs.append(content["traceback"]) 51 | 52 | # If the execution state of the kernel is idle, it means the cell finished executing 53 | if msg_type == "status" and content["execution_state"] == "idle": 54 | break 55 | except: 56 | break 57 | 58 | outputs = [] 59 | error_flag = False 60 | 61 | # Start the thread to run the code 62 | thread = threading.Thread(target=run_code_in_thread) 63 | thread.start() 64 | 65 | # Wait for 20 seconds for the thread to finish 66 | thread.join(timeout=20) 67 | 68 | # If the thread is still alive after 20 seconds, it's a timeout 69 | if thread.is_alive(): 70 | outputs = ["Execution timed out."] 71 | # outputs = ["Error"] 72 | error_flag = "Timeout" 73 | 74 | return self.clean_output(outputs), error_flag 75 | 76 | def close(self): 77 | """Shutdown the kernel.""" 78 | self.km.shutdown_kernel() 79 | 80 | def __deepcopy__(self, memo): 81 | if id(self) in memo: 82 | return memo[id(self)] 83 | new_copy = type(self)() 84 | memo[id(self)] = new_copy 85 | return new_copy 86 | -------------------------------------------------------------------------------- /Web_demo/sandbox/cpp/CMakeLists.txt: -------------------------------------------------------------------------------- 1 | cmake_minimum_required(VERSION 3.14) 2 | project(ScriptTest) 3 | 4 | set(CMAKE_CXX_STANDARD 11) 5 | 6 | include(FetchContent) 7 | FetchContent_Declare( 8 | googletest 9 | URL https://github.com/google/googletest/archive/release-1.10.0.tar.gz 10 | ) 11 | include(GoogleTest) 12 | FetchContent_MakeAvailable(googletest) 13 | 14 | add_executable(script_test script.cpp) 15 | target_link_libraries(script_test gtest_main) 16 | 17 | enable_testing() 18 | include(GoogleTest) 19 | gtest_discover_tests(script_test) 20 | -------------------------------------------------------------------------------- /Web_demo/sandbox/cpp/Dockerfile.cpp: -------------------------------------------------------------------------------- 1 | # 使用最新的Ubuntu镜像作为基础镜像 2 | FROM ubuntu:latest 3 | 4 | # 设置非交互模式，防止apt-get等命令在安装过程中等待用户输入 5 | ENV DEBIAN_FRONTEND=noninteractive 6 | 7 | # 更新软件包列表，并安装必要的软件包 8 | RUN apt-get update && \ 9 | apt-get install -y cmake git build-essential libomp-dev 10 | 11 | # 克隆Google Test的源码，编译并安装 12 | RUN git clone https://github.com/google/googletest.git /googletest && \ 13 | cd /googletest && \ 14 | cmake . && \ 15 | make && \ 16 | make install 17 | 18 | # 设置工作目录为/project 19 | WORKDIR /app 20 | 21 | # 复制当前目录下的所有文件到容器的/project目录中 22 | COPY . /app/ 23 | 24 | # 编译C++程序，这里假设主要的C++文件名为script.cpp，并且生成的可执行文件名为test 25 | # 注意：-L/usr/local/lib选项指定了库文件的搜索路径，这在某些情况下可能是必要的 26 | # RUN g++ -fopenmp script.cpp -L/usr/local/lib -lgtest -lgtest_main -pthread -o test 27 | 28 | # 容器启动时默认执行的命令 29 | # CMD ["./test"] 30 | CMD ["/app/compile_run.sh"] 31 | 32 | -------------------------------------------------------------------------------- /Web_demo/sandbox/cpp/compile_run.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | set -e 4 | 5 | # echo "Starting compilation and execution..." 6 | 7 | # compile 8 | g++ -fopenmp /app/script.cpp -L/usr/local/lib -lgtest -lgtest_main -pthread -o /app/test 9 | 10 | # run 11 | /app/test --gtest_print_time=0 --gtest_brief=1 12 | 13 | # echo "Execution completed." 14 | 15 | # exit_code=$? 16 | # exit $exit_code -------------------------------------------------------------------------------- /Web_demo/sandbox/cpp/script.cpp: -------------------------------------------------------------------------------- 1 | #include 2 | #include 3 | #include 4 | 5 | using namespace std; 6 | 7 | vector convolution(vector a, vector b) { 8 | int n = a.size(); 9 | vector c(2 * n - 1, 0); 10 | for(int i = 0; i < 2 * n - 1; ++i) { 11 | for(int j = max(0, i - n + 1); j <= min(i, n - 1); ++j) { 12 | c[i] += a[j] * b[i - j]; 13 | } 14 | } 15 | return c; 16 | } 17 | 18 | void test_convolution() { 19 | // Test case 1 20 | { 21 | vector a = {1, 2, 3}; 22 | vector b = {4, 5, 6}; 23 | vector expected = {4, 13, 28, 27, 18}; 24 | assert(convolution(a, b) == expected); 25 | } 26 | 27 | // Test case 2: Negative values 28 | { 29 | vector a = {-1, -2, -3}; 30 | vector b = {1, 2, 3}; 31 | vector expected = {-1, -4, -10, -8, -9}; 32 | assert(convolution(a, b) == expected); 33 | } 34 | 35 | // Test case 3: Zeroes 36 | { 37 | vector a = {0, 0, 0}; 38 | vector b = {1, 2, 3}; 39 | vector expected = {0, 0, 0, 0, 0}; 40 | assert(convolution(a, b) == expected); 41 | } 42 | 43 | // Test case 4: Single element arrays 44 | { 45 | vector a = {5}; 46 | vector b = {10}; 47 | vector expected = {50}; 48 | assert(convolution(a, b) == expected); 49 | } 50 | 51 | // Test case 5: Different positive values 52 | { 53 | vector a = {2, 4, 6}; 54 | vector b = {1, 3, 5}; 55 | vector expected = {2, 10, 28, 32, 30}; 56 | assert(convolution(a, b) == expected); 57 | } 58 | 59 | // Test case 6: Larger arrays 60 | { 61 | vector a = {1, 3, 5, 7}; 62 | vector b = {2, 4, 6, 8}; 63 | vector expected = {2, 10, 28, 52, 60, 58, 56}; 64 | assert(convolution(a, b) == expected); 65 | } 66 | 67 | // Test case 7: Arrays with a negative and positive mix 68 | { 69 | vector a = {-1, 2, -3, 4}; 70 | vector b = {5, -6, 7, -8}; 71 | vector expected = {-5, 16, -31, 58, -67, 52, -32}; 72 | assert(convolution(a, b) == expected); 73 | } 74 | 75 | cout << "All test cases passed!" << endl; 76 | } 77 | 78 | int main() { 79 | test_convolution(); 80 | return 0; 81 | } -------------------------------------------------------------------------------- /Web_demo/sandbox/cpp/test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/sandbox/cpp/test -------------------------------------------------------------------------------- /Web_demo/sandbox/fortran/Dockerfile.fortran: -------------------------------------------------------------------------------- 1 | FROM ubuntu:latest 2 | 3 | RUN apt-get update && apt-get install -y gfortran libgomp1 4 | 5 | WORKDIR /app 6 | 7 | COPY . /app 8 | 9 | CMD ["/app/compile_run.sh"] 10 | -------------------------------------------------------------------------------- /Web_demo/sandbox/fortran/compile_run.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | # compile 3 | gfortran -fopenmp -J /app/ -o /app/test /app/script.f90 4 | # run 5 | /app/test 6 | -------------------------------------------------------------------------------- /Web_demo/sandbox/fortran/script.f90: -------------------------------------------------------------------------------- 1 | program hello 2 | print *, 'Updated Hello from Fortran' 3 | end program hello -------------------------------------------------------------------------------- /Web_demo/sandbox/fortran/test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/sandbox/fortran/test -------------------------------------------------------------------------------- /Web_demo/sandbox/java/Dockerfile.java: -------------------------------------------------------------------------------- 1 | # 使用官方 Java 11 JDK 镜像作为基础镜像 2 | FROM openjdk:11-jdk 3 | 4 | # 设置非交互模式，防止 apt-get 等命令在安装过程中等待用户输入 5 | ENV DEBIAN_FRONTEND=noninteractive 6 | 7 | # 安装必要的工具，比如构建和调试工具 8 | RUN apt-get update && \ 9 | apt-get install -y --no-install-recommends \ 10 | git \ 11 | maven \ 12 | && rm -rf /var/lib/apt/lists/* 13 | 14 | WORKDIR /app 15 | 16 | COPY . /app 17 | 18 | CMD ["/app/compile_run.sh"] 19 | -------------------------------------------------------------------------------- /Web_demo/sandbox/java/compile_run.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | set -e 4 | 5 | cd /app 6 | 7 | mkdir -p src/main/java 8 | 9 | mv script.java src/main/java/ 10 | 11 | mvn clean package 12 | 13 | java -jar target/test-1.0-SNAPSHOT.jar 14 | -------------------------------------------------------------------------------- /Web_demo/sandbox/java/pom.xml: -------------------------------------------------------------------------------- 1 | 4 | 4.0.0 5 | 6 | com.example 7 | test 8 | 1.0-SNAPSHOT 9 | 10 | 11 | 12 | org.eclipse.paho 13 | org.eclipse.paho.client.mqttv3 14 | 1.2.5 15 | 16 | 17 | 18 | -------------------------------------------------------------------------------- /Web_demo/sandbox/java/src/main/java/script.java: -------------------------------------------------------------------------------- 1 | import org.eclipse.paho.client.mqttv3.*; 2 | import org.eclipse.paho.client.mqttv3.persist.MemoryPersistence; 3 | 4 | // 移除了 public 修饰符，使得 MqttSubscriber 类变成包级私有 5 | class MqttSubscriber { 6 | 7 | private MqttClient client; 8 | private MqttConnectOptions options = new MqttConnectOptions(); 9 | 10 | public void connectAndSubscribe(String brokerUrl, String clientId, String topic, int qos) throws MqttException { 11 | String serverURI = "tcp://" + brokerUrl; 12 | client = new MqttClient(serverURI, clientId, new MemoryPersistence()); 13 | options.setCleanSession(true); // 假设你想要一个干净的会话 14 | client.connect(options); 15 | client.subscribe(topic, qos, this::messageArrived); 16 | } 17 | 18 | public void disconnect() throws MqttException { 19 | if (client != null && client.isConnected()) { 20 | client.disconnect(); 21 | } 22 | } 23 | 24 | private void messageArrived(String topic, MqttMessage message) { 25 | System.out.println("Received message: " + new String(message.getPayload()) + " on topic: " + topic); 26 | } 27 | } 28 | 29 | // 创建一个新的类，用于启动和运行 MqttSubscriber 30 | class ScriptMain { 31 | public static void main(String[] args) { 32 | MqttSubscriber subscriber = new MqttSubscriber(); 33 | // 填入你的 MQTT 服务器 URL、客户端 ID、主题和 QoS 34 | String brokerUrl = "your_broker_url"; 35 | String clientId = "your_client_id"; 36 | String topic = "your_topic"; 37 | int qos = 1; // Quality of Service Level 38 | try { 39 | subscriber.connectAndSubscribe(brokerUrl, clientId, topic, qos); 40 | // 假设你想要在接收到消息后立即断开连接，或者在这里添加逻辑等待消息 41 | subscriber.disconnect(); 42 | } catch (MqttException e) { 43 | e.printStackTrace(); 44 | } 45 | } 46 | } -------------------------------------------------------------------------------- /Web_demo/sandbox/java/target/maven-status/maven-compiler-plugin/compile/default-compile/createdFiles.lst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/sandbox/java/target/maven-status/maven-compiler-plugin/compile/default-compile/createdFiles.lst -------------------------------------------------------------------------------- /Web_demo/sandbox/java/target/maven-status/maven-compiler-plugin/compile/default-compile/inputFiles.lst: -------------------------------------------------------------------------------- 1 | /app/src/main/java/script.java 2 | -------------------------------------------------------------------------------- /Web_demo/sandbox/python_0/Dockerfile.python: -------------------------------------------------------------------------------- 1 | FROM python:latest 2 | WORKDIR /app 3 | COPY . /app 4 | 5 | # CMD ["python", "script.py"] 6 | -------------------------------------------------------------------------------- /Web_demo/sandbox/python_0/script.py: -------------------------------------------------------------------------------- 1 | def sum_numbers(n): 2 | total = 0 3 | for i in range(n + 1): 4 | total += i 5 | return total 6 | 7 | def main(): 8 | n = 10 # Predefined value for n 9 | result = sum_numbers(n) 10 | print(f"The sum of numbers from 1 to {n} is: {result}") 11 | 12 | if __name__ == "__main__": 13 | main() -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/Cargo.lock: -------------------------------------------------------------------------------- 1 | # This file is automatically @generated by Cargo. 2 | # It is not intended for manual editing. 3 | version = 3 4 | 5 | [[package]] 6 | name = "myapp" 7 | version = "0.1.0" 8 | -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/Cargo.toml: -------------------------------------------------------------------------------- 1 | [package] 2 | name = "myapp" 3 | version = "0.1.0" 4 | edition = "2018" 5 | 6 | [[bin]] 7 | name = "test" 8 | path = "main.rs" 9 | -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/Dockerfile.rust: -------------------------------------------------------------------------------- 1 | # 使用最新的Ubuntu镜像作为基础镜像 2 | FROM ubuntu:latest 3 | 4 | # 设置非交互模式，防止apt-get等命令在安装过程中等待用户输入 5 | ENV DEBIAN_FRONTEND=noninteractive 6 | 7 | # 更新软件包列表 8 | RUN apt-get update 9 | 10 | # 安装curl工具，用于下载Rust安装脚本，以及安装 build-essential 包 11 | RUN apt-get install -y curl build-essential 12 | 13 | # 使用Rust官方安装脚本安装Rust，安装后清理不必要的文件 14 | RUN curl --proto '=https' --tlsv1.2 https://sh.rustup.rs -sSf | sh -s -- -y && \ 15 | rm -rf /var/lib/apt/lists/* 16 | 17 | # 将Rust的cargo工具的二进制目录添加到PATH环境变量中，以便可以直接使用cargo命令 18 | ENV PATH="/root/.cargo/bin:${PATH}" 19 | 20 | # 设置工作目录为/app 21 | WORKDIR /app 22 | 23 | # 复制当前目录下的所有文件到容器的/app目录中 24 | COPY . /app/ 25 | 26 | CMD ["/app/compile_run.sh"] 27 | -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/compile_run.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | set -e 4 | 5 | mv /app/script.rs /app/main.rs 6 | 7 | # 创建 Cargo.toml 文件 8 | echo '[package] 9 | name = "myapp" 10 | version = "0.1.0" 11 | edition = "2018" 12 | 13 | [[bin]] 14 | name = "test" 15 | path = "main.rs"' > /app/Cargo.toml 16 | 17 | cd /app 18 | 19 | cargo build --release 20 | 21 | ./target/release/test 22 | 23 | -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/main.rs: -------------------------------------------------------------------------------- 1 | // 定义 input_handler 模块 2 | mod input_handler { 3 | pub struct InputHandler {} 4 | 5 | impl InputHandler { 6 | pub fn new() -> Self { 7 | Self {} 8 | } 9 | 10 | pub fn handle_input(&self) { 11 | println!("Handling general input..."); 12 | } 13 | } 14 | } 15 | 16 | // 定义 keyboard 模块 17 | mod keyboard { 18 | pub struct Keyboard {} 19 | 20 | impl Keyboard { 21 | pub fn new() -> Self { 22 | Self {} 23 | } 24 | 25 | pub fn handle_key_press(&self) { 26 | println!("Handling keyboard input..."); 27 | } 28 | } 29 | } 30 | 31 | // 定义 mouse 模块 32 | mod mouse { 33 | pub struct Mouse {} 34 | 35 | impl Mouse { 36 | pub fn new() -> Self { 37 | Self {} 38 | } 39 | 40 | pub fn handle_mouse_move(&self) { 41 | println!("Handling mouse movement..."); 42 | } 43 | } 44 | } 45 | 46 | // 定义 gamepad 模块 47 | mod gamepad { 48 | pub struct Gamepad {} 49 | 50 | impl Gamepad { 51 | pub fn new() -> Self { 52 | Self {} 53 | } 54 | 55 | pub fn handle_button_press(&self) { 56 | println!("Handling gamepad button press..."); 57 | } 58 | } 59 | } 60 | 61 | // 定义 input 模块，将其他模块重新导出 62 | mod input { 63 | pub use crate::input_handler::InputHandler; 64 | pub use crate::keyboard::Keyboard; 65 | pub use crate::mouse::Mouse; 66 | pub use crate::gamepad::Gamepad; 67 | } 68 | 69 | fn main() { 70 | // 实例化每个结构体 71 | let handler = input::InputHandler::new(); 72 | let keyboard = input::Keyboard::new(); 73 | let mouse = input::Mouse::new(); 74 | let gamepad = input::Gamepad::new(); 75 | 76 | // 调用每个实例的方法 77 | handler.handle_input(); 78 | keyboard.handle_key_press(); 79 | mouse.handle_mouse_move(); 80 | gamepad.handle_button_press(); 81 | 82 | println!("All inputs handled."); 83 | } -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/.rustc_info.json: -------------------------------------------------------------------------------- 1 | {"rustc_fingerprint":5138894494729493183,"outputs":{"4614504638168534921":{"success":true,"status":"","code":0,"stdout":"rustc 1.77.1 (7cf61ebde 2024-03-27)\nbinary: rustc\ncommit-hash: 7cf61ebde7b22796c69757901dd346d0fe70bd97\ncommit-date: 2024-03-27\nhost: x86_64-unknown-linux-gnu\nrelease: 1.77.1\nLLVM version: 17.0.6\n","stderr":""},"15729799797837862367":{"success":true,"status":"","code":0,"stdout":"___\nlib___.rlib\nlib___.so\nlib___.so\nlib___.a\nlib___.so\n/root/.rustup/toolchains/stable-x86_64-unknown-linux-gnu\noff\npacked\nunpacked\n___\ndebug_assertions\npanic=\"unwind\"\nproc_macro\ntarget_arch=\"x86_64\"\ntarget_endian=\"little\"\ntarget_env=\"gnu\"\ntarget_family=\"unix\"\ntarget_feature=\"fxsr\"\ntarget_feature=\"sse\"\ntarget_feature=\"sse2\"\ntarget_has_atomic=\"16\"\ntarget_has_atomic=\"32\"\ntarget_has_atomic=\"64\"\ntarget_has_atomic=\"8\"\ntarget_has_atomic=\"ptr\"\ntarget_os=\"linux\"\ntarget_pointer_width=\"64\"\ntarget_vendor=\"unknown\"\nunix\n","stderr":""}},"successes":{}} -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/CACHEDIR.TAG: -------------------------------------------------------------------------------- 1 | Signature: 8a477f597d28d172789f06886806bc55 2 | # This file is a cache directory tag created by cargo. 3 | # For information about cache directory tags see https://bford.info/cachedir/ 4 | -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/.cargo-lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/sandbox/rust/target/release/.cargo-lock -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/.fingerprint/myapp-0a8bfcae0d226a1c/bin-test: -------------------------------------------------------------------------------- 1 | 205748b9c486ad59 -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/.fingerprint/myapp-0a8bfcae0d226a1c/bin-test.json: -------------------------------------------------------------------------------- 1 | {"rustc":16286356497298320803,"features":"[]","declared_features":"","target":10996953811719133845,"profile":18277820415669657429,"path":12539050212544219519,"deps":[],"local":[{"CheckDepInfo":{"dep_info":"release/.fingerprint/myapp-0a8bfcae0d226a1c/dep-bin-test"}}],"rustflags":[],"metadata":7797948686568424061,"config":2202906307356721367,"compile_kind":0} -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/.fingerprint/myapp-0a8bfcae0d226a1c/dep-bin-test: -------------------------------------------------------------------------------- 1 | main.rs -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/.fingerprint/myapp-0a8bfcae0d226a1c/invoked.timestamp: -------------------------------------------------------------------------------- 1 | This file has an mtime of when this was started. -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/deps/test-0a8bfcae0d226a1c: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/sandbox/rust/target/release/deps/test-0a8bfcae0d226a1c -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/deps/test-0a8bfcae0d226a1c.d: -------------------------------------------------------------------------------- 1 | /app/target/release/deps/test-0a8bfcae0d226a1c: main.rs 2 | 3 | /app/target/release/deps/test-0a8bfcae0d226a1c.d: main.rs 4 | 5 | main.rs: 6 | -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/test: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bin123apple/AutoCoder/a51540e7d27a9d600a783a824de2a9017f599099/Web_demo/sandbox/rust/target/release/test -------------------------------------------------------------------------------- /Web_demo/sandbox/rust/target/release/test.d: -------------------------------------------------------------------------------- 1 | /app/target/release/test: /app/main.rs 2 | -------------------------------------------------------------------------------- /Web_demo/utils/cleaner.py: -------------------------------------------------------------------------------- 1 | import re 2 | import os 3 | 4 | PYTHON_PREFIX = os.environ.get("CONDA_PREFIX", "/usr/local") 5 | 6 | SITE_PKG_ERROR_PREFIX = f'File {PYTHON_PREFIX}/lib/python3.10/' 7 | 8 | def get_error_header(traceback_str): 9 | lines = traceback_str.split('\n') 10 | for line in lines: 11 | if 'Error:' in line: 12 | return line 13 | return '' # Return None if no error message is found 14 | 15 | def clean_error_msg(error_str:str =''): 16 | filtered_error_msg = error_str.__str__().split('An error occurred while executing the following cell')[-1].split("\n------------------\n")[-1] 17 | raw_error_msg = "".join(filtered_error_msg) 18 | 19 | # Remove escape sequences for colored text 20 | ansi_escape = re.compile(r'\x1b\[[0-?]*[ -/]*[@-~]') 21 | error_msg = ansi_escape.sub('', raw_error_msg) 22 | 23 | error_str_out = '' 24 | error_msg_only_cell = error_msg.split(SITE_PKG_ERROR_PREFIX) 25 | 26 | error_str_out += f'{error_msg_only_cell[0]}\n' 27 | error_header = get_error_header(error_msg_only_cell[-1]) 28 | if error_header not in error_str_out: 29 | error_str_out += get_error_header(error_msg_only_cell[-1]) 30 | 31 | return error_str_out -------------------------------------------------------------------------------- /Web_demo/utils/const.py: -------------------------------------------------------------------------------- 1 | TOOLS_CODE = """ 2 | import numpy as np 3 | import pandas as pd 4 | import matplotlib.pyplot as plt 5 | import seaborn as sns 6 | from scipy import stats 7 | import os,sys 8 | import re 9 | from datetime import datetime 10 | from sympy import symbols, Eq, solve 11 | import torch 12 | import requests 13 | from bs4 import BeautifulSoup 14 | import json 15 | import math 16 | import yfinance 17 | import time 18 | """ 19 | 20 | write_denial_function = 'lambda *args, **kwargs: (_ for _ in ()).throw(PermissionError("Writing to disk operation is not permitted due to safety reasons. Please do not try again!"))' 21 | read_denial_function = 'lambda *args, **kwargs: (_ for _ in ()).throw(PermissionError("Reading from disk operation is not permitted due to safety reasons. Please do not try again!"))' 22 | class_denial = """Class Denial: 23 | def __getattr__(self, name): 24 | def method(*args, **kwargs): 25 | return "Using this class is not permitted due to safety reasons. Please do not try again!" 26 | return method 27 | """ 28 | 29 | GUARD_CODE = f""" 30 | import os 31 | 32 | os.kill = {write_denial_function} 33 | os.system = {write_denial_function} 34 | os.putenv = {write_denial_function} 35 | os.remove = {write_denial_function} 36 | os.removedirs = {write_denial_function} 37 | os.rmdir = {write_denial_function} 38 | os.fchdir = {write_denial_function} 39 | os.setuid = {write_denial_function} 40 | os.fork = {write_denial_function} 41 | os.forkpty = {write_denial_function} 42 | os.killpg = {write_denial_function} 43 | os.rename = {write_denial_function} 44 | os.renames = {write_denial_function} 45 | os.truncate = {write_denial_function} 46 | os.replace = {write_denial_function} 47 | os.unlink = {write_denial_function} 48 | os.fchmod = {write_denial_function} 49 | os.fchown = {write_denial_function} 50 | os.chmod = {write_denial_function} 51 | os.chown = {write_denial_function} 52 | os.chroot = {write_denial_function} 53 | os.fchdir = {write_denial_function} 54 | os.lchflags = {write_denial_function} 55 | os.lchmod = {write_denial_function} 56 | os.lchown = {write_denial_function} 57 | os.getcwd = {write_denial_function} 58 | os.chdir = {write_denial_function} 59 | os.popen = {write_denial_function} 60 | 61 | import shutil 62 | 63 | shutil.rmtree = {write_denial_function} 64 | shutil.move = {write_denial_function} 65 | shutil.chown = {write_denial_function} 66 | 67 | import subprocess 68 | 69 | subprocess.Popen = {write_denial_function} # type: ignore 70 | 71 | import sys 72 | 73 | sys.modules["ipdb"] = {write_denial_function} 74 | sys.modules["joblib"] = {write_denial_function} 75 | sys.modules["resource"] = {write_denial_function} 76 | sys.modules["psutil"] = {write_denial_function} 77 | sys.modules["tkinter"] = {write_denial_function} 78 | """ 79 | 80 | CODE_INTERPRETER_SYSTEM_PROMPT = """You are an AI code interpreter. 81 | Your goal is to help users do a variety of jobs by executing Python code. 82 | 83 | You should: 84 | 1. Comprehend the user's requirements carefully & to the letter. 85 | 2. Give a brief description for what you plan to do & call the provided function to run code. 86 | 3. Provide results analysis based on the execution output. 87 | 4. If error occurred, try to fix it. 88 | 5. Response in the same language as the user.""" 89 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | numpy==1.25.0 2 | torchneuromorphic 3 | h5py==3.11.0 4 | scipy>=1.0 5 | tensorboardX==2.6.2.2 6 | datasets==2.19.1 7 | transformers==4.40.2 8 | torch==2.0.1 9 | accelerate==0.30.0 10 | gradio==3.48.0 11 | jupyter_client==8.3.0 --------------------------------------------------------------------------------