aient 1.0.29__py3-none-any.whl

aient/utils/scripts.py

@@ -0,0 +1,235 @@
+import os
+import json
+import base64
+import tiktoken
+import requests
+import urllib.parse
+
+from ..core.utils import get_image_message
+
+def get_encode_text(text, model_name):
+    tiktoken.get_encoding("cl100k_base")
+    model_name = "gpt-3.5-turbo"
+    encoding = tiktoken.encoding_for_model(model_name)
+    encode_text = encoding.encode(text, disallowed_special=())
+    return encoding, encode_text
+
+def get_text_token_len(text, model_name):
+    encoding, encode_text = get_encode_text(text, model_name)
+    return len(encode_text)
+
+def cut_message(message: str, max_tokens: int, model_name: str):
+    if type(message) != str:
+        message = str(message)
+    encoding, encode_text = get_encode_text(message, model_name)
+    if len(encode_text) > max_tokens:
+        encode_text = encode_text[:max_tokens]
+        message = encoding.decode(encode_text)
+    encode_text = encoding.encode(message, disallowed_special=())
+    return message, len(encode_text)
+
+import imghdr
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        file_content = image_file.read()
+        file_type = imghdr.what(None, file_content)
+        base64_encoded = base64.b64encode(file_content).decode('utf-8')
+
+        if file_type == 'png':
+            return f"data:image/png;base64,{base64_encoded}"
+        elif file_type in ['jpeg', 'jpg']:
+            return f"data:image/jpeg;base64,{base64_encoded}"
+        else:
+            raise ValueError(f"不支持的图片格式: {file_type}")
+
+def get_doc_from_url(url):
+    filename = urllib.parse.unquote(url.split("/")[-1])
+    response = requests.get(url, stream=True)
+    with open(filename, 'wb') as f:
+        for chunk in response.iter_content(chunk_size=1024):
+            f.write(chunk)
+    return filename
+
+def get_encode_image(image_url):
+    filename = get_doc_from_url(image_url)
+    image_path = os.getcwd() + "/" + filename
+    base64_image = encode_image(image_path)
+    os.remove(image_path)
+    return base64_image
+
+from io import BytesIO
+def get_audio_message(file_bytes):
+    try:
+        # 创建一个字节流对象
+        audio_stream = BytesIO(file_bytes)
+
+        # 直接使用字节流对象进行转录
+        import config
+        transcript = config.whisperBot.generate(audio_stream)
+        # print("transcript", transcript)
+
+        return transcript
+
+    except Exception as e:
+        return f"处理音频文件时出错： {str(e)}"
+
+async def Document_extract(docurl, docpath=None, engine_type = None):
+    filename = docpath
+    text = None
+    prompt = None
+    if docpath and docurl and "paper.pdf" != docpath:
+        filename = get_doc_from_url(docurl)
+        docpath = os.getcwd() + "/" + filename
+    if filename and filename[-3:] == "pdf":
+        from pdfminer.high_level import extract_text
+        text = extract_text(docpath)
+    if filename and (filename[-3:] == "txt" or filename[-3:] == ".md" or filename[-3:] == ".py" or filename[-3:] == "yml"):
+        with open(docpath, 'r') as f:
+            text = f.read()
+    if text:
+        prompt = (
+            "Here is the document, inside <document></document> XML tags:"
+            "<document>"
+            "{}"
+            "</document>"
+        ).format(text)
+    if filename and filename[-3:] == "jpg" or filename[-3:] == "png" or filename[-4:] == "jpeg":
+        prompt = await get_image_message(docurl, engine_type)
+    if filename and filename[-3:] == "wav" or filename[-3:] == "mp3":
+        with open(docpath, "rb") as file:
+            file_bytes = file.read()
+        prompt = get_audio_message(file_bytes)
+        prompt = (
+            "Here is the text content after voice-to-text conversion, inside <voice-to-text></voice-to-text> XML tags:"
+            "<voice-to-text>"
+            "{}"
+            "</voice-to-text>"
+        ).format(prompt)
+    if os.path.exists(docpath):
+        os.remove(docpath)
+    return prompt
+
+def split_json_strings(input_string):
+    # 初始化结果列表和当前 JSON 字符串
+    json_strings = []
+    current_json = ""
+    brace_count = 0
+
+    # 遍历输入字符串的每个字符
+    for char in input_string:
+        current_json += char
+        if char == '{':
+            brace_count += 1
+        elif char == '}':
+            brace_count -= 1
+
+            # 如果花括号配对完成，我们找到了一个完整的 JSON 字符串
+            if brace_count == 0:
+                # 尝试解析当前 JSON 字符串
+                try:
+                    json.loads(current_json)
+                    json_strings.append(current_json)
+                    current_json = ""
+                except json.JSONDecodeError:
+                    # 如果解析失败，继续添加字符
+                    pass
+    if json_strings == []:
+        json_strings.append(input_string)
+    return json_strings
+
+def check_json(json_data):
+    while True:
+        try:
+            result = split_json_strings(json_data)
+            if len(result) > 0:
+                json_data = result[0]
+            json.loads(json_data)
+            break
+        except json.decoder.JSONDecodeError as e:
+            print("JSON error：", e)
+            print("JSON body", repr(json_data))
+            if "Invalid control character" in str(e):
+                json_data = json_data.replace("\n", "\\n")
+            elif "Unterminated string starting" in str(e):
+                json_data += '"}'
+            elif "Expecting ',' delimiter" in str(e):
+                json_data =  {"prompt": json_data}
+            elif "Expecting ':' delimiter" in str(e):
+                json_data = '{"prompt": ' + json.dumps(json_data) + '}'
+            elif "Expecting value: line 1 column 1" in str(e):
+                if json_data.startswith("prompt: "):
+                    json_data = json_data.replace("prompt: ", "")
+                json_data = '{"prompt": ' + json.dumps(json_data) + '}'
+            else:
+                json_data = '{"prompt": ' + json.dumps(json_data) + '}'
+    return json_data
+
+def is_surrounded_by_chinese(text, index):
+    left_char = text[index - 1]
+    if 0 < index < len(text) - 1:
+        right_char = text[index + 1]
+        return '\u4e00' <= left_char <= '\u9fff' or '\u4e00' <= right_char <= '\u9fff'
+    if index == len(text) - 1:
+        return '\u4e00' <= left_char <= '\u9fff'
+    return False
+
+def replace_char(string, index, new_char):
+    return string[:index] + new_char + string[index+1:]
+
+def claude_replace(text):
+    Punctuation_mapping = {",": "，", ":": "：", "!": "！", "?": "？", ";": "；"}
+    key_list = list(Punctuation_mapping.keys())
+    for i in range(len(text)):
+        if is_surrounded_by_chinese(text, i) and (text[i] in key_list):
+            text = replace_char(text, i, Punctuation_mapping[text[i]])
+    return text
+
+def safe_get(data, *keys, default=None):
+    for key in keys:
+        try:
+            data = data[key] if isinstance(data, (dict, list)) else data.get(key)
+        except (KeyError, IndexError, AttributeError, TypeError):
+            return default
+    return data
+
+import asyncio
+def async_generator_to_sync(async_gen):
+    """
+    将异步生成器转换为同步生成器的工具函数
+
+    Args:
+        async_gen: 异步生成器函数
+
+    Yields:
+        异步生成器产生的每个值
+    """
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+
+    try:
+        async def collect_chunks():
+            chunks = []
+            async for chunk in async_gen:
+                chunks.append(chunk)
+            return chunks
+
+        chunks = loop.run_until_complete(collect_chunks())
+        for chunk in chunks:
+            yield chunk
+
+    except Exception as e:
+        print(f"Error during async execution: {e}")
+        raise
+    finally:
+        try:
+            # 清理所有待处理的任务
+            tasks = [t for t in asyncio.all_tasks(loop) if not t.done()]
+            if tasks:
+                loop.run_until_complete(asyncio.gather(*tasks, return_exceptions=True))
+            loop.run_until_complete(loop.shutdown_asyncgens())
+            loop.close()
+        except Exception as e:
+            print(f"Error during cleanup: {e}")
+
+if __name__ == "__main__":
+    os.system("clear")

aient-1.0.29.dist-info/METADATA

@@ -0,0 +1,119 @@
+Metadata-Version: 2.4
+Name: aient
+Version: 1.0.29
+Summary: Aient: The Awakening of Agent.
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pytz
+Requires-Dist: httpx
+Requires-Dist: pillow
+Requires-Dist: msgspec
+Requires-Dist: fastapi
+Requires-Dist: PyExecJS
+Requires-Dist: requests
+Requires-Dist: html2text
+Requires-Dist: fake-useragent
+Requires-Dist: beautifulsoup4
+Requires-Dist: tiktoken==0.6.0
+Requires-Dist: lxml-html-clean
+Requires-Dist: pdfminer.six==20240706
+Requires-Dist: duckduckgo-search==5.3.1
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: summary
+
+# aient
+
+[English](./README.md) | [Chinese](./README_CN.md)
+
+aient is a powerful library designed to simplify and unify the use of different large language models, including GPT-3.5/4/4 Turbo/4o, o1-preview/o1-mini, DALL-E 3, Claude2/3/3.5, Gemini1.5 Pro/Flash, Vertex AI (Claude, Gemini), DuckDuckGo, and Groq. The library supports GPT format function calls and has built-in Google search and URL summarization features, greatly enhancing the practicality and flexibility of the models.
+
+## ✨ Features
+
+- **Multi-model support**: Integrate various latest large language models.
+- **Real-time Interaction**: Supports real-time query streams, real-time model response retrieval.
+- **Function Expansion**: With built-in function calling support, the model's functions can be easily expanded, currently supporting plugins such as DuckDuckGo and Google search, content summarization, Dalle-3 drawing, arXiv paper summaries, current time, code interpreter, and more.
+- **Simple Interface**: Provides a concise and unified API interface, making it easy to call and manage the model.
+
+## Quick Start
+
+The following is a guide on how to quickly integrate and use aient in your Python project.
+
+### Install
+
+First, you need to install aient. It can be installed directly via pip:
+
+```bash
+pip install aient
+```
+
+### Usage example
+
+The following is a simple example demonstrating how to use aient to request the GPT-4 model and handle the returned streaming data:
+
+```python
+from aient import chatgpt
+
+# Initialize the model, set the API key and the selected model
+bot = chatgpt(api_key="{YOUR_API_KEY}", engine="gpt-4o")
+
+# Get response
+result = bot.ask("python list use")
+
+# Send request and get streaming response in real-time
+for text in bot.ask_stream("python list use"):
+    print(text, end="")
+
+# Disable all plugins
+bot = chatgpt(api_key="{YOUR_API_KEY}", engine="gpt-4o", use_plugins=False)
+```
+
+## 🍃 Environment Variables
+
+The following is a list of environment variables related to plugin settings:
+
+| Variable Name | Description | Required? |
+|---------------|-------------|-----------|
+| get_search_results | Enable search plugin. Default value is `False`. | No |
+| get_url_content | Enable URL summary plugin. The default value is `False`. | No |
+| download_read_arxiv_pdf | Whether to enable the arXiv paper abstract plugin. The default value is `False`. | No |
+| run_python_script | Whether to enable the code interpreter plugin. The default value is `False`. | No |
+| generate_image | Whether to enable the image generation plugin. The default value is `False`. | No |
+| get_date_time_weekday | Whether to enable the date plugin. The default value is `False`. | No |
+
+## Supported models
+
+- GPT-3.5/4/4 Turbo/4o
+- o1-preview/o1-mini
+- DALL-E 3
+- Claude2/3/3.5
+- Gemini1.5 Pro/Flash
+- Vertex AI (Claude, Gemini)
+- Groq
+- DuckDuckGo(gpt-4o-mini, claude-3-haiku, Meta-Llama-3.1-70B, Mixtral-8x7B)
+
+## 🧩 Plugin
+
+This project supports multiple plugins, including: DuckDuckGo and Google search, URL summary, ArXiv paper summary, DALLE-3 drawing, and code interpreter, etc. You can enable or disable these plugins by setting environment variables.
+
+- How to develop a plugin?
+
+The plugin-related code is all in the aient git submodule of this repository. aient is an independent repository I developed for handling API requests, conversation history management, and other functionality. When you clone this repository with the `--recurse-submodules` parameter, aient will be automatically downloaded. All plugin code is located in the relative path `aient/src/aient/plugins` in this repository. You can add your own plugin code in this directory. The plugin development process is as follows:
+
+1. Create a new Python file in the `aient/src/aient/plugins` directory, for example, `myplugin.py`. Register the plugin by adding the `@register_tool()` decorator above the function. Import `register_tool` with `from .registry import register_tool`.
+
+After completing the above steps, your plugin is ready to use. 🎉
+
+## License
+
+This project is licensed under the MIT License.
+
+## Contribution
+
+Welcome to contribute improvements by submitting issues or pull requests through GitHub.
+
+## Contact Information
+
+If you have any questions or need assistance, please contact us at [yym68686@outlook.com](mailto:yym68686@outlook.com).

aient-1.0.29.dist-info/RECORD

@@ -0,0 +1,36 @@
+aient/__init__.py,sha256=SRfF7oDVlOOAi6nGKiJIUK6B_arqYLO9iSMp-2IZZps,21
+aient/core/.git,sha256=lrAcW1SxzRBUcUiuKL5tS9ykDmmTXxyLP3YYU-Y-Q-I,45
+aient/core/__init__.py,sha256=NxjebTlku35S4Dzr16rdSqSTWUvvwEeACe8KvHJnjPg,34
+aient/core/log_config.py,sha256=kz2_yJv1p-o3lUQOwA3qh-LSc3wMHv13iCQclw44W9c,274
+aient/core/models.py,sha256=8MsuiYHBHVR5UMQ_cNLkvntoxalS7NpVwaNwHA0iZmk,7379
+aient/core/request.py,sha256=Tk8ylLBHPsrA4C_fb2XUEz_ZM7tR4691mlIxn7x8LUU,48249
+aient/core/response.py,sha256=jE2d-X-ukP5Jy5FCG2VHw5VZgPzhH56_N0gQPqIVggA,26351
+aient/core/utils.py,sha256=i9ZwyywBLIhRM0fNmFSD3jF3dBL5QqVMOtSlG_ddv-I,24101
+aient/core/test/test_base_api.py,sha256=CjfFzMG26r8C4xCPoVkKb3Ac6pp9gy5NUCbZJHoSSsM,393
+aient/core/test/test_image.py,sha256=_T4peNGdXKBHHxyQNx12u-NTyFE8TlYI6NvvagsG2LE,319
+aient/core/test/test_payload.py,sha256=8jBiJY1uidm1jzL-EiK0s6UGmW9XkdsuuKFGrwFhFkw,2755
+aient/models/__init__.py,sha256=ouNDNvoBBpIFrLsk09Q_sq23HR0GbLAKfGLIFmfEuXE,219
+aient/models/audio.py,sha256=kRd-8-WXzv4vwvsTGwnstK-WR8--vr9CdfCZzu8y9LA,1934
+aient/models/base.py,sha256=Loyt2F2WrDMBbK-sdmTtgkLVtdUXxK5tg4qoI6nc0Xo,7527
+aient/models/chatgpt.py,sha256=-07w8jTw6S5eKMWRtyWxTAM-2QQsDI1qyUWvnsT5eLU,36921
+aient/models/claude.py,sha256=thK9P8qkaaoUN3OOJ9Shw4KDs-pAGKPoX4FOPGFXva8,28597
+aient/models/duckduckgo.py,sha256=1l7vYCs9SG5SWPCbcl7q6pCcB5AUF_r-a4l9frz3Ogo,8115
+aient/models/gemini.py,sha256=chGLc-8G_DAOxr10HPoOhvVFW1RvMgHd6mt--VyAW98,14730
+aient/models/groq.py,sha256=2JCB0QE1htOprJHI5fZ11R2RtOhsHlsTjbmFyzc8oSM,10084
+aient/models/vertex.py,sha256=qVD5l1Q538xXUPulxG4nmDjXE1VoV4yuAkTCpIeJVw0,16795
+aient/plugins/__init__.py,sha256=KrCM6kFD1NB96hfhwUZIG8vJcdZVnfpACMew5YOWxSo,956
+aient/plugins/arXiv.py,sha256=yHjb6PS3GUWazpOYRMKMzghKJlxnZ5TX8z9F6UtUVow,1461
+aient/plugins/config.py,sha256=S7UHlo5e-czjssSyDQXVbR9bUlB21Fj934OfOKW5Vug,8191
+aient/plugins/image.py,sha256=ZElCIaZznE06TN9xW3DrSukS7U3A5_cjk1Jge4NzPxw,2072
+aient/plugins/registry.py,sha256=YknzhieU_8nQ3oKlUSSWDB4X7t2Jx0JnqT2Jd9Xsvfk,3574
+aient/plugins/run_python.py,sha256=dgcUwBunMuDkaSKR5bToudVzSdrXVewktDDFUz_iIOQ,4589
+aient/plugins/today.py,sha256=btnXJNqWorJDKPvH9PBTdHaExpVI1YPuSAeRrq-fg9A,667
+aient/plugins/websearch.py,sha256=RY0BaYgPC3OTTTDlezakXm6JvXixMEXUqHN5MXpXijw,15144
+aient/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+aient/utils/prompt.py,sha256=UcSzKkFE4-h_1b6NofI6xgk3GoleqALRKY8VBaXLjmI,11311
+aient/utils/scripts.py,sha256=O-0IXN3mezPauFs6fw83WDDgklpXTDvcbJBNTDrsIG0,8201
+aient-1.0.29.dist-info/licenses/LICENSE,sha256=XNdbcWldt0yaNXXWB_Bakoqnxb3OVhUft4MgMA_71ds,1051
+aient-1.0.29.dist-info/METADATA,sha256=BmMRouk-Oict-XOBDYh8toZrKz54jBi2r9XHtzceiOY,4986
+aient-1.0.29.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
+aient-1.0.29.dist-info/top_level.txt,sha256=3oXzrP5sAVvyyqabpeq8A2_vfMtY554r4bVE-OHBrZk,6
+aient-1.0.29.dist-info/RECORD,,

aient-1.0.29.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (77.0.3)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

aient-1.0.29.dist-info/licenses/LICENSE

@@ -0,0 +1,7 @@
+Copyright (c) 2024 yym68686
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

aient-1.0.29.dist-info/top_level.txt

@@ -0,0 +1 @@
+aient