h2ogpte 1.6.41rc5__py3-none-any.whl → 1.6.43__py3-none-any.whl

h2ogpte/rest_sync/models/update_collection_workspace_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
+from typing import Optional, Set
+from typing_extensions import Self
+
+class UpdateCollectionWorkspaceRequest(BaseModel):
+    """
+    UpdateCollectionWorkspaceRequest
+    """ # noqa: E501
+    workspace: StrictStr = Field(description="The name of the workspace to be associated with the collection.")
+    __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 UpdateCollectionWorkspaceRequest 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 UpdateCollectionWorkspaceRequest 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
+
+

h2ogpte/rest_sync/models/update_extractor_privacy_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, StrictBool
+from typing import Any, ClassVar, Dict, List
+from typing import Optional, Set
+from typing_extensions import Self
+
+class UpdateExtractorPrivacyRequest(BaseModel):
+    """
+    UpdateExtractorPrivacyRequest
+    """ # noqa: E501
+    is_public: StrictBool = Field(description="A flag specifying whether a extractor is private or public.")
+    __properties: ClassVar[List[str]] = ["is_public"]
+
+    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 UpdateExtractorPrivacyRequest 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 UpdateExtractorPrivacyRequest from a dict"""
+        if obj is None:
+            return None
+
+        if not isinstance(obj, dict):
+            return cls.model_validate(obj)
+
+        _obj = cls.model_validate({
+            "is_public": obj.get("is_public")
+        })
+        return _obj
+
+

h2ogpte/session.py

@@ -149,6 +149,7 @@ class Session:
                     ssl_context=ssl_context,
                     open_timeout=self._open_timeout,
                     close_timeout=self._close_timeout,
+                    max_size=5 * 1024 * 1024,  # 5 MB limit for large responses
                 )
                 return self._connection
             except (ConnectionClosedError, InvalidURI, InvalidHandshake) as e:
@@ -261,6 +262,7 @@ class Session:
                     json_preserve_system_prompt (bool, default: None) — Whether to preserve system prompt in JSON response.
                     client_metadata (str, default: None) — Additional metadata to send with the request.
                     min_chars_per_yield (int, default: 1) — Minimum characters to yield in streaming response.
+                    reasoning_effort (int, 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: Optional dictionary
                         max_cost (float) - 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 (float) - 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.
@@ -276,6 +278,14 @@ class Session:
                     agent_timeout (int, default: None) — Timeout in seconds for each agent turn.
                     agent_total_timeout (int, default: 3600) — Total timeout in seconds for all agent processing.
                     agent_min_time (int, default: 0) — Minimum time in seconds for all agent processing.
+                    final_answer_guidelines_mode (str, default: "auto") — Mode for formatting agent final answers. Options:
+                        * auto: chooses "detailed" for now, but may later adapt
+                        * detailed: full deep_research like final answer guidelines
+                        * detailed_no_file_links: Like detailed, but without files provided to LLM for final answer so LLM doesn't over-emphasize showing file links except what it auto-decides from chat history
+                        * detailed_no_image_links: Like detailed, but without images provided to LLM for final answer so LLM doesn't over-emphasize showing image links except what it auto-decides from chat history
+                        * detailed_no_links: Like detailed, but without files or images provided to LLM for final answer so LLM doesn't over-emphasize showing file or image links except what it auto-decides from chat history
+                        * file_template: Use file final_answer_guidelines_template.txt (in agent_files or original_agent_files) that has optional f-strings: agent_accuracy, new_image_files, new_non_image_files, formatted_references
+                        * raw_LLM: Bypasses final answer guidelines and just stops after own final LLM response that has no executable code.
                     agent_code_writer_system_message (str, default: None) — System message for agent code writer.
                     agent_num_executable_code_blocks_limit (int, default: 1) — Maximum number of executable code blocks.
                     agent_system_site_packages (bool, default: True) — Whether agent has access to system site packages.
@@ -288,6 +298,8 @@ class Session:
                     agent_planning_forced_mode (Optional[bool], default: None) — Whether to force planning mode for agent.
                     agent_too_soon_forced_mode (Optional[bool], default: None) — Whether to force "too soon" mode for agent.
                     agent_critique_forced_mode (Optional[int], default: None) — Whether to force critique mode for agent.
+                    agent_query_understanding_parallel_calls (Optional[int], default: None) — Number of parallel calls for query understanding.
+                    tool_building_mode (Optional[str], default: None) — Mode for tool building configuration.
                     agent_stream_files (bool, default: True) — Whether to stream files from agent.
             self_reflection_config:
                 Dictionary of arguments for self-reflection, can contain the following
@@ -426,7 +438,7 @@ class Session:
         deadline = time.time() + timeout
 
         current_retries = 0
-        while current_retries < retries:
+        while current_retries <= retries:
             try:
                 self.connection.send(serialize(request))
                 break
@@ -441,7 +453,7 @@ class Session:
 
         current_retries = 0
         request_id: Optional[str] = None
-        while current_retries < retries:
+        while current_retries <= retries:
             try:
                 while True:
                     try:

h2ogpte/session_async.py

@@ -29,6 +29,7 @@ from h2ogpte.types import (
     ChatRequest,
     ChatResponse,
     SessionError,
+    PartialChatMessage,
 )
 from h2ogpte.errors import (
     UnauthorizedError,
@@ -111,7 +112,9 @@ class SessionAsync:
         metadata_filter: Optional[Dict[str, Any]] = None,
         timeout: Optional[float] = None,
         retries: int = 3,
-        callback: Optional[Callable[[ChatMessage], None]] = None,
+        callback: Optional[
+            Callable[[Union[ChatMessage, PartialChatMessage]], None]
+        ] = None,
     ) -> ChatMessage:
         """Retrieval-augmented generation for a query on a collection.
         Finds a collection of chunks relevant to the query using similarity scores.
@@ -172,6 +175,7 @@ class SessionAsync:
                     json_preserve_system_prompt (bool, default: None) — Whether to preserve system prompt in JSON response.
                     client_metadata (str, default: None) — Additional metadata to send with the request.
                     min_chars_per_yield (int, default: 1) — Minimum characters to yield in streaming response.
+                    reasoning_effort (int, 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: Optional dictionary
                         max_cost (float) - 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 (float) - 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.
@@ -187,6 +191,14 @@ class SessionAsync:
                     agent_timeout (int, default: None) — Timeout in seconds for each agent turn.
                     agent_total_timeout (int, default: 3600) — Total timeout in seconds for all agent processing.
                     agent_min_time (int, default: 0) — Minimum time in seconds for all agent processing.
+                    final_answer_guidelines_mode (str, default: "auto") — Mode for formatting agent final answers. Options:
+                        * auto: chooses "detailed" for now, but may later adapt
+                        * detailed: full deep_research like final answer guidelines
+                        * detailed_no_file_links: Like detailed, but without files provided to LLM for final answer so LLM doesn't over-emphasize showing file links except what it auto-decides from chat history
+                        * detailed_no_image_links: Like detailed, but without images provided to LLM for final answer so LLM doesn't over-emphasize showing image links except what it auto-decides from chat history
+                        * detailed_no_links: Like detailed, but without files or images provided to LLM for final answer so LLM doesn't over-emphasize showing file or image links except what it auto-decides from chat history
+                        * file_template: Use file final_answer_guidelines_template.txt (in agent_files or original_agent_files) that has optional f-strings: agent_accuracy, new_image_files, new_non_image_files, formatted_references
+                        * raw_LLM: Bypasses final answer guidelines and just stops after own final LLM response that has no executable code.
                     agent_code_writer_system_message (str, default: None) — System message for agent code writer.
                     agent_num_executable_code_blocks_limit (int, default: 1) — Maximum number of executable code blocks.
                     agent_system_site_packages (bool, default: True) — Whether agent has access to system site packages.
@@ -199,6 +211,8 @@ class SessionAsync:
                     agent_planning_forced_mode (Optional[bool], default: None) — Whether to force planning mode for agent.
                     agent_too_soon_forced_mode (Optional[bool], default: None) — Whether to force "too soon" mode for agent.
                     agent_critique_forced_mode (Optional[int], default: None) — Whether to force critique mode for agent.
+                    agent_query_understanding_parallel_calls (Optional[int], default: None) — Number of parallel calls for query understanding.
+                    tool_building_mode (Optional[str], default: None) — Mode for tool building configuration.
                     agent_stream_files (bool, default: True) — Whether to stream files from agent.
             self_reflection_config:
                 Dictionary of arguments for self-reflection, can contain the following
@@ -336,7 +350,7 @@ class SessionAsync:
             return info.message
 
         current_retries = 0
-        while current_retries < retries:
+        while current_retries <= retries:
             try:
                 return await asyncio.wait_for(send_recv_query(), timeout=timeout)
             except (ConnectionClosed, ConnectionClosedError) as e:
@@ -423,9 +437,17 @@ class SessionAsync:
         elif not info.message.id:
             info.message.id = info.message_id
         info.message.content = res.body
-        if info.callback:
-            info.callback(info.message)
+        if res.t in ["cp", "cm"] and info.callback:
+            info.callback(
+                PartialChatMessage(
+                    id=info.message.id,
+                    content=info.message.content,
+                    reply_to=info.message.reply_to,
+                )
+            )
         if res.t == "ca":
+            if info.callback:
+                info.callback(info.message)
             info.done = True
 
     async def connect(self):
@@ -456,6 +478,7 @@ class SessionAsync:
                     open_timeout=self._open_timeout,
                     close_timeout=self._close_timeout,
                     ssl=ssl_context,
+                    max_size=5 * 1024 * 1024,  # 5 MB limit for large responses
                 )
                 return self._websocket
             except (ConnectionClosedError, InvalidURI, InvalidHandshake) as e:
@@ -511,10 +534,14 @@ class _QueryInfo:
     def __init__(
         self,
         correlation_id: str,
-        callback: Optional[Callable[[ChatMessage], None]] = None,
+        callback: Optional[
+            Callable[[Union[ChatMessage, PartialChatMessage]], None]
+        ] = None,
     ):
         self.correlation_id = correlation_id
-        self.callback: Optional[Callable[[ChatMessage], None]] = callback
+        self.callback: Optional[
+            Callable[[Union[ChatMessage, PartialChatMessage]], None]
+        ] = callback
         self.query_id: Optional[str] = None
         self.message_id: Optional[str] = None
         self.done: bool = False

h2ogpte/types.py

@@ -1,4 +1,4 @@
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 from datetime import datetime
 from enum import Enum
 from pydantic import BaseModel
@@ -11,6 +11,7 @@ class JobKind(str, Enum):
     IngestAgentOnlyToStandardJob = "IngestAgentOnlyToStandardJob"
     IngestFromFileSystemJob = "IngestFromFileSystemJob"
     IngestFromCloudStorageJob = "IngestFromCloudStorageJob"
+    IngestWithScheduledConnectorJob = "IngestWithScheduledConnectorJob"
     IngestPlainTextJob = "IngestPlainTextJob"
     IngestUploadsJob = "IngestUploadsJob"
     IngestWebsiteJob = "IngestWebsiteJob"
@@ -150,6 +151,7 @@ class ChatSessionInfo(BaseModel):
     collection_name: Optional[str] = None
     prompt_template_id: Optional[str] = None
     updated_at: datetime
+    workspace: Optional[str] = None
 
 
 class QuestionReplyData(BaseModel):
@@ -244,6 +246,7 @@ class Collection(BaseModel):
     expiry_date: Optional[datetime] = None
     inactivity_interval: Optional[int] = None
     size_limit: Optional[int] = None
+    workspace: Optional[str] = None
 
 
 class CollectionCount(BaseModel):
@@ -267,6 +270,7 @@ class CollectionInfo(BaseModel):
     archived_at: Optional[datetime] = None
     size_limit: Optional[int] = None
     metadata_dict: Optional[dict] = None
+    workspace: Optional[str] = None
 
 
 class Document(BaseModel):
@@ -300,6 +304,7 @@ class Extractor(BaseModel):
     llm: Optional[str] = None
     # can't use name schema as it conflicts with BaseModel's internals
     extractor_schema: Optional[Dict[str, Any]] = None
+    is_public: bool
 
 
 class Tag(BaseModel):
@@ -476,6 +481,7 @@ class Meta(BaseModel):
     user_configs: List[ConfigItem]
     picture: Optional[str]
     groups: Optional[List[str]]
+    workspaces: Optional[List[str]]
     permissions: List[str]
     ui_config: MetaUIConfig
 
@@ -614,6 +620,7 @@ class ChatAcknowledgement:
     message_id: str
     username: str
     body: str
+    use_agent: Optional[bool] = None
 
 
 @dataclass
@@ -624,6 +631,7 @@ class ChatResponse:
     reply_to_id: str
     body: str
     error: str
+    meta: List[Any] = field(default_factory=list)
 
 
 @dataclass

{h2ogpte-1.6.41rc5.dist-info → h2ogpte-1.6.43.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: h2ogpte
-Version: 1.6.41rc5
+Version: 1.6.43
 Summary: Client library for Enterprise h2oGPTe
 Author-email: "H2O.ai, Inc." <support@h2o.ai>
 Project-URL: Source, https://github.com/h2oai/h2ogpte
@@ -34,6 +34,10 @@ Requires-Dist: h2o_authn
 Requires-Dist: packaging
 Requires-Dist: filetype
 Requires-Dist: tzlocal
+Requires-Dist: rich>=13.7.0
+Requires-Dist: pathspec>=0.12.0
+Requires-Dist: gitpython>=3.1.40
+Requires-Dist: toml>=0.10.2
 
 ### Python Client and Documentation