Online chat formatter

README.ENG.md

@@ -88,9 +88,10 @@ mweb = lazyllm.WebModule(ppl, port=23456).start().wait()
 
 ```python
 import lazyllm
-from lazyllm import pipeline, parallel, Identity, warp, package
+from lazyllm import pipeline, warp, package, bind
 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.
@@ -133,13 +134,15 @@ 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))
+t1 = lazyllm.OnlineChatModule(source="openai", stream=False).formatter(JsonFormatter().prompt(toc_prompt)
+t2 = lazyllm.OnlineChatModule(source="openai", stream=False).prompt(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'])
+writter = pipeline(lambda d: json.dumps(d, ensure_ascii=False), t2)
 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)
+with pipeline() as m:
+    m.m1 = t1
+    m.m2 = warp(writter)
+    m.m3 = bind(collector, m.m1, m.m2)
 
 print(m({'query': 'Please help me write an article about the application of artificial intelligence in the medical field.'}))
 ```

README.md

@@ -85,9 +85,10 @@ mweb = lazyllm.WebModule(ppl, port=23456).start().wait()
 
 ```python
 import lazyllm
-from lazyllm import pipeline, parallel, Identity, warp, package
+from lazyllm import pipeline, warp, package, bind
 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。
 
@@ -128,13 +129,15 @@ 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))
+t1 = lazyllm.OnlineChatModule(source="openai", stream=False).formatter(JsonFormatter()).prompt(toc_prompt)
+t2 = lazyllm.OnlineChatModule(source="openai", stream=False).prompt(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'])
+writter = pipeline(lambda d: json.dumps(d, ensure_ascii=False), t2)
 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)
+with pipeline() as m:
+    m.m1 = t1
+    m.m2 = warp(writter)
+    m.m3 = bind(collector, m.m1, m.m2)
 
 print(m({'query':'请帮我写一篇关于人工智能在医疗领域应用的文章。'}))
 ```

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/common/common.py

@@ -334,19 +334,19 @@ class LazyLlmRequest(struct):
 
     def split(self, flag=None):
         if flag is None:
-            assert len(self.kwargs) == 0 and isinstance(self.input, tuple), (
+            assert len(self.kwargs) == 0 and isinstance(self.input, (tuple, list)), (
                 f'Only tuple input can be split automatically, your input is {self.input} <{type(self.input)}>')
             return [LazyLlmRequest(input=inp, global_parameters=self.global_parameters) for inp in self.input]
         elif isinstance(flag, int):
-            assert len(self.kwargs) == 0 and isinstance(self.input, tuple), (
+            assert len(self.kwargs) == 0 and isinstance(self.input, (tuple, list)), (
                 f'Only tuple input can be split automatically, your input is {self.input} <{type(self.input)}>')
             assert flag == len(self.input), 'input size mismatch with split number'
             return [LazyLlmRequest(input=inp, global_parameters=self.global_parameters) for inp in self.input]
         elif isinstance(flag, list):
             if isinstance(self.input, dict):
                 assert len(self.kwargs) == 0, 'Cannot provived input and kwargs at the same time for split'
                 d = self.input
-            elif isinstance(self.input, tuple):
+            elif isinstance(self.input, (tuple, list)):
                 return self.split(len(flag))
             else:
                 assert not self.input, 'Cannot provived input and kwargs at the same time for split'

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 +1,50 @@
+from ...common import LazyLLMRegisterMetaClass
+
+def is_number(s: str):
+    try:
+        int(s)
+        return True
+    except ValueError:
+        if s.lower == "none" or len(s) == 0:
+            return False
+        else:
+            raise ValueError("Invalid number: " + s)
+
+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(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(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 +1,57 @@
+import json
+from .formatterBase import LazyLLMFormatterBase as FormatterBase
+import lazyllm
+
+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(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 _parse_py_data_by_formatter(self, data, *, slices=None):
+        if slices is None: slices = self._slices
+        if not slices: return data
+        if isinstance(slices[0], slice): return [self._parse_py_data_by_formatter(d, slices=slices[1:])
+                                                 for d in data[slices[0]]]
+        else: return self._parse_py_data_by_formatter(data[slices[0]], slices=slices[1:])