h2ogpte 1.6.55rc1__py3-none-any.whl → 1.7.0rc2__py3-none-any.whl

h2ogpte/__init__.py

@@ -3,7 +3,7 @@ from h2ogpte.h2ogpte import H2OGPTE
 from h2ogpte.h2ogpte_async import H2OGPTEAsync
 from h2ogpte.session_async import SessionAsync
 
-__version__ = "1.6.55rc1"
+__version__ = "1.7.0rc2"
 
 __all__ = [
     "H2OGPTE",

h2ogpte/h2ogpte.py

@@ -470,25 +470,60 @@ class H2OGPTE(H2OGPTESyncBase):
         llm: str,
         extractor_schema: Dict[str, Any],
         description: str = "",
+        prompt: str = "",
+        pre_prompt_summary: str = "",
+        keep_intermediate_results: bool = False,
+        system_prompt: str = "",
+        max_num_chunks: int = 100,
+        vision: str = "auto",
+        vision_llm: str = "auto",
+        image_batch_image_prompt: str = "",
+        image_batch_final_prompt: str = "",
+        guardrails_settings: Optional[Dict] = None,
     ) -> Extractor:
         """Creates a new extractor.
 
         Args:
             name: Name of the extractor.
             llm: LLM to use for extraction.
-            extractor_schema: JSON schema defining the extraction structure.
+            extractor_schema: JSON schema defining the extraction structure.  If not empty, extractor will return data as JSON object.
             description: Optional description of the extractor.
+            prompt: Optional prompt text for the extractor. If combined with extractor_schema, prompt can modify the output, but not its format as it's set to be JSON object.
+            pre_prompt_summary: Optional pre-prompt summary text for the extractor.
+            keep_intermediate_results: Optional flag indicating whether to keep intermediate results during extraction.
+            system_prompt: Optional system prompt text for the extractor.
+            max_num_chunks: Optional maximum number of chunks to process.
+            vision: Optional vision mode setting.
+            vision_llm: Optional vision LLM model identifier.
+            image_batch_image_prompt: Optional image batch processing prompt.
+            image_batch_final_prompt: Optional final prompt for image batch processing.
+            guardrails_settings: Optional guardrails settings configuration as a dictionary.
 
         Returns:
             Extractor: Details of the newly created extractor.
         """
         header = self._get_auth_header()
 
+        # Convert guardrails_settings dict to GuardrailsSettings object if provided
+        guardrails_settings_obj = None
+        if guardrails_settings is not None:
+            guardrails_settings_obj = rest.GuardrailsSettings(**guardrails_settings)
+
         request_body = rest.ExtractorCreateRequest(
             name=name,
             description=description,
             llm=llm,
             schema=json.dumps(extractor_schema),
+            prompt=prompt,
+            pre_prompt_summary=pre_prompt_summary,
+            keep_intermediate_results=keep_intermediate_results,
+            system_prompt=system_prompt,
+            max_num_chunks=max_num_chunks,
+            vision=vision,
+            vision_llm=vision_llm,
+            image_batch_image_prompt=image_batch_image_prompt,
+            image_batch_final_prompt=image_batch_final_prompt,
+            guardrails_settings=guardrails_settings_obj,
         )
 
         with self._RESTClient(self) as rest_client:
@@ -1013,24 +1048,6 @@ class H2OGPTE(H2OGPTESyncBase):
             )
         return self._wait_for_completion(response.id, timeout=timeout)
 
-    def create_topic_model(
-        self,
-        collection_id: str,
-        timeout: Union[float, None] = None,
-    ) -> Job:
-        header = self._get_auth_header()
-        with self._RESTClient(self) as rest_client:
-            response = _rest_to_client_exceptions(
-                lambda: rest_client.model_api.create_topic_model_job(
-                    create_topic_model_job_request=rest.CreateTopicModelJobRequest(
-                        collection_id=collection_id,
-                    ),
-                    timeout=timeout,
-                    _headers=header,
-                )
-            )
-        return self._wait_for_completion(response.id, timeout=timeout)
-
     def delete_chat_sessions(
         self,
         chat_session_ids: Iterable[str],
@@ -1450,6 +1467,7 @@ class H2OGPTE(H2OGPTESyncBase):
         handwriting_check: Union[bool, None] = None,
         timeout: Union[float, None] = None,
         ingest_mode: Union[str, None] = None,
+        preserve_document_status: Union[bool, None] = None,
     ):
         """Import all documents from a collection into an existing collection
 
@@ -1486,6 +1504,10 @@ class H2OGPTE(H2OGPTESyncBase):
                 "standard" - Files will be ingested for use with RAG
                 "lite" - Files will be ingested for use with RAG, but minimal processing will be done, favoring ingest speed over accuracy
                 "agent_only" - Bypasses standard ingestion. Files can only be used with agents.
+            preserve_document_status:
+                Whether to preserve each document's original ingest mode (agent_only vs standard) when importing.
+                When True, documents with agent_only status remain agent_only in the target collection.
+                When False, all documents use the ingest_mode parameter uniformly.
         """
         header = self._get_auth_header()
         with self._RESTClient(self) as rest_client:
@@ -1504,6 +1526,7 @@ class H2OGPTE(H2OGPTESyncBase):
                     chunk_by_page=chunk_by_page,
                     handwriting_check=handwriting_check,
                     ingest_mode=ingest_mode,
+                    preserve_document_status=preserve_document_status,
                     timeout=timeout,
                     _headers=header,
                 )
@@ -2496,6 +2519,7 @@ class H2OGPTE(H2OGPTESyncBase):
         base_url: str,
         page_id: Union[str, List[str]],
         credentials: ConfluenceCredential,
+        include_attachments: Union[bool, None] = None,
         gen_doc_summaries: Union[bool, None] = None,
         gen_doc_questions: Union[bool, None] = None,
         audio_input_language: Union[str, None] = None,
@@ -2519,6 +2543,8 @@ class H2OGPTE(H2OGPTESyncBase):
                 The page id or ids of pages to be ingested.
             credentials:
                 The object with Confluence credentials.
+            include_attachments:
+                A flag indicating whether to also ingest attachments with the page.
             gen_doc_summaries:
                 Whether to auto-generate document summaries (uses LLM)
             gen_doc_questions:
@@ -2560,6 +2586,7 @@ class H2OGPTE(H2OGPTESyncBase):
                         page_ids=[page_id] if isinstance(page_id, str) else page_id,
                         credentials=rest.ConfluenceCredentials(**credentials.__dict__),
                         metadata=metadata,
+                        include_attachments=include_attachments,
                     ),
                     gen_doc_summaries=gen_doc_summaries,
                     gen_doc_questions=gen_doc_questions,
@@ -2741,7 +2768,20 @@ class H2OGPTE(H2OGPTESyncBase):
             handwriting_check:
                 Check pages for handwriting. Will use specialized models if handwriting is found.
             metadata:
-                Metadata to be associated with the document.
+                Dictionary mapping upload_ids to their metadata. Each key must be an upload_id
+                from the upload_ids list, and each value is a dictionary of metadata key-value
+                pairs to associate with that document.
+
+                Example::
+
+                    # Single document
+                    metadata = {upload_id: {"category": "reports", "year": "2024"}}
+
+                    # Multiple documents
+                    metadata = {
+                        upload_id_1: {"category": "reports"},
+                        upload_id_2: {"category": "invoices"}
+                    }
             timeout:
                 Timeout in seconds.
             ingest_mode:
@@ -3628,6 +3668,29 @@ class H2OGPTE(H2OGPTESyncBase):
             )
         return [GroupSharePermission(**d.to_dict()) for d in response]
 
+    def list_collection_public_permissions(self, collection_id: str) -> List[str]:
+        """Returns the public permissions for a given collection.
+
+        The returned list contains the permission strings that apply to
+        public access of the collection.
+
+        Args:
+            collection_id:
+                ID of the collection to inspect.
+
+        Returns:
+            list of str: Public permissions list for the given collection.
+        """
+        header = self._get_auth_header()
+        with self._RESTClient(self) as rest_client:
+            response = _rest_to_client_exceptions(
+                lambda: rest_client.collection_api.list_collection_public_permissions(
+                    collection_id=collection_id,
+                    _headers=header,
+                )
+            )
+        return response
+
     def list_users(self, offset: int, limit: int) -> List[User]:
         """List system users.
 
@@ -4514,6 +4577,11 @@ class H2OGPTE(H2OGPTESyncBase):
                         Requires 1 LLM or Agent call.
                     :code:`"agent_only"` Agent Only - Answer the query with only original files passed to agent.
                         Requires 1 Agent call.
+                    :code:`"agentic_rag"` Agentic RAG - Agent with RAG tool that retrieves and answers from collection.
+                        Requires 1 Agent call with RAG tool execution.
+                    :code:`"rlm_rag"` RLM RAG - Agent programmatically analyzes documents using Python code
+                        execution and sub-LLM calls. Best for complex multi-hop reasoning over large documents.
+                        Requires 1 Agent call.
                     :code:`"rag"` RAG (Retrieval Augmented Generation) - Use supporting document contexts
                         to answer the query. Requires 1 LLM or Agent call.
                     :code:`"hyde1"` LLM Only + RAG composite - HyDE RAG (Hypothetical Document Embedding).
@@ -7132,6 +7200,41 @@ class H2OGPTE(H2OGPTESyncBase):
     def add_custom_agent_tool(
         self, tool_type: str, tool_args: dict, custom_tool_path: Optional[str] = None
     ) -> list:
+        """Adds a custom agent tool.
+
+        Args:
+            tool_type: The type of custom tool being added. Valid values:
+                - 'local_mcp': Model Context Protocol server running locally
+                - 'remote_mcp': Model Context Protocol server running remotely
+                - 'browser_action': Custom browser automation actions
+                - 'general_code': General purpose code execution tools
+
+            tool_args: Dictionary containing tool-specific arguments. Structure varies by tool_type:
+
+                For 'remote_mcp':
+                {
+                    "mcp_config_json": "JSON string with MCP server configuration",
+                    "enable_by_default": True/False (optional, defaults to True)
+                }
+
+                For 'local_mcp', 'browser_action', and 'general_code':
+                {
+                    "tool_name": "string (optional, defaults to filename without extension)",
+                    "description": "string (optional, tool description)",
+                    "enable_by_default": True/False (optional, defaults to True),
+                    "should_unzip": True/False (optional, for general_code .zip files only),
+                    "tool_usage_mode": ["runner", "creator"] (optional list of strings, for remote_mcp)
+                }
+
+            custom_tool_path: Path to the tool file to upload (optional). Requirements vary by tool_type:
+                - 'local_mcp': .zip file containing MCP server code
+                - 'remote_mcp': Optional .json file with MCP configuration
+                - 'browser_action': .py file (must start with 'browser_') or .zip containing browser action scripts
+                - 'general_code': .py or .zip file with custom code
+
+        Returns:
+            list: List of created custom agent tool IDs
+        """
         header = self._get_auth_header()
         custom_tool_path = str(custom_tool_path) if custom_tool_path else None
         with self._RESTClient(self) as rest_client:
@@ -7189,6 +7292,96 @@ class H2OGPTE(H2OGPTESyncBase):
             )
         return response.agent_custom_tool_id
 
+    def pause_chat(self, question_id: str) -> Result:
+        """Pause a streaming chat response.
+
+        Args:
+            question_id: The ID of the chat message/question to pause.
+
+        Returns:
+            Result: Status of the pause operation.
+
+        Raises:
+            Exception: If the user is not authorized to pause this chat or if the operation fails.
+        """
+        header = self._get_auth_header()
+        with self._RESTClient(self) as rest_client:
+            _rest_to_client_exceptions(
+                lambda: rest_client.chat_api.pause_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
+    def resume_chat(self, question_id: str) -> Result:
+        """Resume a paused chat response.
+
+        Args:
+            question_id: The ID of the chat message/question to resume.
+
+        Returns:
+            Result: Status of the resume operation.
+
+        Raises:
+            Exception: If the user is not authorized to resume this chat or if the operation fails.
+        """
+        header = self._get_auth_header()
+        with self._RESTClient(self) as rest_client:
+            _rest_to_client_exceptions(
+                lambda: rest_client.chat_api.resume_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
+    def finish_chat(self, question_id: str) -> Result:
+        """Signal the LLM to complete its current thought and finish naturally.
+
+        Unlike stop_chat which immediately halts response generation, finish_chat allows
+        the LLM to complete its current thought naturally, providing a more coherent ending.
+
+        Args:
+            question_id: The ID of the chat message/question to finish gracefully.
+
+        Returns:
+            Result: Status of the finish operation.
+
+        Raises:
+            Exception: If the user is not authorized to finish this chat or if the operation fails.
+        """
+        header = self._get_auth_header()
+        with self._RESTClient(self) as rest_client:
+            _rest_to_client_exceptions(
+                lambda: rest_client.chat_api.finish_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
+    def stop_chat(self, question_id: str) -> Result:
+        """Immediately stop/cancel a streaming chat response.
+
+        This will immediately halt response generation, which may result in an incomplete
+        sentence or thought. For a more graceful termination, use finish_chat instead.
+
+        Args:
+            question_id: The ID of the chat message/question to stop immediately.
+
+        Returns:
+            Result: Status of the cancel operation.
+
+        Raises:
+            Exception: If the user is not authorized to cancel this chat or if the operation fails.
+        """
+        header = self._get_auth_header()
+        with self._RESTClient(self) as rest_client:
+            _rest_to_client_exceptions(
+                lambda: rest_client.chat_api.stop_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
     def get_custom_agent_tools(self) -> List[dict]:
         """Gets all custom agent tools for the current user.
 

h2ogpte/h2ogpte_async.py

@@ -676,25 +676,60 @@ class H2OGPTEAsync:
         llm: str,
         extractor_schema: Dict[str, Any],
         description: str = "",
+        prompt: str = "",
+        pre_prompt_summary: str = "",
+        keep_intermediate_results: bool = False,
+        system_prompt: str = "",
+        max_num_chunks: int = 100,
+        vision: str = "auto",
+        vision_llm: str = "auto",
+        image_batch_image_prompt: str = "",
+        image_batch_final_prompt: str = "",
+        guardrails_settings: Optional[Dict] = None,
     ) -> Extractor:
         """Creates a new extractor.
 
         Args:
             name: Name of the extractor.
             llm: LLM to use for extraction.
-            extractor_schema: JSON schema defining the extraction structure.
+            extractor_schema: JSON schema defining the extraction structure.  If not empty, extractor will return data as JSON object.
             description: Optional description of the extractor.
+            prompt: Optional prompt text for the extractor. If combined with extractor_schema, prompt can modify the output, but not its format as it's set to be JSON object.
+            pre_prompt_summary: Optional pre-prompt summary text for the extractor.
+            keep_intermediate_results: Optional flag indicating whether to keep intermediate results during extraction.
+            system_prompt: Optional system prompt text for the extractor.
+            max_num_chunks: Optional maximum number of chunks to process.
+            vision: Optional vision mode setting.
+            vision_llm: Optional vision LLM model identifier.
+            image_batch_image_prompt: Optional image batch processing prompt.
+            image_batch_final_prompt: Optional final prompt for image batch processing.
+            guardrails_settings: Optional guardrails settings configuration as a dictionary.
 
         Returns:
             Extractor: Details of the newly created extractor.
         """
         header = await self._get_auth_header()
 
+        # Convert guardrails_settings dict to GuardrailsSettings object if provided
+        guardrails_settings_obj = None
+        if guardrails_settings is not None:
+            guardrails_settings_obj = rest.GuardrailsSettings(**guardrails_settings)
+
         request_body = rest.ExtractorCreateRequest(
             name=name,
             description=description,
             llm=llm,
             schema=json.dumps(extractor_schema),
+            prompt=prompt,
+            pre_prompt_summary=pre_prompt_summary,
+            keep_intermediate_results=keep_intermediate_results,
+            system_prompt=system_prompt,
+            max_num_chunks=max_num_chunks,
+            vision=vision,
+            vision_llm=vision_llm,
+            image_batch_image_prompt=image_batch_image_prompt,
+            image_batch_final_prompt=image_batch_final_prompt,
+            guardrails_settings=guardrails_settings_obj,
         )
 
         async with self._RESTClient(self) as rest_client:
@@ -1213,24 +1248,6 @@ class H2OGPTEAsync:
             )
         return await self._wait_for_completion(response.id, timeout=timeout)
 
-    async def create_topic_model(
-        self,
-        collection_id: str,
-        timeout: Union[float, None] = None,
-    ) -> Job:
-        header = await self._get_auth_header()
-        async with self._RESTClient(self) as rest_client:
-            response = await _rest_to_client_exceptions(
-                rest_client.model_api.create_topic_model_job(
-                    create_topic_model_job_request=rest.CreateTopicModelJobRequest(
-                        collection_id=collection_id,
-                    ),
-                    timeout=timeout,
-                    _headers=header,
-                )
-            )
-        return await self._wait_for_completion(response.id, timeout=timeout)
-
     async def delete_chat_sessions(
         self,
         chat_session_ids: Iterable[str],
@@ -1650,6 +1667,7 @@ class H2OGPTEAsync:
         handwriting_check: Union[bool, None] = None,
         timeout: Union[float, None] = None,
         ingest_mode: Union[str, None] = None,
+        preserve_document_status: Union[bool, None] = None,
     ):
         """Import all documents from a collection into an existing collection
 
@@ -1686,6 +1704,10 @@ class H2OGPTEAsync:
                 "standard" - Files will be ingested for use with RAG
                 "lite" - Files will be ingested for use with RAG, but minimal processing will be done, favoring ingest speed over accuracy
                 "agent_only" - Bypasses standard ingestion. Files can only be used with agents.
+            preserve_document_status:
+                Whether to preserve each document's original ingest mode (agent_only vs standard) when importing.
+                When True, documents with agent_only status remain agent_only in the target collection.
+                When False, all documents use the ingest_mode parameter uniformly.
         """
         header = await self._get_auth_header()
         async with self._RESTClient(self) as rest_client:
@@ -1704,6 +1726,7 @@ class H2OGPTEAsync:
                     chunk_by_page=chunk_by_page,
                     handwriting_check=handwriting_check,
                     ingest_mode=ingest_mode,
+                    preserve_document_status=preserve_document_status,
                     timeout=timeout,
                     _headers=header,
                 )
@@ -2698,6 +2721,7 @@ class H2OGPTEAsync:
         base_url: str,
         page_id: Union[str, List[str]],
         credentials: ConfluenceCredential,
+        include_attachments: Union[bool, None] = None,
         gen_doc_summaries: Union[bool, None] = None,
         gen_doc_questions: Union[bool, None] = None,
         audio_input_language: Union[str, None] = None,
@@ -2721,6 +2745,8 @@ class H2OGPTEAsync:
                 The page id or ids of pages to be ingested.
             credentials:
                 The object with Confluence credentials.
+            include_attachments:
+                A flag indicating whether to also ingest attachments with the page.
             gen_doc_summaries:
                 Whether to auto-generate document summaries (uses LLM)
             gen_doc_questions:
@@ -2762,6 +2788,7 @@ class H2OGPTEAsync:
                         page_ids=[page_id] if isinstance(page_id, str) else page_id,
                         credentials=rest.ConfluenceCredentials(**credentials.__dict__),
                         metadata=metadata,
+                        include_attachments=include_attachments,
                     ),
                     gen_doc_summaries=gen_doc_summaries,
                     gen_doc_questions=gen_doc_questions,
@@ -2939,7 +2966,20 @@ class H2OGPTEAsync:
             handwriting_check:
                 Check pages for handwriting. Will use specialized models if handwriting is found.
             metadata:
-                Metadata to be associated with the document.
+                Dictionary mapping upload_ids to their metadata. Each key must be an upload_id
+                from the upload_ids list, and each value is a dictionary of metadata key-value
+                pairs to associate with that document.
+
+                Example::
+
+                    # Single document
+                    metadata = {upload_id: {"category": "reports", "year": "2024"}}
+
+                    # Multiple documents
+                    metadata = {
+                        upload_id_1: {"category": "reports"},
+                        upload_id_2: {"category": "invoices"}
+                    }
             timeout:
                 Timeout in seconds.
             ingest_mode:
@@ -3830,6 +3870,29 @@ class H2OGPTEAsync:
             )
         return [GroupSharePermission(**d.to_dict()) for d in response]
 
+    async def list_collection_public_permissions(self, collection_id: str) -> List[str]:
+        """Returns the public permissions for a given collection.
+
+        The returned list contains the permission strings that apply to
+        public access of the collection.
+
+        Args:
+            collection_id:
+                ID of the collection to inspect.
+
+        Returns:
+            list of str: Public permissions list for the given collection.
+        """
+        header = await self._get_auth_header()
+        async with self._RESTClient(self) as rest_client:
+            response = await _rest_to_client_exceptions(
+                rest_client.collection_api.list_collection_public_permissions(
+                    collection_id=collection_id,
+                    _headers=header,
+                )
+            )
+        return response
+
     async def list_users(self, offset: int, limit: int) -> List[User]:
         """List system users.
 
@@ -4722,6 +4785,11 @@ class H2OGPTEAsync:
                         Requires 1 LLM or Agent call.
                     :code:`"agent_only"` Agent Only - Answer the query with only original files passed to agent.
                         Requires 1 Agent call.
+                    :code:`"agentic_rag"` Agentic RAG - Agent with RAG tool that retrieves and answers from collection.
+                        Requires 1 Agent call with RAG tool execution.
+                    :code:`"rlm_rag"` RLM RAG - Agent programmatically analyzes documents using Python code
+                        execution and sub-LLM calls. Best for complex multi-hop reasoning over large documents.
+                        Requires 1 Agent call.
                     :code:`"rag"` RAG (Retrieval Augmented Generation) - Use supporting document contexts
                         to answer the query. Requires 1 LLM or Agent call.
                     :code:`"hyde1"` LLM Only + RAG composite - HyDE RAG (Hypothetical Document Embedding).
@@ -7387,6 +7455,41 @@ class H2OGPTEAsync:
     async def add_custom_agent_tool(
         self, tool_type: str, tool_args: dict, custom_tool_path: Optional[str] = None
     ) -> list:
+        """Adds a custom agent tool.
+
+        Args:
+            tool_type: The type of custom tool being added. Valid values:
+                - 'local_mcp': Model Context Protocol server running locally
+                - 'remote_mcp': Model Context Protocol server running remotely
+                - 'browser_action': Custom browser automation actions
+                - 'general_code': General purpose code execution tools
+
+            tool_args: Dictionary containing tool-specific arguments. Structure varies by tool_type:
+
+                For 'remote_mcp':
+                {
+                    "mcp_config_json": "JSON string with MCP server configuration",
+                    "enable_by_default": True/False (optional, defaults to True)
+                }
+
+                For 'local_mcp', 'browser_action', and 'general_code':
+                {
+                    "tool_name": "string (optional, defaults to filename without extension)",
+                    "description": "string (optional, tool description)",
+                    "enable_by_default": True/False (optional, defaults to True),
+                    "should_unzip": True/False (optional, for general_code .zip files only),
+                    "tool_usage_mode": ["runner", "creator"] (optional list of strings, for remote_mcp)
+                }
+
+            custom_tool_path: Path to the tool file to upload (optional). Requirements vary by tool_type:
+                - 'local_mcp': .zip file containing MCP server code
+                - 'remote_mcp': Optional .json file with MCP configuration
+                - 'browser_action': .py file (must start with 'browser_') or .zip containing browser action scripts
+                - 'general_code': .py or .zip file with custom code
+
+        Returns:
+            list: List of created custom agent tool IDs
+        """
         header = await self._get_auth_header()
         custom_tool_path = str(custom_tool_path) if custom_tool_path else None
         async with self._RESTClient(self) as rest_client:
@@ -7444,6 +7547,96 @@ class H2OGPTEAsync:
             )
         return response.agent_custom_tool_id
 
+    async def pause_chat(self, question_id: str) -> Result:
+        """Pause a streaming chat response.
+
+        Args:
+            question_id: The ID of the chat message/question to pause.
+
+        Returns:
+            Result: Status of the pause operation.
+
+        Raises:
+            Exception: If the user is not authorized to pause this chat or if the operation fails.
+        """
+        header = await self._get_auth_header()
+        async with self._RESTClient(self) as rest_client:
+            await _rest_to_client_exceptions(
+                rest_client.chat_api.pause_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
+    async def resume_chat(self, question_id: str) -> Result:
+        """Resume a paused chat response.
+
+        Args:
+            question_id: The ID of the chat message/question to resume.
+
+        Returns:
+            Result: Status of the resume operation.
+
+        Raises:
+            Exception: If the user is not authorized to resume this chat or if the operation fails.
+        """
+        header = await self._get_auth_header()
+        async with self._RESTClient(self) as rest_client:
+            await _rest_to_client_exceptions(
+                rest_client.chat_api.resume_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
+    async def finish_chat(self, question_id: str) -> Result:
+        """Signal the LLM to complete its current thought and finish naturally.
+
+        Unlike stop_chat which immediately halts response generation, finish_chat allows
+        the LLM to complete its current thought naturally, providing a more coherent ending.
+
+        Args:
+            question_id: The ID of the chat message/question to finish gracefully.
+
+        Returns:
+            Result: Status of the finish operation.
+
+        Raises:
+            Exception: If the user is not authorized to finish this chat or if the operation fails.
+        """
+        header = await self._get_auth_header()
+        async with self._RESTClient(self) as rest_client:
+            await _rest_to_client_exceptions(
+                rest_client.chat_api.finish_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
+    async def stop_chat(self, question_id: str) -> Result:
+        """Immediately stop/cancel a streaming chat response.
+
+        This will immediately halt response generation, which may result in an incomplete
+        sentence or thought. For a more graceful termination, use finish_chat instead.
+
+        Args:
+            question_id: The ID of the chat message/question to stop immediately.
+
+        Returns:
+            Result: Status of the cancel operation.
+
+        Raises:
+            Exception: If the user is not authorized to cancel this chat or if the operation fails.
+        """
+        header = await self._get_auth_header()
+        async with self._RESTClient(self) as rest_client:
+            await _rest_to_client_exceptions(
+                rest_client.chat_api.stop_chat_message(
+                    question_id=question_id, _headers=header
+                )
+            )
+        return Result(status="completed")
+
     async def get_custom_agent_tools(self) -> List[dict]:
         """Gets all custom agent tools for the current user.