diff --git a/app_chatgpt/i18n/zh_CN.po b/app_chatgpt/i18n/zh_CN.po
index 53f4aa0a..3f170f4a 100644
--- a/app_chatgpt/i18n/zh_CN.po
+++ b/app_chatgpt/i18n/zh_CN.po
@@ -4,10 +4,10 @@
 #
 msgid ""
 msgstr ""
-"Project-Id-Version: Odoo Server 16.0+e-20230213\n"
+"Project-Id-Version: Odoo Server 16.0+e-20230320\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2023-03-02 10:08+0000\n"
-"PO-Revision-Date: 2023-03-02 10:08+0000\n"
+"POT-Creation-Date: 2023-03-29 07:58+0000\n"
+"PO-Revision-Date: 2023-03-29 07:58+0000\n"
 "Last-Translator: \n"
 "Language-Team: \n"
 "MIME-Version: 1.0\n"
@@ -15,6 +15,21 @@ msgstr ""
 "Content-Transfer-Encoding: \n"
 "Plural-Forms: \n"
 
+#. module: app_chatgpt
+#: model:ir.model.fields,help:app_chatgpt.field_ai_robot__ai_model
+msgid ""
+"\n"
+"GPT-4: Can understand Image, generate natural language or code.\n"
+"GPT-3.5: A set of models that improve on GPT-3 and can understand as well as generate natural language or code\n"
+"DALL·E: A model that can generate and edit images given a natural language prompt\n"
+"Whisper: A model that can convert audio into text\n"
+"Embeddings:\tA set of models that can convert text into a numerical form\n"
+"CodexLimited: A set of models that can understand and generate code, including translating natural language to code\n"
+"Moderation: A fine-tuned model that can detect whether text may be sensitive or unsafe\n"
+"GPT-3\tA set of models that can understand and generate natural language\n"
+"                             "
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -405,6 +420,16 @@ msgstr ""
 msgid "ABCD"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__ai_model
+msgid "AI Model"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__provider
+msgid "AI Provider"
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -414,11 +439,14 @@ msgstr ""
 
 #. module: app_chatgpt
 #: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__openapi_api_key
-#: model:ir.model.fields,field_description:app_chatgpt.field_res_config_settings__openapi_api_key
-#: model_terms:ir.ui.view,arch_db:app_chatgpt.is_res_config_settings_view
 msgid "API Key"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__api_version
+msgid "API Version"
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -510,6 +538,11 @@ msgstr ""
 msgid "Australia"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__provider__azure
+msgid "Azure"
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -619,6 +652,11 @@ msgstr ""
 msgid "ChatGPT"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ai.robot,name:app_chatgpt.chatgpt_robot3
+msgid "ChatGPT Azure"
+msgstr ""
+
 #. module: app_chatgpt
 #: model:ai.robot,name:app_chatgpt.chatgpt_robot1
 msgid "ChatGPT Coding"
@@ -648,6 +686,36 @@ msgstr ""
 msgid "ChatGpt Training"
 msgstr "ChatGpt训练"
 
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__code-davinci-002
+msgid "Chatgpt 2 Code Optimized"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__text-davinci-002
+msgid "Chatgpt 2 Davinci"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__text-davinci-003
+msgid "Chatgpt 3 Davinci"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__gpt-3_5-turbo
+msgid "Chatgpt 3.5 Turbo"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__gpt-3_5-turbo-0301
+msgid "Chatgpt 3.5 Turbo on 20230301"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__gpt-4
+msgid "Chatgpt 4"
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -710,6 +778,11 @@ msgstr ""
 msgid "DVD"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__ai_model__dall-e2
+msgid "Dall-E Image"
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -764,6 +837,16 @@ msgstr ""
 msgid "END arrow"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__endpoint
+msgid "End Point"
+msgstr ""
+
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__engine
+msgid "Engine"
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -822,6 +905,11 @@ msgstr ""
 msgid "Ferris"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__is_filtering
+msgid "Filter Sensitive Words"
+msgstr "是否启用敏感词过滤"
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -917,6 +1005,11 @@ msgstr ""
 msgid "ILY"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,help:app_chatgpt.field_ai_robot__engine
+msgid "If use Azure, Please input the Model deployment name."
+msgstr ""
+
 #. module: app_chatgpt
 #. odoo-javascript
 #: code:addons/app_chatgpt/static/src/models_data/emoji_data.js:0
@@ -1244,6 +1337,11 @@ msgstr ""
 msgid "Mahjong red dragon"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__max_length
+msgid "Max Length"
+msgstr ""
+
 #. module: app_chatgpt
 #: model:ir.model,name:app_chatgpt.model_mail_message
 msgid "Message"
@@ -1436,8 +1534,13 @@ msgid "Objects"
 msgstr ""
 
 #. module: app_chatgpt
-#: model_terms:ir.ui.view,arch_db:app_chatgpt.is_res_config_settings_view
-msgid "OpenAPI API Key"
+#: model:ir.model.fields.selection,name:app_chatgpt.selection__ai_robot__provider__openai
+msgid "OpenAI"
+msgstr ""
+
+#. module: app_chatgpt
+#: model_terms:ir.ui.view,arch_db:app_chatgpt.ai_robot_form_view
+msgid "OpenAI Document"
 msgstr ""
 
 #. module: app_chatgpt
@@ -1487,9 +1590,22 @@ msgstr ""
 msgid "Pisces"
 msgstr ""
 
+#. module: app_chatgpt
+#. odoo-python
+#: code:addons/app_chatgpt/models/ai_robot.py:0
+#, python-format
+msgid "Please Set your AI robot's API Version first."
+msgstr ""
+
+#. module: app_chatgpt
+#. odoo-python
+#: code:addons/app_chatgpt/models/ai_robot.py:0
+#, python-format
+msgid "Please Set your AI robot's endpoint first."
+msgstr ""
+
 #. module: app_chatgpt
 #: model:ir.model.fields,help:app_chatgpt.field_ai_robot__openapi_api_key
-#: model:ir.model.fields,help:app_chatgpt.field_res_config_settings__openapi_api_key
 msgid "Provide the API key here"
 msgstr ""
 
@@ -1582,6 +1698,16 @@ msgstr ""
 msgid "Selected Users"
 msgstr ""
 
+#. module: app_chatgpt
+#: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__sensitive_words
+msgid "Sensitive Words"
+msgstr "敏感词"
+
+#. module: app_chatgpt
+#: model:ir.model.fields,help:app_chatgpt.field_ai_robot__sensitive_words
+msgid "Sensitive word filtering. Separate keywords with a carriage return."
+msgstr "敏感词过滤。请用回车符分隔关键词。"
+
 #. module: app_chatgpt
 #: model:ir.model.fields,field_description:app_chatgpt.field_ai_robot__sequence
 msgid "Sequence"
@@ -1805,7 +1931,7 @@ msgstr ""
 #. module: app_chatgpt
 #: model:ir.model,name:app_chatgpt.model_res_users
 msgid "User"
-msgstr "用户"
+msgstr ""
 
 #. module: app_chatgpt
 #. odoo-javascript
diff --git a/app_chatgpt/models/ai_robot.py b/app_chatgpt/models/ai_robot.py
index 8d863317..0259218e 100644
--- a/app_chatgpt/models/ai_robot.py
+++ b/app_chatgpt/models/ai_robot.py
@@ -4,10 +4,12 @@ import requests
 import openai
 from odoo import api, fields, models, _
 from odoo.exceptions import UserError
+from .lib.WordsSearch import WordsSearch
 
 import logging
 _logger = logging.getLogger(__name__)
 
+
 class AiRobot(models.Model):
     _name = 'ai.robot'
     _description = 'Gpt Robot'
@@ -41,6 +43,8 @@ GPT-3	A set of models that can understand and generate natural language
     engine = fields.Char('Engine', help='If use Azure, Please input the Model deployment name.')
     api_version = fields.Char('API Version', default='2022-12-01')
     sequence = fields.Integer('Sequence', help="Determine the display order", default=10)
+    sensitive_words = fields.Text('Sensitive Words', help='Sensitive word filtering. Separate keywords with a carriage return.')
+    is_filtering = fields.Boolean('Filter Sensitive Words', default=False)
 
     def action_disconnect(self):
         requests.delete('https://chatgpt.com/v1/disconnect')
@@ -68,6 +72,7 @@ GPT-3	A set of models that can understand and generate natural language
         _logger.warning('=====================azure input data: %s' % data)
         if 'choices' in response:
             res = response['choices'][0]['text'].replace(' .', '.').strip()
+            res = self.filter_sensitive_words(res)
             return res
 
     @api.onchange('provider')
@@ -77,3 +82,10 @@ GPT-3	A set of models that can understand and generate natural language
         elif self.provider == 'azure':
             self.endpoint = 'https://odoo.openai.azure.com'
             
+    def filter_sensitive_words(self, data):
+        if self.is_filtering:
+            search = WordsSearch()
+            s = self.sensitive_words
+            search.SetKeywords(s.split('\n'))
+            result = search.Replace(text=data)
+            return result
diff --git a/app_chatgpt/models/lib/WordsSearch.py b/app_chatgpt/models/lib/WordsSearch.py
new file mode 100644
index 00000000..02c16410
--- /dev/null
+++ b/app_chatgpt/models/lib/WordsSearch.py
@@ -0,0 +1,291 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+# ToolGood.Words.WordsSearch.py
+# 2020, Lin Zhijun, https://github.com/toolgood/ToolGood.Words
+# Licensed under the Apache License 2.0
+# 更新日志
+# 2020.04.06 第一次提交
+# 2020.05.16 修改，支持大于0xffff的字符
+
+__all__ = ['WordsSearch']
+__author__ = 'Lin Zhijun'
+__date__ = '2020.05.16'
+
+
+class TrieNode():
+    def __init__(self):
+        self.Index = 0
+        self.Index = 0
+        self.Layer = 0
+        self.End = False
+        self.Char = ''
+        self.Results = []
+        self.m_values = {}
+        self.Failure = None
+        self.Parent = None
+
+    def Add(self, c):
+        if c in self.m_values:
+            return self.m_values[c]
+        node = TrieNode()
+        node.Parent = self
+        node.Char = c
+        self.m_values[c] = node
+        return node
+
+    def SetResults(self, index):
+        if (self.End == False):
+            self.End = True
+        self.Results.append(index)
+
+
+class TrieNode2():
+    def __init__(self):
+        self.End = False
+        self.Results = []
+        self.m_values = {}
+        self.minflag = 0xffff
+        self.maxflag = 0
+
+    def Add(self, c, node3):
+        if (self.minflag > c):
+            self.minflag = c
+        if (self.maxflag < c):
+            self.maxflag = c
+        self.m_values[c] = node3
+
+    def SetResults(self, index):
+        if (self.End == False):
+            self.End = True
+        if (index in self.Results) == False:
+            self.Results.append(index)
+
+    def HasKey(self, c):
+        return c in self.m_values
+
+    def TryGetValue(self, c):
+        if (self.minflag <= c and self.maxflag >= c):
+            if c in self.m_values:
+                return self.m_values[c]
+        return None
+
+
+class WordsSearch():
+    def __init__(self):
+        self._first = {}
+        self._keywords = []
+        self._indexs = []
+
+    def SetKeywords(self, keywords):
+        self._keywords = keywords
+        self._indexs = []
+        for i in range(len(keywords)):
+            self._indexs.append(i)
+
+        root = TrieNode()
+        allNodeLayer = {}
+
+        for i in range(len(self._keywords)):  # for (i = 0; i < _keywords.length; i++)
+            p = self._keywords[i]
+            nd = root
+            for j in range(len(p)):  # for (j = 0; j < p.length; j++)
+                nd = nd.Add(ord(p[j]))
+                if (nd.Layer == 0):
+                    nd.Layer = j + 1
+                    if nd.Layer in allNodeLayer:
+                        allNodeLayer[nd.Layer].append(nd)
+                    else:
+                        allNodeLayer[nd.Layer] = []
+                        allNodeLayer[nd.Layer].append(nd)
+            nd.SetResults(i)
+
+        allNode = []
+        allNode.append(root)
+        for key in allNodeLayer.keys():
+            for nd in allNodeLayer[key]:
+                allNode.append(nd)
+        allNodeLayer = None
+
+        for i in range(len(allNode)):  # for (i = 0; i < allNode.length; i++)
+            if i == 0:
+                continue
+            nd = allNode[i]
+            nd.Index = i
+            r = nd.Parent.Failure
+            c = nd.Char
+            while (r != None and (c in r.m_values) == False):
+                r = r.Failure
+            if (r == None):
+                nd.Failure = root
+            else:
+                nd.Failure = r.m_values[c]
+                for key2 in nd.Failure.Results:
+                    nd.SetResults(key2)
+        root.Failure = root
+
+        allNode2 = []
+        for i in range(len(allNode)):  # for (i = 0; i < allNode.length; i++)
+            allNode2.append(TrieNode2())
+
+        for i in range(len(allNode2)):  # for (i = 0; i < allNode2.length; i++)
+            oldNode = allNode[i]
+            newNode = allNode2[i]
+
+            for key in oldNode.m_values:
+                index = oldNode.m_values[key].Index
+                newNode.Add(key, allNode2[index])
+
+            for index in range(len(oldNode.Results)):  # for (index = 0; index < oldNode.Results.length; index++)
+                item = oldNode.Results[index]
+                newNode.SetResults(item)
+
+            oldNode = oldNode.Failure
+            while oldNode != root:
+                for key in oldNode.m_values:
+                    if (newNode.HasKey(key) == False):
+                        index = oldNode.m_values[key].Index
+                        newNode.Add(key, allNode2[index])
+                for index in range(len(oldNode.Results)):
+                    item = oldNode.Results[index]
+                    newNode.SetResults(item)
+                oldNode = oldNode.Failure
+        allNode = None
+        root = None
+
+        # first = []
+        # for index in range(65535):# for (index = 0; index < 0xffff; index++)
+        #     first.append(None)
+
+        # for key in allNode2[0].m_values :
+        #     first[key] = allNode2[0].m_values[key]
+
+        self._first = allNode2[0]
+
+    def FindFirst(self, text):
+        ptr = None
+        for index in range(len(text)):  # for (index = 0; index < text.length; index++)
+            t = ord(text[index])  # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn == None):
+                    tn = self._first.TryGetValue(t)
+
+            if (tn != None):
+                if (tn.End):
+                    item = tn.Results[0]
+                    keyword = self._keywords[item]
+                    return {"Keyword": keyword, "Success": True, "End": index, "Start": index + 1 - len(keyword), "Index": self._indexs[item]}
+            ptr = tn
+        return None
+
+    def FindAll(self, text):
+        ptr = None
+        list = []
+
+        for index in range(len(text)):  # for (index = 0; index < text.length; index++)
+            t = ord(text[index])  # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn == None):
+                    tn = self._first.TryGetValue(t)
+
+            if (tn != None):
+                if (tn.End):
+                    for j in range(len(tn.Results)):  # for (j = 0; j < tn.Results.length; j++)
+                        item = tn.Results[j]
+                        keyword = self._keywords[item]
+                        list.append({"Keyword": keyword, "Success": True, "End": index, "Start": index + 1 - len(keyword), "Index": self._indexs[item]})
+            ptr = tn
+        return list
+
+    def ContainsAny(self, text):
+        ptr = None
+        for index in range(len(text)):  # for (index = 0; index < text.length; index++)
+            t = ord(text[index])  # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn == None):
+                    tn = self._first.TryGetValue(t)
+
+            if (tn != None):
+                if (tn.End):
+                    return True
+            ptr = tn
+        return False
+
+    def Replace(self, text, replaceChar='*'):
+        result = list(text)
+
+        ptr = None
+        for i in range(len(text)):  # for (i = 0; i < text.length; i++)
+            t = ord(text[i])  # text.charCodeAt(index)
+            tn = None
+            if (ptr == None):
+                tn = self._first.TryGetValue(t)
+            else:
+                tn = ptr.TryGetValue(t)
+                if (tn == None):
+                    tn = self._first.TryGetValue(t)
+
+            if (tn != None):
+                if (tn.End):
+                    maxLength = len(self._keywords[tn.Results[0]])
+                    start = i + 1 - maxLength
+                    for j in range(start, i + 1):  # for (j = start; j <= i; j++)
+                        result[j] = replaceChar
+            ptr = tn
+        return ''.join(result)
+
+
+if __name__ == "__main__":
+    s = "中国|国人|zg人|乾清宫"
+    test = "我是中国人"
+
+    search = WordsSearch()
+    search.SetKeywords(s.split('|'))
+
+    print("-----------------------------------  WordsSearch  -----------------------------------")
+
+    print("WordsSearch FindFirst is run.")
+    f = search.FindFirst(test)
+    if f["Keyword"] != "中国":
+        print("WordsSearch FindFirst is error.............................")
+
+    print("WordsSearch FindFirst is run.")
+    all = search.FindAll("乾清宫")
+    if all[0]["Keyword"] != "乾清宫":
+        print("WordsSearch FindFirst is error.............................")
+
+    print("WordsSearch FindAll is run.")
+    all = search.FindAll(test)
+    if all[0]["Keyword"] != "中国":
+        print("WordsSearch FindAll is error.............................")
+    if all[1]["Keyword"] != "国人":
+        print("WordsSearch FindAll is error.............................")
+    if all[0]["Start"] != 2:
+        print("WordsSearch FindAll is error.............................")
+    if all[0]["End"] != 3:
+        print("WordsSearch FindAll is error.............................")
+    if len(all) != 2:
+        print("WordsSearch FindAll is error.............................")
+
+    print("WordsSearch ContainsAny is run.")
+    b = search.ContainsAny(test)
+    if b == False:
+        print("WordsSearch ContainsAny is error.............................")
+
+    print("WordsSearch Replace  is run.")
+    txt = search.Replace(test)
+    if (txt != "我是***"):
+        print("WordsSearch Replace  is error.............................")
+
+    print("-----------------------------------  Test End  -----------------------------------")
\ No newline at end of file
diff --git a/app_chatgpt/views/ai_robot_views.xml b/app_chatgpt/views/ai_robot_views.xml
index 017010c8..735934d0 100644
--- a/app_chatgpt/views/ai_robot_views.xml
+++ b/app_chatgpt/views/ai_robot_views.xml
@@ -43,6 +43,10 @@
                             <field name="endpoint"/>
                             <field name="api_version"/>
                         </group>
+                        <group>
+                            <field name="is_filtering"/>
+                            <field name="sensitive_words" attrs="{'invisible': [('is_filtering', '=', False)]}"/>
+                        </group>
                     </group>
                 </sheet>
             </form>