Online chat formatter

README.ENG.md

@@ -92,6 +92,7 @@ import lazyllm
 from lazyllm import pipeline, parallel, Identity, warp, package
 import time
 import re, json
+from lazyllm.components.formatter import JsonFormatter
 
 toc_prompt="""
 You are now an intelligent assistant. Your task is to understand the user's input and convert the outline into a list of nested dictionaries. Each dictionary contains a `title` and a `describe`, where the `title` should clearly indicate the level using Markdown format, and the `describe` is a description and writing guide for that section.
@@ -134,11 +135,12 @@ Receive as follows:
 </details>
 
 ```python
-t1 = lazyllm.OnlineChatModule(source="openai", stream=False, prompter=ChatPrompter(instruction=toc_prompt))
-t2 = lazyllm.OnlineChatModule(source="openai", stream=False, prompter=ChatPrompter(instruction=completion_prompt))
+jsonFormatter = JsonFormatter("[:]")
+t1 = lazyllm.OnlineChatModule(source="openai", stream=False).formatter(jsonFormatter).prompt(ChatPrompter(instruction=toc_prompt))
+t2 = lazyllm.OnlineChatModule(source="openai", stream=False).prompt(ChatPrompter(instruction=completion_prompt))
 
-spliter = lambda s: tuple(eval(re.search(r'\[\s*\{.*\}\s*\]', s['message']['content'], re.DOTALL).group()))
-writter = pipeline(lambda d: json.dumps(d, ensure_ascii=False), t2, lambda d : d['message']['content'])
+warper = lambda s: tuple(s)
+writter = pipeline(lambda d: json.dumps(d, ensure_ascii=False), t2, lambda d : d)
 collector = lambda dict_tuple, repl_tuple: "\n".join([v for d in [{**d, "describe": repl_tuple[i]} for i, d in enumerate(dict_tuple)] for v in d.values()])
 m = pipeline(t1, spliter, parallel(Identity, warp(writter)), collector)
 

README.md

@@ -89,6 +89,7 @@ import lazyllm
 from lazyllm import pipeline, parallel, Identity, warp, package
 import time
 import re, json
+from lazyllm.components.formatter import JsonFormatter
 
 toc_prompt=""" 你现在是一个智能助手。你的任务是理解用户的输入，将大纲以列表嵌套字典的列表。每个字典包含一个 `title` 和 `describe`，其中 `title` 中需要用Markdown格式标清层级，`describe` `describe` 是对该段的描述和写作指导。
 
@@ -129,11 +130,12 @@ completion_prompt="""
 </details>
 
 ```python
-t1 = lazyllm.OnlineChatModule(source="openai", stream=False, prompter=ChatPrompter(instruction=toc_prompt))
-t2 = lazyllm.OnlineChatModule(source="openai", stream=False, prompter=ChatPrompter(instruction=completion_prompt))
+jsonFormatter = JsonFormatter("[:]")
+t1 = lazyllm.OnlineChatModule(source="openai", stream=False).formatter(jsonFormatter).prompt(ChatPrompter(instruction=toc_prompt))
+t2 = lazyllm.OnlineChatModule(source="openai", stream=False).prompt(ChatPrompter(instruction=completion_prompt))
 
-spliter = lambda s: tuple(eval(re.search(r'\[\s*\{.*\}\s*\]', s['message']['content'], re.DOTALL).group()))
-writter = pipeline(lambda d: json.dumps(d, ensure_ascii=False), t2, lambda d : d['message']['content'])
+warper = lambda s: tuple(s)
+writter = pipeline(lambda d: json.dumps(d, ensure_ascii=False), t2, lambda d : d)
 collector = lambda dict_tuple, repl_tuple: "\n".join([v for d in [{**d, "describe": repl_tuple[i]} for i, d in enumerate(dict_tuple)] for v in d.values()])
 m = pipeline(t1, spliter, parallel(Identity, warp(writter)), collector)
 

docs/source/api/components.rst

@@ -60,3 +60,18 @@ ModelDownloader
 .. autoclass:: lazyllm.components.ModelDownloader
     :members: 
     :exclude-members:
+
+Formatter
+==========
+
+.. autoclass:: lazyllm.components.formatter.LazyLLMFormatterBase
+    :members:
+    :exclude-members:
+
+.. autoclass:: lazyllm.components.JsonFormatter
+    :members:
+    :exclude-members:
+
+.. autoclass:: lazyllm.components.EmptyFormatter
+    :members:
+    :exclude-members:

lazyllm/__init__.py

@@ -7,7 +7,8 @@
                    Loop as loop, Switch as switch, IFS as ifs, Warp as warp)
 from .components import (LazyLLMDataprocBase, LazyLLMFinetuneBase, LazyLLMDeployBase,
                          LazyLLMValidateBase, register as component_register, Prompter,
-                         AlpacaPrompter, ChatPrompter, FastapiApp)
+                         AlpacaPrompter, ChatPrompter, FastapiApp, JsonFormatter)
+
 from .module import (ModuleBase, UrlModule, TrainableModule, ActionModule,
                      ServerModule, TrialModule, register as module_register,
                      OnlineChatModule, OnlineEmbeddingModule)
@@ -33,6 +34,7 @@
     'AlpacaPrompter',
     'ChatPrompter',
     'FastapiApp',
+    'JsonFormatter',
 
     # flow
     'LazyLLMFlowsBase',            # pipeline, parallel

lazyllm/components/__init__.py

@@ -6,6 +6,7 @@
 from .validate import LazyLLMValidateBase
 from .auto import AutoDeploy, AutoFinetune
 from .utils import ModelDownloader
+from .formatter import FormatterBase, EmptyFormatter, JsonFormatter
 
 __all__ = [
     'register',
@@ -19,5 +20,8 @@
     'FastapiApp',
     'AutoDeploy',
     'AutoFinetune',
-    'ModelDownloader'
+    'ModelDownloader',
+    'FormatterBase',
+    'EmptyFormatter',
+    'JsonFormatter'
 ]

lazyllm/components/formatter/__init__.py

@@ -0,0 +1,10 @@
+from .formatterBase import LazyLLMFormatterBase, LazyLLMFormatterBase as FormatterBase, EmptyFormatter
+from .jsonFormatter import JsonFormatter
+
+
+__all__ = [
+    'LazyLLMFormatterBase',
+    'FormatterBase',
+    'EmptyFormatter',
+    'JsonFormatter'
+]

lazyllm/components/formatter/formatterBase.py

@@ -0,0 +1,55 @@
+from ...common import LazyLLMRegisterMetaClass
+
+def is_number(s):
+    try:
+        float(s)
+        return True
+    except ValueError:
+        pass
+
+    try:
+        import unicodedata
+        unicodedata.numeric(s)
+        return True
+    except (TypeError, ValueError):
+        pass
+    return False
+
+class LazyLLMFormatterBase(metaclass=LazyLLMRegisterMetaClass):
+    def __init__(self, formatter: str = None):
+        self._formatter = formatter
+        if self._formatter:
+            self._parse_formatter()
+        else:
+            self._slices = None
+
+    def _parse_formatter(self):
+        # Remove the surrounding brackets
+        slice_str = self._formatter.strip()[1:-1]
+        dimensions = slice_str.split(",")
+        slices = []
+
+        for dim in dimensions:
+            if ":" in dim:
+                parts = dim.split(":")
+                start = int(parts[0]) if is_number(parts[0]) else None
+                end = int(parts[1]) if len(parts) > 1 and is_number(parts[1]) else None
+                step = int(parts[2]) if len(parts) > 2 and is_number(parts[2]) else None
+                slices.append(slice(start, end, step))
+            else:
+                slices.append(dim.strip())
+        self._slices = slices
+
+    def _load_str(self, msg: str):
+        raise NotImplementedError("This parse str function is not implemented.")
+
+    def _parse_py_data_by_formatter(self, py_data):
+        raise NotImplementedError("This data parse function is not implemented.")
+
+    def format(self, msg):
+        if isinstance(msg, str): msg = self._load_str(msg)
+        return self._parse_py_data_by_formatter(msg)
+
+class EmptyFormatter(LazyLLMFormatterBase):
+    def format(self, msg):
+        return msg

lazyllm/components/formatter/jsonFormatter.py

@@ -0,0 +1,82 @@
+import copy
+import json
+from .formatterBase import LazyLLMFormatterBase as FormatterBase
+import lazyllm
+from typing import List, Dict, Union, Any
+
+class JsonFormatter(FormatterBase):
+    def _extract_json_from_string(self, mixed_str: str):
+        json_objects = []
+        brace_level = 0
+        current_json = ""
+        in_string = False
+
+        for char in mixed_str:
+            if char == '"' and (len(current_json) == 0 or current_json[-1] != '\\'):
+                in_string = not in_string
+
+            if not in_string:
+                if char == '{':
+                    if brace_level == 0:
+                        current_json = ""
+                    brace_level += 1
+                elif char == '}':
+                    brace_level -= 1
+
+            if brace_level > 0 or (brace_level == 0 and char == '}'):
+                current_json += char
+
+            if brace_level == 0 and current_json:
+                try:
+                    json.loads(current_json)
+                    json_objects.append(current_json)
+                    current_json = ""
+                except json.JSONDecodeError:
+                    continue
+
+        return json_objects
+
+    def _load_str(self, msg: str):
+        # Convert str to json format
+        assert msg.count("{") == msg.count("}"), f"{msg} is not a valid json string."
+        try:
+            json_strs = self._extract_json_from_string(msg)
+            if len(json_strs) == 0:
+                raise TypeError(f"{msg} is not a valid json string.")
+            res = []
+            for json_str in json_strs:
+                res.append(json.loads(json_str))
+            return res if len(res) > 1 else res[0]
+        except Exception as e:
+            lazyllm.LOG.info(f"Error: {e}")
+            return ""
+
+    def _parsing_format_output(self, keys: List, data: Union[List[Dict[str, Any]], Dict[str, Any]]):
+        if not keys:
+            return data
+        key = keys.pop(0)
+        try:
+            if isinstance(key, slice):
+                return self._parsing_format_output(keys, data[key])
+            elif isinstance(key, str):
+                if isinstance(data, List):
+                    res = [val[key] for val in data]
+                    return self._parsing_format_output(keys, res if len(res) > 1 else res[0])
+                elif isinstance(data, Dict):
+                    return self._parsing_format_output(keys, data.get(key, {}))
+                else:
+                    return data
+            else:
+                raise TypeError(f"This class is not support {key} index.")
+        except Exception as e:
+            lazyllm.LOG.error(f"{e}")
+            return ""
+
+    def _parse_py_data_by_formatter(self, data):
+        if self._slices is None:
+            return data
+        else:
+            keys = copy.deepcopy(self._slices)
+            result = self._parsing_format_output(keys, data)
+
+            return result[0] if len(result) == 1 and isinstance(result, List) else result