h2ogpte 1.6.42__py3-none-any.whl → 1.6.43rc2__py3-none-any.whl

h2ogpte/rest_sync/api/prompt_templates_api.py

@@ -24,8 +24,8 @@ from h2ogpte.rest_sync.models.group_share_permission import GroupSharePermission
 from h2ogpte.rest_sync.models.prompt_template import PromptTemplate
 from h2ogpte.rest_sync.models.prompt_template_base import PromptTemplateBase
 from h2ogpte.rest_sync.models.prompt_template_create_request import PromptTemplateCreateRequest
-from h2ogpte.rest_sync.models.reset_and_share_prompt_template_request import ResetAndSharePromptTemplateRequest
-from h2ogpte.rest_sync.models.reset_and_share_prompt_template_with_groups_request import ResetAndSharePromptTemplateWithGroupsRequest
+from h2ogpte.rest_sync.models.reset_and_share_request import ResetAndShareRequest
+from h2ogpte.rest_sync.models.reset_and_share_with_groups_request import ResetAndShareWithGroupsRequest
 from h2ogpte.rest_sync.models.share_permission import SharePermission
 from h2ogpte.rest_sync.models.update_default_prompt_template_visibility_request import UpdateDefaultPromptTemplateVisibilityRequest
 from h2ogpte.rest_sync.models.update_prompt_template_privacy_request import UpdatePromptTemplatePrivacyRequest
@@ -2589,7 +2589,7 @@ class PromptTemplatesApi:
     def reset_and_share_prompt_template(
         self,
         prompt_template_id: Annotated[StrictStr, Field(description="Id of a prompt template.")],
-        reset_and_share_prompt_template_request: Annotated[ResetAndSharePromptTemplateRequest, Field(description="List of usernames the prompt template should be shared with.")],
+        reset_and_share_request: Annotated[ResetAndShareRequest, Field(description="List of usernames the prompt template should be shared with.")],
         _request_timeout: Union[
             None,
             Annotated[StrictFloat, Field(gt=0)],
@@ -2609,8 +2609,8 @@ class PromptTemplatesApi:
 
         :param prompt_template_id: Id of a prompt template. (required)
         :type prompt_template_id: str
-        :param reset_and_share_prompt_template_request: List of usernames the prompt template should be shared with. (required)
-        :type reset_and_share_prompt_template_request: ResetAndSharePromptTemplateRequest
+        :param reset_and_share_request: List of usernames the prompt template should be shared with. (required)
+        :type reset_and_share_request: ResetAndShareRequest
         :param _request_timeout: timeout setting for this request. If one
                                  number provided, it will be total request
                                  timeout. It can also be a pair (tuple) of
@@ -2635,7 +2635,7 @@ class PromptTemplatesApi:
 
         _param = self._reset_and_share_prompt_template_serialize(
             prompt_template_id=prompt_template_id,
-            reset_and_share_prompt_template_request=reset_and_share_prompt_template_request,
+            reset_and_share_request=reset_and_share_request,
             _request_auth=_request_auth,
             _content_type=_content_type,
             _headers=_headers,
@@ -2661,7 +2661,7 @@ class PromptTemplatesApi:
     def reset_and_share_prompt_template_with_http_info(
         self,
         prompt_template_id: Annotated[StrictStr, Field(description="Id of a prompt template.")],
-        reset_and_share_prompt_template_request: Annotated[ResetAndSharePromptTemplateRequest, Field(description="List of usernames the prompt template should be shared with.")],
+        reset_and_share_request: Annotated[ResetAndShareRequest, Field(description="List of usernames the prompt template should be shared with.")],
         _request_timeout: Union[
             None,
             Annotated[StrictFloat, Field(gt=0)],
@@ -2681,8 +2681,8 @@ class PromptTemplatesApi:
 
         :param prompt_template_id: Id of a prompt template. (required)
         :type prompt_template_id: str
-        :param reset_and_share_prompt_template_request: List of usernames the prompt template should be shared with. (required)
-        :type reset_and_share_prompt_template_request: ResetAndSharePromptTemplateRequest
+        :param reset_and_share_request: List of usernames the prompt template should be shared with. (required)
+        :type reset_and_share_request: ResetAndShareRequest
         :param _request_timeout: timeout setting for this request. If one
                                  number provided, it will be total request
                                  timeout. It can also be a pair (tuple) of
@@ -2707,7 +2707,7 @@ class PromptTemplatesApi:
 
         _param = self._reset_and_share_prompt_template_serialize(
             prompt_template_id=prompt_template_id,
-            reset_and_share_prompt_template_request=reset_and_share_prompt_template_request,
+            reset_and_share_request=reset_and_share_request,
             _request_auth=_request_auth,
             _content_type=_content_type,
             _headers=_headers,
@@ -2733,7 +2733,7 @@ class PromptTemplatesApi:
     def reset_and_share_prompt_template_without_preload_content(
         self,
         prompt_template_id: Annotated[StrictStr, Field(description="Id of a prompt template.")],
-        reset_and_share_prompt_template_request: Annotated[ResetAndSharePromptTemplateRequest, Field(description="List of usernames the prompt template should be shared with.")],
+        reset_and_share_request: Annotated[ResetAndShareRequest, Field(description="List of usernames the prompt template should be shared with.")],
         _request_timeout: Union[
             None,
             Annotated[StrictFloat, Field(gt=0)],
@@ -2753,8 +2753,8 @@ class PromptTemplatesApi:
 
         :param prompt_template_id: Id of a prompt template. (required)
         :type prompt_template_id: str
-        :param reset_and_share_prompt_template_request: List of usernames the prompt template should be shared with. (required)
-        :type reset_and_share_prompt_template_request: ResetAndSharePromptTemplateRequest
+        :param reset_and_share_request: List of usernames the prompt template should be shared with. (required)
+        :type reset_and_share_request: ResetAndShareRequest
         :param _request_timeout: timeout setting for this request. If one
                                  number provided, it will be total request
                                  timeout. It can also be a pair (tuple) of
@@ -2779,7 +2779,7 @@ class PromptTemplatesApi:
 
         _param = self._reset_and_share_prompt_template_serialize(
             prompt_template_id=prompt_template_id,
-            reset_and_share_prompt_template_request=reset_and_share_prompt_template_request,
+            reset_and_share_request=reset_and_share_request,
             _request_auth=_request_auth,
             _content_type=_content_type,
             _headers=_headers,
@@ -2800,7 +2800,7 @@ class PromptTemplatesApi:
     def _reset_and_share_prompt_template_serialize(
         self,
         prompt_template_id,
-        reset_and_share_prompt_template_request,
+        reset_and_share_request,
         _request_auth,
         _content_type,
         _headers,
@@ -2828,8 +2828,8 @@ class PromptTemplatesApi:
         # process the header parameters
         # process the form parameters
         # process the body parameter
-        if reset_and_share_prompt_template_request is not None:
-            _body_params = reset_and_share_prompt_template_request
+        if reset_and_share_request is not None:
+            _body_params = reset_and_share_request
 
 
         # set the HTTP header `Accept`
@@ -2881,7 +2881,7 @@ class PromptTemplatesApi:
     def reset_and_share_prompt_template_with_groups(
         self,
         prompt_template_id: Annotated[StrictStr, Field(description="Id of a prompt template.")],
-        reset_and_share_prompt_template_with_groups_request: Annotated[ResetAndSharePromptTemplateWithGroupsRequest, Field(description="List of group ids the prompt template should be shared with.")],
+        reset_and_share_with_groups_request: Annotated[ResetAndShareWithGroupsRequest, Field(description="List of group ids the prompt template should be shared with.")],
         _request_timeout: Union[
             None,
             Annotated[StrictFloat, Field(gt=0)],
@@ -2901,8 +2901,8 @@ class PromptTemplatesApi:
 
         :param prompt_template_id: Id of a prompt template. (required)
         :type prompt_template_id: str
-        :param reset_and_share_prompt_template_with_groups_request: List of group ids the prompt template should be shared with. (required)
-        :type reset_and_share_prompt_template_with_groups_request: ResetAndSharePromptTemplateWithGroupsRequest
+        :param reset_and_share_with_groups_request: List of group ids the prompt template should be shared with. (required)
+        :type reset_and_share_with_groups_request: ResetAndShareWithGroupsRequest
         :param _request_timeout: timeout setting for this request. If one
                                  number provided, it will be total request
                                  timeout. It can also be a pair (tuple) of
@@ -2927,7 +2927,7 @@ class PromptTemplatesApi:
 
         _param = self._reset_and_share_prompt_template_with_groups_serialize(
             prompt_template_id=prompt_template_id,
-            reset_and_share_prompt_template_with_groups_request=reset_and_share_prompt_template_with_groups_request,
+            reset_and_share_with_groups_request=reset_and_share_with_groups_request,
             _request_auth=_request_auth,
             _content_type=_content_type,
             _headers=_headers,
@@ -2953,7 +2953,7 @@ class PromptTemplatesApi:
     def reset_and_share_prompt_template_with_groups_with_http_info(
         self,
         prompt_template_id: Annotated[StrictStr, Field(description="Id of a prompt template.")],
-        reset_and_share_prompt_template_with_groups_request: Annotated[ResetAndSharePromptTemplateWithGroupsRequest, Field(description="List of group ids the prompt template should be shared with.")],
+        reset_and_share_with_groups_request: Annotated[ResetAndShareWithGroupsRequest, Field(description="List of group ids the prompt template should be shared with.")],
         _request_timeout: Union[
             None,
             Annotated[StrictFloat, Field(gt=0)],
@@ -2973,8 +2973,8 @@ class PromptTemplatesApi:
 
         :param prompt_template_id: Id of a prompt template. (required)
         :type prompt_template_id: str
-        :param reset_and_share_prompt_template_with_groups_request: List of group ids the prompt template should be shared with. (required)
-        :type reset_and_share_prompt_template_with_groups_request: ResetAndSharePromptTemplateWithGroupsRequest
+        :param reset_and_share_with_groups_request: List of group ids the prompt template should be shared with. (required)
+        :type reset_and_share_with_groups_request: ResetAndShareWithGroupsRequest
         :param _request_timeout: timeout setting for this request. If one
                                  number provided, it will be total request
                                  timeout. It can also be a pair (tuple) of
@@ -2999,7 +2999,7 @@ class PromptTemplatesApi:
 
         _param = self._reset_and_share_prompt_template_with_groups_serialize(
             prompt_template_id=prompt_template_id,
-            reset_and_share_prompt_template_with_groups_request=reset_and_share_prompt_template_with_groups_request,
+            reset_and_share_with_groups_request=reset_and_share_with_groups_request,
             _request_auth=_request_auth,
             _content_type=_content_type,
             _headers=_headers,
@@ -3025,7 +3025,7 @@ class PromptTemplatesApi:
     def reset_and_share_prompt_template_with_groups_without_preload_content(
         self,
         prompt_template_id: Annotated[StrictStr, Field(description="Id of a prompt template.")],
-        reset_and_share_prompt_template_with_groups_request: Annotated[ResetAndSharePromptTemplateWithGroupsRequest, Field(description="List of group ids the prompt template should be shared with.")],
+        reset_and_share_with_groups_request: Annotated[ResetAndShareWithGroupsRequest, Field(description="List of group ids the prompt template should be shared with.")],
         _request_timeout: Union[
             None,
             Annotated[StrictFloat, Field(gt=0)],
@@ -3045,8 +3045,8 @@ class PromptTemplatesApi:
 
         :param prompt_template_id: Id of a prompt template. (required)
         :type prompt_template_id: str
-        :param reset_and_share_prompt_template_with_groups_request: List of group ids the prompt template should be shared with. (required)
-        :type reset_and_share_prompt_template_with_groups_request: ResetAndSharePromptTemplateWithGroupsRequest
+        :param reset_and_share_with_groups_request: List of group ids the prompt template should be shared with. (required)
+        :type reset_and_share_with_groups_request: ResetAndShareWithGroupsRequest
         :param _request_timeout: timeout setting for this request. If one
                                  number provided, it will be total request
                                  timeout. It can also be a pair (tuple) of
@@ -3071,7 +3071,7 @@ class PromptTemplatesApi:
 
         _param = self._reset_and_share_prompt_template_with_groups_serialize(
             prompt_template_id=prompt_template_id,
-            reset_and_share_prompt_template_with_groups_request=reset_and_share_prompt_template_with_groups_request,
+            reset_and_share_with_groups_request=reset_and_share_with_groups_request,
             _request_auth=_request_auth,
             _content_type=_content_type,
             _headers=_headers,
@@ -3092,7 +3092,7 @@ class PromptTemplatesApi:
     def _reset_and_share_prompt_template_with_groups_serialize(
         self,
         prompt_template_id,
-        reset_and_share_prompt_template_with_groups_request,
+        reset_and_share_with_groups_request,
         _request_auth,
         _content_type,
         _headers,
@@ -3120,8 +3120,8 @@ class PromptTemplatesApi:
         # process the header parameters
         # process the form parameters
         # process the body parameter
-        if reset_and_share_prompt_template_with_groups_request is not None:
-            _body_params = reset_and_share_prompt_template_with_groups_request
+        if reset_and_share_with_groups_request is not None:
+            _body_params = reset_and_share_with_groups_request
 
 
         # set the HTTP header `Accept`

h2ogpte/rest_sync/api_client.py

@@ -90,7 +90,7 @@ class ApiClient:
             self.default_headers[header_name] = header_value
         self.cookie = cookie
         # Set default User-Agent.
-        self.user_agent = 'OpenAPI-Generator/1.6.42/python'
+        self.user_agent = 'OpenAPI-Generator/1.6.43-dev2/python'
         self.client_side_validation = configuration.client_side_validation
 
     def __enter__(self):

h2ogpte/rest_sync/configuration.py

@@ -503,7 +503,7 @@ class Configuration:
                "OS: {env}\n"\
                "Python Version: {pyversion}\n"\
                "Version of the API: v1.0.0\n"\
-               "SDK Package Version: 1.6.42".\
+               "SDK Package Version: 1.6.43-dev2".\
                format(env=sys.platform, pyversion=sys.version)
 
     def get_host_settings(self) -> List[HostSetting]:

h2ogpte/rest_sync/models/__init__.py

@@ -51,6 +51,7 @@ from h2ogpte.rest_sync.models.count_with_queue_details import CountWithQueueDeta
 from h2ogpte.rest_sync.models.create_agent_key_request import CreateAgentKeyRequest
 from h2ogpte.rest_sync.models.create_agent_tool_key_associations_request import CreateAgentToolKeyAssociationsRequest
 from h2ogpte.rest_sync.models.create_agent_tool_request import CreateAgentToolRequest
+from h2ogpte.rest_sync.models.create_chat_session_request import CreateChatSessionRequest
 from h2ogpte.rest_sync.models.create_import_collection_to_collection_job_request import CreateImportCollectionToCollectionJobRequest
 from h2ogpte.rest_sync.models.create_insert_document_to_collection_job_request import CreateInsertDocumentToCollectionJobRequest
 from h2ogpte.rest_sync.models.create_secret201_response import CreateSecret201Response
@@ -106,8 +107,8 @@ from h2ogpte.rest_sync.models.prompt_template_create_request import PromptTempla
 from h2ogpte.rest_sync.models.qa_feedback import QAFeedback
 from h2ogpte.rest_sync.models.question_request import QuestionRequest
 from h2ogpte.rest_sync.models.queue_details import QueueDetails
-from h2ogpte.rest_sync.models.reset_and_share_prompt_template_request import ResetAndSharePromptTemplateRequest
-from h2ogpte.rest_sync.models.reset_and_share_prompt_template_with_groups_request import ResetAndSharePromptTemplateWithGroupsRequest
+from h2ogpte.rest_sync.models.reset_and_share_request import ResetAndShareRequest
+from h2ogpte.rest_sync.models.reset_and_share_with_groups_request import ResetAndShareWithGroupsRequest
 from h2ogpte.rest_sync.models.role_create_request import RoleCreateRequest
 from h2ogpte.rest_sync.models.role_info import RoleInfo
 from h2ogpte.rest_sync.models.roles_reset_request import RolesResetRequest
@@ -130,9 +131,11 @@ from h2ogpte.rest_sync.models.update_agent_tool_preference_request import Update
 from h2ogpte.rest_sync.models.update_collection_expiry_date_request import UpdateCollectionExpiryDateRequest
 from h2ogpte.rest_sync.models.update_collection_inactivity_interval_request import UpdateCollectionInactivityIntervalRequest
 from h2ogpte.rest_sync.models.update_collection_privacy_request import UpdateCollectionPrivacyRequest
+from h2ogpte.rest_sync.models.update_collection_workspace_request import UpdateCollectionWorkspaceRequest
 from h2ogpte.rest_sync.models.update_custom_agent_tool200_response import UpdateCustomAgentTool200Response
 from h2ogpte.rest_sync.models.update_custom_agent_tool_request import UpdateCustomAgentToolRequest
 from h2ogpte.rest_sync.models.update_default_prompt_template_visibility_request import UpdateDefaultPromptTemplateVisibilityRequest
+from h2ogpte.rest_sync.models.update_extractor_privacy_request import UpdateExtractorPrivacyRequest
 from h2ogpte.rest_sync.models.update_prompt_template_privacy_request import UpdatePromptTemplatePrivacyRequest
 from h2ogpte.rest_sync.models.update_qa_feedback_request import UpdateQAFeedbackRequest
 from h2ogpte.rest_sync.models.update_secret_request import UpdateSecretRequest

h2ogpte/rest_sync/models/chat_completion.py

@@ -17,7 +17,7 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, StrictStr
+from pydantic import BaseModel, ConfigDict, Field, StrictStr
 from typing import Any, ClassVar, Dict, List
 from typing import Optional, Set
 from typing_extensions import Self
@@ -26,8 +26,9 @@ class ChatCompletion(BaseModel):
     """
     ChatCompletion
     """ # noqa: E501
+    message_id: StrictStr = Field(description="Id of the chat completion message")
     body: StrictStr
-    __properties: ClassVar[List[str]] = ["body"]
+    __properties: ClassVar[List[str]] = ["message_id", "body"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -80,6 +81,7 @@ class ChatCompletion(BaseModel):
             return cls.model_validate(obj)
 
         _obj = cls.model_validate({
+            "message_id": obj.get("message_id"),
             "body": obj.get("body")
         })
         return _obj

h2ogpte/rest_sync/models/chat_completion_delta.py

@@ -17,8 +17,8 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, StrictBool, StrictStr
-from typing import Any, ClassVar, Dict, List
+from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictStr
+from typing import Any, ClassVar, Dict, List, Optional
 from typing import Optional, Set
 from typing_extensions import Self
 
@@ -26,9 +26,10 @@ class ChatCompletionDelta(BaseModel):
     """
     ChatCompletionDelta
     """ # noqa: E501
+    message_id: Optional[StrictStr] = Field(default=None, description="Id of the chat completion message. The attribute is populated only in the last message (`finished==True`).")
     body: StrictStr
     finished: StrictBool
-    __properties: ClassVar[List[str]] = ["body", "finished"]
+    __properties: ClassVar[List[str]] = ["message_id", "body", "finished"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -81,6 +82,7 @@ class ChatCompletionDelta(BaseModel):
             return cls.model_validate(obj)
 
         _obj = cls.model_validate({
+            "message_id": obj.get("message_id"),
             "body": obj.get("body"),
             "finished": obj.get("finished")
         })

h2ogpte/rest_sync/models/chat_completion_request.py

@@ -33,7 +33,7 @@ class ChatCompletionRequest(BaseModel):
     image_batch_final_prompt: Optional[StrictStr] = Field(default=None, description="A prompt for each image batch for vision models.")
     image_batch_image_prompt: Optional[StrictStr] = Field(default=None, description="A prompt to reduce all answers each image batch for vision models")
     llm: Optional[StrictStr] = Field(default=None, description="LLM name to send the query. Use \"auto\" for automatic model routing, set cost_controls of llm_args for detailed control over automatic routing.")
-    llm_args: Optional[Dict[str, Any]] = Field(default=None, description="A map of arguments sent to LLM with query.   * `temperature` **(type=double, default=0.0)** - A value used to modulate the next token probabilities.     0 is the most deterministic and 1 is most creative.   * `top_k` **(type=integer, default=1)** - A number of highest probability vocabulary tokens to keep for top-k-filtering.   * `top_p` **(type=double, default=0.0)** - If set to a value < 1, only the smallest set of most probable     tokens with probabilities that add up to top_p or higher are kept for generation.   * `seed` **(type=integer, default=0)** - A seed for the random number generator when sampling during      generation (if temp>0 or top_k>1 or top_p<1), seed=0 picks a random seed.   * `repetition_penalty` **(type=double, default=1.07)** - A parameter for repetition penalty. 1.0 means no penalty.   * `max_new_tokens` **(type=double, default=1024)** - A maximum number of new tokens to generate.     This limit applies to each (map+reduce) step during summarization and each (map) step during extraction.   * `min_max_new_tokens` **(type=integer, default=512)** - A minimum value for max_new_tokens when auto-adjusting for content of prompt, docs, etc.   * `response_format` **(type=enum[text, json_object, json_code], default=text)** - An output type of LLM   * `guided_json` **(type=map)** - If specified, the output will follow the JSON schema.   * `guided_regex` **(type=string)** - If specified, the output will follow the regex pattern.     Only for models that support guided generation.   * `guided_choice` **(type=array[string])** - If specified, the output will be exactly one of the choices.     Only for models that support guided generation.   * `guided_grammar` **(type=string)** - If specified, the output will follow the context free grammar.     Only for models that support guided generation.   * `guided_whitespace_pattern` **(type=string)** - If specified, will override the default whitespace pattern for guided json decoding.     Only for models that support guided generation.   * `enable_vision` **(type=enum[on, off, auto], default=auto)** - Controls vision mode,     send images to the LLM in addition to text chunks.   * `visible_vision_models` **(type=array[string], default=[auto])** - Controls which vision model to use when processing images.     Must provide exactly one model. [auto] for automatic.   * `images_num_max` **(type=integer, default=None)** - Maximum number of images to process.   * `json_preserve_system_prompt` **(type=boolean, default=None)** - Whether to preserve system prompt in JSON response.   * `client_metadata` **(type=string, default=None)** - Additional metadata to send with the request.   * `min_chars_per_yield` **(type=integer, default=1)** - Minimum characters to yield in streaming response.   * `cost_controls` **(type=map)** A map with cost controls settings:     * `max_cost` **(type=double)** - Sets the maximum allowed cost in USD per LLM call when doing Automatic model routing.       If the estimated cost based on input and output token counts is higher than this limit,       the request will fail as early as possible.     * `max_cost_per_million_tokens` **(type=double)** - Only consider models that cost less than this value in USD per million tokens       when doing automatic routing. Using the max of input and output cost.     * `model` **(type=array[string])** - Optional subset of models to consider when doing automatic routing.       If not specified, all models are considered.     * `willingness_to_pay` **(type=double)** - Controls the willingness to pay extra for a more accurate model for every LLM call       when doing automatic routing, in units of USD per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated cost divided by the increase in estimated accuracy       is no more than this value divided by 10%, up to the upper limit specified above.       Lower values will try to keep the cost as low as possible,       higher values will approach the cost limit to increase accuracy. 0 means unlimited.     * `willingness_to_wait` **(type=double)** - Controls the willingness to wait longer for a more accurate model for every LLM call       when doing automatic routing, in units of seconds per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated time divided by the increase in estimated accuracy       is no more than this value divided by 10%. Lower values will try to keep the time       as low as possible, higher values will take longer to increase accuracy. 0 means unlimited.   * `use_agent` **(type=boolean, default=False)** - If True, use the AI agent (with access to tools) to generate the response.   * `agent_accuracy` **(type=string, default=\"standard\")** - Effort level by the agent. Only if use_agent=True. One of [\"quick\", \"basic\", \"standard\", \"maximum\"].   * `agent_max_turns` **(type=union[string, integer], default=\"auto\")** - Optional max. number of back-and-forth turns with the agent. Only if use_agent=True. Either \"auto\" or an integer.   * `agent_tools` **(type=union[string, array[string]], default=\"auto\")** - Either \"auto\", \"all\", \"any\" to enable all available tools, or a specific list of tools to use. Only if use_agent=True.   * `agent_type` **(type=string, default=\"auto\")** - Type of agent to use for task processing.   * `agent_original_files` **(type=array[string], default=None)** - List of file paths for agent to process.   * `agent_timeout` **(type=integer, default=None)** - Timeout in seconds for each agent turn.   * `agent_total_timeout` **(type=integer, default=3600)** - Total timeout in seconds for all agent processing.   * `agent_code_writer_system_message` **(type=string, default=None)** - System message for agent code writer.   * `agent_num_executable_code_blocks_limit` **(type=integer, default=1)** - Maximum number of executable code blocks.   * `agent_system_site_packages` **(type=boolean, default=True)** - Whether agent has access to system site packages.   * `agent_main_model` **(type=string, default=None)** - Main model to use for agent.   * `agent_max_stream_length` **(type=integer, default=None)** - Maximum stream length for agent response.   * `agent_max_memory_usage` **(type=integer, default=16*1024**3)** - Maximum memory usage for agent in bytes (16GB default).   * `agent_main_reasoning_effort` **(type=integer, default=None)** - Effort level for main reasoning.   * `agent_advanced_reasoning_effort` **(type=integer, default=None)** - Effort level for advanced reasoning.   * `agent_max_confidence_level` **(type=integer, default=None)** - Maximum confidence level for agent responses.   * `agent_planning_forced_mode` **(type=boolean, default=None)** - Whether to force planning mode for agent.   * `agent_too_soon_forced_mode` **(type=boolean, default=None)** - Whether to force \"too soon\" mode for agent.   * `agent_critique_forced_mode` **(type=integer, default=None)** - Whether to force critique mode for agent.   * `agent_stream_files` **(type=boolean, default=True)** - Whether to stream files from agent. ")
+    llm_args: Optional[Dict[str, Any]] = Field(default=None, description="A map of arguments sent to LLM with query.   * `temperature` **(type=double, default=0.0)** - A value used to modulate the next token probabilities.     0 is the most deterministic and 1 is most creative.   * `top_k` **(type=integer, default=1)** - A number of highest probability vocabulary tokens to keep for top-k-filtering.   * `top_p` **(type=double, default=0.0)** - If set to a value < 1, only the smallest set of most probable     tokens with probabilities that add up to top_p or higher are kept for generation.   * `seed` **(type=integer, default=0)** - A seed for the random number generator when sampling during      generation (if temp>0 or top_k>1 or top_p<1), seed=0 picks a random seed.   * `repetition_penalty` **(type=double, default=1.07)** - A parameter for repetition penalty. 1.0 means no penalty.   * `max_new_tokens` **(type=double, default=1024)** - A maximum number of new tokens to generate.     This limit applies to each (map+reduce) step during summarization and each (map) step during extraction.   * `min_max_new_tokens` **(type=integer, default=512)** - A minimum value for max_new_tokens when auto-adjusting for content of prompt, docs, etc.   * `response_format` **(type=enum[text, json_object, json_code], default=text)** - An output type of LLM   * `guided_json` **(type=map)** - If specified, the output will follow the JSON schema.   * `guided_regex` **(type=string)** - If specified, the output will follow the regex pattern.     Only for models that support guided generation.   * `guided_choice` **(type=array[string])** - If specified, the output will be exactly one of the choices.     Only for models that support guided generation.   * `guided_grammar` **(type=string)** - If specified, the output will follow the context free grammar.     Only for models that support guided generation.   * `guided_whitespace_pattern` **(type=string)** - If specified, will override the default whitespace pattern for guided json decoding.     Only for models that support guided generation.   * `enable_vision` **(type=enum[on, off, auto], default=auto)** - Controls vision mode,     send images to the LLM in addition to text chunks.   * `visible_vision_models` **(type=array[string], default=[auto])** - Controls which vision model to use when processing images.     Must provide exactly one model. [auto] for automatic.   * `images_num_max` **(type=integer, default=None)** - Maximum number of images to process.   * `json_preserve_system_prompt` **(type=boolean, default=None)** - Whether to preserve system prompt in JSON response.   * `client_metadata` **(type=string, default=None)** - Additional metadata to send with the request.   * `min_chars_per_yield` **(type=integer, default=1)** - Minimum characters to yield in streaming response.   * `reasoning_effort` **(type=integer, default=0)** - Level of reasoning effort for the model (higher values = deeper reasoning, e.g., 10000-65000).     Use for models that support chain-of-thought reasoning. 0 means no additional reasoning effort.   * `cost_controls` **(type=map)** A map with cost controls settings:     * `max_cost` **(type=double)** - Sets the maximum allowed cost in USD per LLM call when doing Automatic model routing.       If the estimated cost based on input and output token counts is higher than this limit,       the request will fail as early as possible.     * `max_cost_per_million_tokens` **(type=double)** - Only consider models that cost less than this value in USD per million tokens       when doing automatic routing. Using the max of input and output cost.     * `model` **(type=array[string])** - Optional subset of models to consider when doing automatic routing.       If not specified, all models are considered.     * `willingness_to_pay` **(type=double)** - Controls the willingness to pay extra for a more accurate model for every LLM call       when doing automatic routing, in units of USD per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated cost divided by the increase in estimated accuracy       is no more than this value divided by 10%, up to the upper limit specified above.       Lower values will try to keep the cost as low as possible,       higher values will approach the cost limit to increase accuracy. 0 means unlimited.     * `willingness_to_wait` **(type=double)** - Controls the willingness to wait longer for a more accurate model for every LLM call       when doing automatic routing, in units of seconds per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated time divided by the increase in estimated accuracy       is no more than this value divided by 10%. Lower values will try to keep the time       as low as possible, higher values will take longer to increase accuracy. 0 means unlimited.   * `use_agent` **(type=boolean, default=False)** - If True, use the AI agent (with access to tools) to generate the response.   * `agent_accuracy` **(type=string, default=\"standard\")** - Effort level by the agent. Only if use_agent=True. One of [\"quick\", \"basic\", \"standard\", \"maximum\"].   * `agent_max_turns` **(type=union[string, integer], default=\"auto\")** - Optional max. number of back-and-forth turns with the agent. Only if use_agent=True. Either \"auto\" or an integer.   * `agent_tools` **(type=union[string, array[string]], default=\"auto\")** - Either \"auto\", \"all\", \"any\" to enable all available tools, or a specific list of tools to use. Only if use_agent=True.   * `agent_type` **(type=string, default=\"auto\")** - Type of agent to use for task processing.   * `agent_original_files` **(type=array[string], default=None)** - List of file paths for agent to process.   * `agent_timeout` **(type=integer, default=None)** - Timeout in seconds for each agent turn.   * `agent_total_timeout` **(type=integer, default=3600)** - Total timeout in seconds for all agent processing.   * `agent_code_writer_system_message` **(type=string, default=None)** - System message for agent code writer.   * `agent_num_executable_code_blocks_limit` **(type=integer, default=1)** - Maximum number of executable code blocks.   * `agent_system_site_packages` **(type=boolean, default=True)** - Whether agent has access to system site packages.   * `agent_main_model` **(type=string, default=None)** - Main model to use for agent.   * `agent_max_stream_length` **(type=integer, default=None)** - Maximum stream length for agent response.   * `agent_max_memory_usage` **(type=integer, default=16*1024**3)** - Maximum memory usage for agent in bytes (16GB default).   * `agent_main_reasoning_effort` **(type=integer, default=None)** - Effort level for main reasoning.   * `agent_advanced_reasoning_effort` **(type=integer, default=None)** - Effort level for advanced reasoning.   * `agent_max_confidence_level` **(type=integer, default=None)** - Maximum confidence level for agent responses.   * `agent_planning_forced_mode` **(type=boolean, default=None)** - Whether to force planning mode for agent.   * `agent_too_soon_forced_mode` **(type=boolean, default=None)** - Whether to force \"too soon\" mode for agent.   * `agent_critique_forced_mode` **(type=integer, default=None)** - Whether to force critique mode for agent.   * `agent_stream_files` **(type=boolean, default=True)** - Whether to stream files from agent. ")
     self_reflection_config: Optional[Dict[str, Any]] = Field(default=None, description="A map with self reflection settings:   * `llm_reflection` **(type=string, example=gpt-4-0613)**   * `prompt_reflection` **(type=string, example=\\\"\\\"\\\"Prompt:\\\\\\\\n%s\\\\\\\\n\\\"\\\"\\\"\\\\\\\\n\\\\\\\\n\\\"\\\"\\\")**   * `system_prompt_reflection` **(type=string)**   * `llm_args_reflection` **(type=string, example={})** ")
     rag_config: Optional[Dict[str, Any]] = Field(default=None, description="A map with arguments to control RAG (retrieval-augmented-generation) types.:   * `rag_type` **(type=enum[auto, llm_only, rag, hyde1, hyde2, rag+, all_data])** RAG type options:     * `auto` - Automatically select the best rag_type.     * `llm_only` LLM Only - Answer the query without any supporting document contexts.        Requires 1 LLM call.     * `rag` RAG (Retrieval Augmented Generation) - Use supporting document contexts        to answer the query. Requires 1 LLM call.     * `hyde1` LLM Only + RAG composite - HyDE RAG (Hypothetical Document Embedding).        Use 'LLM Only' response to find relevant contexts from a collection for generating        a response. Requires 2 LLM calls.     * `hyde2` HyDE + RAG composite - Use the 'HyDE RAG' response to find relevant        contexts from a collection for generating a response. Requires 3 LLM calls.     * `rag+` Summary RAG - Like RAG, but uses more context and recursive        summarization to overcome LLM context limits. Keeps all retrieved chunks, puts        them in order, adds neighboring chunks, then uses the summary API to get the        answer. Can require several LLM calls.     * `all_data` All Data RAG - Like Summary RAG, but includes all document        chunks. Uses recursive summarization to overcome LLM context limits.        Can require several LLM calls.   * `hyde_no_rag_llm_prompt_extension` **(type=string, example=\\\\\\\\nKeep the answer brief, and list the 5 most relevant key words at the end.)** -     Add this prompt to every user's prompt, when generating answers to be used for subsequent retrieval during HyDE.     Only used when rag_type is `hyde1` or `hyde2`.   * `num_neighbor_chunks_to_include` **(type=integer, default=1)** - A number of neighboring chunks to include      for every retrieved relevant chunk. It helps to keep surrounding context together. Only enabled for rag_type `rag+`.   * `meta_data_to_include` **(type=map)** - A map with flags that indicate whether each piece of document metadata      is to be included as part of the context for a chat with a collection.     * `name` **(type: boolean, default=True)**     * `text` **(type: boolean, default=True)**     * `page` **(type: boolean, default=True)**     * `captions` **(type: boolean, default=True)**     * `uri` **(type: boolean, default=False)**     * `connector` **(type: boolean, default=False)**     * `original_mtime` **(type: boolean, default=False)**     * `age` **(type: boolean, default=False)**     * `score` **(type: boolean, default=False)**   * `rag_max_chunks` **(type=integer, default=-1)** - Maximum number of document chunks to retrieve for RAG.     Actual number depends on rag_type and admin configuration. Set to >0 values to enable.      Can be combined with rag_min_chunk_score.   * `rag_min_chunk_score` **(type=double, default=0.0)** - Minimum score of document chunks to retrieve for RAG.     Set to >0 values to enable. Can be combined with rag_max_chunks. ")
     include_chat_history: Optional[StrictStr] = Field(default=None, description="Whether to include chat history. Includes previous questions and answers for the current chat session for each new chat request. Disable if require deterministic answers for a given question.")

h2ogpte/rest_sync/models/chat_session.py

@@ -34,7 +34,8 @@ class ChatSession(BaseModel):
     prompt_template_id: Optional[StrictStr] = None
     latest_message_content: Optional[StrictStr] = None
     updated_at: datetime
-    __properties: ClassVar[List[str]] = ["id", "name", "collection_id", "collection_name", "prompt_template_id", "latest_message_content", "updated_at"]
+    workspace: Optional[StrictStr] = None
+    __properties: ClassVar[List[str]] = ["id", "name", "collection_id", "collection_name", "prompt_template_id", "latest_message_content", "updated_at", "workspace"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -93,7 +94,8 @@ class ChatSession(BaseModel):
             "collection_name": obj.get("collection_name"),
             "prompt_template_id": obj.get("prompt_template_id"),
             "latest_message_content": obj.get("latest_message_content"),
-            "updated_at": obj.get("updated_at")
+            "updated_at": obj.get("updated_at"),
+            "workspace": obj.get("workspace")
         })
         return _obj
 

h2ogpte/rest_sync/models/chat_settings.py

@@ -27,7 +27,7 @@ class ChatSettings(BaseModel):
     ChatSettings
     """ # noqa: E501
     llm: Optional[StrictStr] = Field(default=None, description="LLM name to send the query. Use \"auto\" for automatic model routing, set cost_controls of llm_args for detailed control over automatic routing.")
-    llm_args: Optional[Dict[str, Any]] = Field(default=None, description="A map of arguments sent to LLM with query.   * `temperature` **(type=double, default=0.0)** - A value used to modulate the next token probabilities.     0 is the most deterministic and 1 is most creative.   * `top_k` **(type=integer, default=1)** - A number of highest probability vocabulary tokens to keep for top-k-filtering.   * `top_p` **(type=double, default=0.0)** - If set to a value < 1, only the smallest set of most probable     tokens with probabilities that add up to top_p or higher are kept for generation.   * `seed` **(type=integer, default=0)** - A seed for the random number generator when sampling during      generation (if temp>0 or top_k>1 or top_p<1), seed=0 picks a random seed.   * `repetition_penalty` **(type=double, default=1.07)** - A parameter for repetition penalty. 1.0 means no penalty.   * `max_new_tokens` **(type=double, default=1024)** - A maximum number of new tokens to generate.     This limit applies to each (map+reduce) step during summarization and each (map) step during extraction.   * `min_max_new_tokens` **(type=integer, default=512)** - A minimum value for max_new_tokens when auto-adjusting for content of prompt, docs, etc.   * `response_format` **(type=enum[text, json_object, json_code], default=text)** - An output type of LLM   * `guided_json` **(type=map)** - If specified, the output will follow the JSON schema.   * `guided_regex` **(type=string)** - If specified, the output will follow the regex pattern.     Only for models that support guided generation.   * `guided_choice` **(type=array[string])** - If specified, the output will be exactly one of the choices.     Only for models that support guided generation.   * `guided_grammar` **(type=string)** - If specified, the output will follow the context free grammar.     Only for models that support guided generation.   * `guided_whitespace_pattern` **(type=string)** - If specified, will override the default whitespace pattern for guided json decoding.     Only for models that support guided generation.   * `enable_vision` **(type=enum[on, off, auto], default=auto)** - Controls vision mode,     send images to the LLM in addition to text chunks.   * `visible_vision_models` **(type=array[string], default=[auto])** - Controls which vision model to use when processing images.     Must provide exactly one model. [auto] for automatic.   * `images_num_max` **(type=integer, default=None)** - Maximum number of images to process.   * `json_preserve_system_prompt` **(type=boolean, default=None)** - Whether to preserve system prompt in JSON response.   * `client_metadata` **(type=string, default=None)** - Additional metadata to send with the request.   * `min_chars_per_yield` **(type=integer, default=1)** - Minimum characters to yield in streaming response.   * `cost_controls` **(type=map)** A map with cost controls settings:     * `max_cost` **(type=double)** - Sets the maximum allowed cost in USD per LLM call when doing Automatic model routing.       If the estimated cost based on input and output token counts is higher than this limit,       the request will fail as early as possible.     * `max_cost_per_million_tokens` **(type=double)** - Only consider models that cost less than this value in USD per million tokens       when doing automatic routing. Using the max of input and output cost.     * `model` **(type=array[string])** - Optional subset of models to consider when doing automatic routing.       If not specified, all models are considered.     * `willingness_to_pay` **(type=double)** - Controls the willingness to pay extra for a more accurate model for every LLM call       when doing automatic routing, in units of USD per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated cost divided by the increase in estimated accuracy       is no more than this value divided by 10%, up to the upper limit specified above.       Lower values will try to keep the cost as low as possible,       higher values will approach the cost limit to increase accuracy. 0 means unlimited.     * `willingness_to_wait` **(type=double)** - Controls the willingness to wait longer for a more accurate model for every LLM call       when doing automatic routing, in units of seconds per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated time divided by the increase in estimated accuracy       is no more than this value divided by 10%. Lower values will try to keep the time       as low as possible, higher values will take longer to increase accuracy. 0 means unlimited.   * `use_agent` **(type=boolean, default=False)** - If True, use the AI agent (with access to tools) to generate the response.   * `agent_accuracy` **(type=string, default=\"standard\")** - Effort level by the agent. Only if use_agent=True. One of [\"quick\", \"basic\", \"standard\", \"maximum\"].   * `agent_max_turns` **(type=union[string, integer], default=\"auto\")** - Optional max. number of back-and-forth turns with the agent. Only if use_agent=True. Either \"auto\" or an integer.   * `agent_tools` **(type=union[string, array[string]], default=\"auto\")** - Either \"auto\", \"all\", \"any\" to enable all available tools, or a specific list of tools to use. Only if use_agent=True.   * `agent_type` **(type=string, default=\"auto\")** - Type of agent to use for task processing.   * `agent_original_files` **(type=array[string], default=None)** - List of file paths for agent to process.   * `agent_timeout` **(type=integer, default=None)** - Timeout in seconds for each agent turn.   * `agent_total_timeout` **(type=integer, default=3600)** - Total timeout in seconds for all agent processing.   * `agent_code_writer_system_message` **(type=string, default=None)** - System message for agent code writer.   * `agent_num_executable_code_blocks_limit` **(type=integer, default=1)** - Maximum number of executable code blocks.   * `agent_system_site_packages` **(type=boolean, default=True)** - Whether agent has access to system site packages.   * `agent_main_model` **(type=string, default=None)** - Main model to use for agent.   * `agent_max_stream_length` **(type=integer, default=None)** - Maximum stream length for agent response.   * `agent_max_memory_usage` **(type=integer, default=16*1024**3)** - Maximum memory usage for agent in bytes (16GB default).   * `agent_main_reasoning_effort` **(type=integer, default=None)** - Effort level for main reasoning.   * `agent_advanced_reasoning_effort` **(type=integer, default=None)** - Effort level for advanced reasoning.   * `agent_max_confidence_level` **(type=integer, default=None)** - Maximum confidence level for agent responses.   * `agent_planning_forced_mode` **(type=boolean, default=None)** - Whether to force planning mode for agent.   * `agent_too_soon_forced_mode` **(type=boolean, default=None)** - Whether to force \"too soon\" mode for agent.   * `agent_critique_forced_mode` **(type=integer, default=None)** - Whether to force critique mode for agent.   * `agent_stream_files` **(type=boolean, default=True)** - Whether to stream files from agent. ")
+    llm_args: Optional[Dict[str, Any]] = Field(default=None, description="A map of arguments sent to LLM with query.   * `temperature` **(type=double, default=0.0)** - A value used to modulate the next token probabilities.     0 is the most deterministic and 1 is most creative.   * `top_k` **(type=integer, default=1)** - A number of highest probability vocabulary tokens to keep for top-k-filtering.   * `top_p` **(type=double, default=0.0)** - If set to a value < 1, only the smallest set of most probable     tokens with probabilities that add up to top_p or higher are kept for generation.   * `seed` **(type=integer, default=0)** - A seed for the random number generator when sampling during      generation (if temp>0 or top_k>1 or top_p<1), seed=0 picks a random seed.   * `repetition_penalty` **(type=double, default=1.07)** - A parameter for repetition penalty. 1.0 means no penalty.   * `max_new_tokens` **(type=double, default=1024)** - A maximum number of new tokens to generate.     This limit applies to each (map+reduce) step during summarization and each (map) step during extraction.   * `min_max_new_tokens` **(type=integer, default=512)** - A minimum value for max_new_tokens when auto-adjusting for content of prompt, docs, etc.   * `response_format` **(type=enum[text, json_object, json_code], default=text)** - An output type of LLM   * `guided_json` **(type=map)** - If specified, the output will follow the JSON schema.   * `guided_regex` **(type=string)** - If specified, the output will follow the regex pattern.     Only for models that support guided generation.   * `guided_choice` **(type=array[string])** - If specified, the output will be exactly one of the choices.     Only for models that support guided generation.   * `guided_grammar` **(type=string)** - If specified, the output will follow the context free grammar.     Only for models that support guided generation.   * `guided_whitespace_pattern` **(type=string)** - If specified, will override the default whitespace pattern for guided json decoding.     Only for models that support guided generation.   * `enable_vision` **(type=enum[on, off, auto], default=auto)** - Controls vision mode,     send images to the LLM in addition to text chunks.   * `visible_vision_models` **(type=array[string], default=[auto])** - Controls which vision model to use when processing images.     Must provide exactly one model. [auto] for automatic.   * `images_num_max` **(type=integer, default=None)** - Maximum number of images to process.   * `json_preserve_system_prompt` **(type=boolean, default=None)** - Whether to preserve system prompt in JSON response.   * `client_metadata` **(type=string, default=None)** - Additional metadata to send with the request.   * `min_chars_per_yield` **(type=integer, default=1)** - Minimum characters to yield in streaming response.   * `reasoning_effort` **(type=integer, default=0)** - Level of reasoning effort for the model (higher values = deeper reasoning, e.g., 10000-65000).     Use for models that support chain-of-thought reasoning. 0 means no additional reasoning effort.   * `cost_controls` **(type=map)** A map with cost controls settings:     * `max_cost` **(type=double)** - Sets the maximum allowed cost in USD per LLM call when doing Automatic model routing.       If the estimated cost based on input and output token counts is higher than this limit,       the request will fail as early as possible.     * `max_cost_per_million_tokens` **(type=double)** - Only consider models that cost less than this value in USD per million tokens       when doing automatic routing. Using the max of input and output cost.     * `model` **(type=array[string])** - Optional subset of models to consider when doing automatic routing.       If not specified, all models are considered.     * `willingness_to_pay` **(type=double)** - Controls the willingness to pay extra for a more accurate model for every LLM call       when doing automatic routing, in units of USD per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated cost divided by the increase in estimated accuracy       is no more than this value divided by 10%, up to the upper limit specified above.       Lower values will try to keep the cost as low as possible,       higher values will approach the cost limit to increase accuracy. 0 means unlimited.     * `willingness_to_wait` **(type=double)** - Controls the willingness to wait longer for a more accurate model for every LLM call       when doing automatic routing, in units of seconds per +10% increase in accuracy.       We start with the least accurate model. For each more accurate model,       we accept it if the increase in estimated time divided by the increase in estimated accuracy       is no more than this value divided by 10%. Lower values will try to keep the time       as low as possible, higher values will take longer to increase accuracy. 0 means unlimited.   * `use_agent` **(type=boolean, default=False)** - If True, use the AI agent (with access to tools) to generate the response.   * `agent_accuracy` **(type=string, default=\"standard\")** - Effort level by the agent. Only if use_agent=True. One of [\"quick\", \"basic\", \"standard\", \"maximum\"].   * `agent_max_turns` **(type=union[string, integer], default=\"auto\")** - Optional max. number of back-and-forth turns with the agent. Only if use_agent=True. Either \"auto\" or an integer.   * `agent_tools` **(type=union[string, array[string]], default=\"auto\")** - Either \"auto\", \"all\", \"any\" to enable all available tools, or a specific list of tools to use. Only if use_agent=True.   * `agent_type` **(type=string, default=\"auto\")** - Type of agent to use for task processing.   * `agent_original_files` **(type=array[string], default=None)** - List of file paths for agent to process.   * `agent_timeout` **(type=integer, default=None)** - Timeout in seconds for each agent turn.   * `agent_total_timeout` **(type=integer, default=3600)** - Total timeout in seconds for all agent processing.   * `agent_code_writer_system_message` **(type=string, default=None)** - System message for agent code writer.   * `agent_num_executable_code_blocks_limit` **(type=integer, default=1)** - Maximum number of executable code blocks.   * `agent_system_site_packages` **(type=boolean, default=True)** - Whether agent has access to system site packages.   * `agent_main_model` **(type=string, default=None)** - Main model to use for agent.   * `agent_max_stream_length` **(type=integer, default=None)** - Maximum stream length for agent response.   * `agent_max_memory_usage` **(type=integer, default=16*1024**3)** - Maximum memory usage for agent in bytes (16GB default).   * `agent_main_reasoning_effort` **(type=integer, default=None)** - Effort level for main reasoning.   * `agent_advanced_reasoning_effort` **(type=integer, default=None)** - Effort level for advanced reasoning.   * `agent_max_confidence_level` **(type=integer, default=None)** - Maximum confidence level for agent responses.   * `agent_planning_forced_mode` **(type=boolean, default=None)** - Whether to force planning mode for agent.   * `agent_too_soon_forced_mode` **(type=boolean, default=None)** - Whether to force \"too soon\" mode for agent.   * `agent_critique_forced_mode` **(type=integer, default=None)** - Whether to force critique mode for agent.   * `agent_stream_files` **(type=boolean, default=True)** - Whether to stream files from agent. ")
     self_reflection_config: Optional[Dict[str, Any]] = Field(default=None, description="A map with self reflection settings:   * `llm_reflection` **(type=string, example=gpt-4-0613)**   * `prompt_reflection` **(type=string, example=\\\"\\\"\\\"Prompt:\\\\\\\\n%s\\\\\\\\n\\\"\\\"\\\"\\\\\\\\n\\\\\\\\n\\\"\\\"\\\")**   * `system_prompt_reflection` **(type=string)**   * `llm_args_reflection` **(type=string, example={})** ")
     rag_config: Optional[Dict[str, Any]] = Field(default=None, description="A map with arguments to control RAG (retrieval-augmented-generation) types.:   * `rag_type` **(type=enum[auto, llm_only, rag, hyde1, hyde2, rag+, all_data])** RAG type options:     * `auto` - Automatically select the best rag_type.     * `llm_only` LLM Only - Answer the query without any supporting document contexts.        Requires 1 LLM call.     * `rag` RAG (Retrieval Augmented Generation) - Use supporting document contexts        to answer the query. Requires 1 LLM call.     * `hyde1` LLM Only + RAG composite - HyDE RAG (Hypothetical Document Embedding).        Use 'LLM Only' response to find relevant contexts from a collection for generating        a response. Requires 2 LLM calls.     * `hyde2` HyDE + RAG composite - Use the 'HyDE RAG' response to find relevant        contexts from a collection for generating a response. Requires 3 LLM calls.     * `rag+` Summary RAG - Like RAG, but uses more context and recursive        summarization to overcome LLM context limits. Keeps all retrieved chunks, puts        them in order, adds neighboring chunks, then uses the summary API to get the        answer. Can require several LLM calls.     * `all_data` All Data RAG - Like Summary RAG, but includes all document        chunks. Uses recursive summarization to overcome LLM context limits.        Can require several LLM calls.   * `hyde_no_rag_llm_prompt_extension` **(type=string, example=\\\\\\\\nKeep the answer brief, and list the 5 most relevant key words at the end.)** -     Add this prompt to every user's prompt, when generating answers to be used for subsequent retrieval during HyDE.     Only used when rag_type is `hyde1` or `hyde2`.   * `num_neighbor_chunks_to_include` **(type=integer, default=1)** - A number of neighboring chunks to include      for every retrieved relevant chunk. It helps to keep surrounding context together. Only enabled for rag_type `rag+`.   * `meta_data_to_include` **(type=map)** - A map with flags that indicate whether each piece of document metadata      is to be included as part of the context for a chat with a collection.     * `name` **(type: boolean, default=True)**     * `text` **(type: boolean, default=True)**     * `page` **(type: boolean, default=True)**     * `captions` **(type: boolean, default=True)**     * `uri` **(type: boolean, default=False)**     * `connector` **(type: boolean, default=False)**     * `original_mtime` **(type: boolean, default=False)**     * `age` **(type: boolean, default=False)**     * `score` **(type: boolean, default=False)**   * `rag_max_chunks` **(type=integer, default=-1)** - Maximum number of document chunks to retrieve for RAG.     Actual number depends on rag_type and admin configuration. Set to >0 values to enable.      Can be combined with rag_min_chunk_score.   * `rag_min_chunk_score` **(type=double, default=0.0)** - Minimum score of document chunks to retrieve for RAG.     Set to >0 values to enable. Can be combined with rag_max_chunks. ")
     include_chat_history: Optional[StrictStr] = Field(default=None, description="Whether to include chat history. Includes previous questions and answers for the current chat session for each new chat request. Disable if require deterministic answers for a given question.")

h2ogpte/rest_sync/models/collection.py

@@ -47,7 +47,8 @@ class Collection(BaseModel):
     inactivity_interval: Optional[StrictInt] = Field(default=None, description="The inactivity interval as an integer number of days.")
     rag_type: Optional[StrictStr] = Field(default=None, description="RAG type options:   * `auto` - Automatically select the best rag_type.   * `llm_only` LLM Only - Answer the query without any supporting document contexts.   Requires 1 LLM call.   * `rag` RAG (Retrieval Augmented Generation) - Use supporting document contexts   to answer the query. Requires 1 LLM call.   * `hyde1` LLM Only + RAG composite - HyDE RAG (Hypothetical Document Embedding).   Use 'LLM Only' response to find relevant contexts from a collection for generating   a response. Requires 2 LLM calls.   * `hyde2` HyDE + RAG composite - Use the 'HyDE RAG' response to find relevant   contexts from a collection for generating a response. Requires 3 LLM calls.   * `rag+` Summary RAG - Like RAG, but uses more context and recursive   summarization to overcome LLM context limits. Keeps all retrieved chunks, puts   them in order, adds neighboring chunks, then uses the summary API to get the   answer. Can require several LLM calls.   * `all_data` All Data RAG - Like Summary RAG, but includes all document   chunks. Uses recursive summarization to overcome LLM context limits.   Can require several LLM calls. ")
     metadata_dict: Optional[Dict[str, Any]] = None
-    __properties: ClassVar[List[str]] = ["id", "name", "description", "embedding_model", "document_count", "document_size", "created_at", "updated_at", "user_count", "is_public", "username", "sessions_count", "status", "prompt_template_id", "thumbnail", "size_limit", "expiry_date", "inactivity_interval", "rag_type", "metadata_dict"]
+    workspace: Optional[StrictStr] = Field(default=None, description="The workspace associated with the collection.")
+    __properties: ClassVar[List[str]] = ["id", "name", "description", "embedding_model", "document_count", "document_size", "created_at", "updated_at", "user_count", "is_public", "username", "sessions_count", "status", "prompt_template_id", "thumbnail", "size_limit", "expiry_date", "inactivity_interval", "rag_type", "metadata_dict", "workspace"]
 
     @field_validator('rag_type')
     def rag_type_validate_enum(cls, value):
@@ -129,7 +130,8 @@ class Collection(BaseModel):
             "expiry_date": obj.get("expiry_date"),
             "inactivity_interval": obj.get("inactivity_interval"),
             "rag_type": obj.get("rag_type"),
-            "metadata_dict": obj.get("metadata_dict")
+            "metadata_dict": obj.get("metadata_dict"),
+            "workspace": obj.get("workspace")
         })
         return _obj
 

h2ogpte/rest_sync/models/collection_create_request.py

@@ -35,7 +35,8 @@ class CollectionCreateRequest(BaseModel):
     collection_settings: Optional[CollectionSettings] = None
     chat_settings: Optional[ChatSettings] = None
     expiry_date: Optional[datetime] = Field(default=None, description="Optional expiration date for the collection")
-    __properties: ClassVar[List[str]] = ["name", "description", "embedding_model", "collection_settings", "chat_settings", "expiry_date"]
+    workspace: Optional[StrictStr] = None
+    __properties: ClassVar[List[str]] = ["name", "description", "embedding_model", "collection_settings", "chat_settings", "expiry_date", "workspace"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -99,7 +100,8 @@ class CollectionCreateRequest(BaseModel):
             "embedding_model": obj.get("embedding_model"),
             "collection_settings": CollectionSettings.from_dict(obj["collection_settings"]) if obj.get("collection_settings") is not None else None,
             "chat_settings": ChatSettings.from_dict(obj["chat_settings"]) if obj.get("chat_settings") is not None else None,
-            "expiry_date": obj.get("expiry_date")
+            "expiry_date": obj.get("expiry_date"),
+            "workspace": obj.get("workspace")
         })
         return _obj
 

h2ogpte/rest_sync/models/create_chat_session_request.py

@@ -0,0 +1,87 @@
+# coding: utf-8
+
+"""
+    h2oGPTe REST API
+
+     # Overview   Users can easily interact with the h2oGPTe API through its REST API, allowing HTTP requests from any programming language.  ## Authorization: Getting an API key  Sign up/in at Enterprise h2oGPTe and generate one of the following two types of API keys:   - **Global API key**: If a Collection is not specified when creating a new API Key, that key is considered to be a global API Key. Use global API Keys to grant full user impersonation and system-wide access to all of your work. Anyone with access to one of your global API Keys can create, delete, or interact with any of your past, current, and future Collections, Documents, Chats, and settings.  - **Collection-specific API key**: Use Collection-specific API Keys to grant external access to only Chat with a specified Collection and make related API calls to it. Collection-specific API keys do not allow other API calls, such as creation, deletion, or access to other Collections or Chats.   Access Enterprise h2oGPTe through your [H2O Generative AI](https://genai.h2o.ai/appstore) app store account, available with a freemium tier.  ## Authorization: Using an API key   All h2oGPTe REST API requests must include an API Key in the \"Authorization\" HTTP header, formatted as follows:  ``` Authorization: Bearer sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX ```  ```sh curl -X 'POST' \\   'https://h2ogpte.genai.h2o.ai/api/v1/collections' \\   -H 'accept: application/json' \\   -H 'Content-Type: application/json' \\   -H 'Authorization: Bearer sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX' \\   -d '{     \"name\": \"The name of my Collection\",     \"description\": \"The description of my Collection\",     \"embedding_model\": \"BAAI/bge-large-en-v1.5\"   }' ```      ## Interactive h2oGPTe API testing  This page only showcases the h2oGPTe REST API; you can test it directly in the [Swagger UI](https://h2ogpte.genai.h2o.ai/swagger-ui/). Ensure that you are logged into your Enterprise h2oGPTe account. 
+
+    The version of the OpenAPI document: v1.0.0
+    Generated by OpenAPI Generator (https://openapi-generator.tech)
+
+    Do not edit the class manually.
+"""  # noqa: E501
+
+
+from __future__ import annotations
+import pprint
+import re  # noqa: F401
+import json
+
+from pydantic import BaseModel, ConfigDict, Field, StrictStr
+from typing import Any, ClassVar, Dict, List, Optional
+from typing import Optional, Set
+from typing_extensions import Self
+
+class CreateChatSessionRequest(BaseModel):
+    """
+    CreateChatSessionRequest
+    """ # noqa: E501
+    workspace: Optional[StrictStr] = Field(default=None, description="Workspace to be associated with the chat session. If not provided, the collection's workspace or default workspace will be used.")
+    __properties: ClassVar[List[str]] = ["workspace"]
+
+    model_config = ConfigDict(
+        populate_by_name=True,
+        validate_assignment=True,
+        protected_namespaces=(),
+    )
+
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.model_dump(by_alias=True))
+
+    def to_json(self) -> str:
+        """Returns the JSON representation of the model using alias"""
+        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
+        return json.dumps(self.to_dict())
+
+    @classmethod
+    def from_json(cls, json_str: str) -> Optional[Self]:
+        """Create an instance of CreateChatSessionRequest from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Return the dictionary representation of the model using alias.
+
+        This has the following differences from calling pydantic's
+        `self.model_dump(by_alias=True)`:
+
+        * `None` is only added to the output dict for nullable fields that
+          were set at model initialization. Other fields with value `None`
+          are ignored.
+        """
+        excluded_fields: Set[str] = set([
+        ])
+
+        _dict = self.model_dump(
+            by_alias=True,
+            exclude=excluded_fields,
+            exclude_none=True,
+        )
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
+        """Create an instance of CreateChatSessionRequest from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "workspace": obj.get("workspace")
+        })
+        return _obj
+
+