[8.0.6] standardise tt.ModelInterface

Author: yashbonde

docs/changelog.rst

@@ -7,6 +7,11 @@ minor versions.
 
 All relevant steps to be taken will be mentioned here.
 
+8.0.6
+-----
+
+- Standardise all the implementations of the ``tuneapi.types.chats.ModelInterface``
+
 8.0.5
 -----
 

docs/conf.py

@@ -13,7 +13,7 @@
 project = "tuneapi"
 copyright = "2024-2025, Frello Technologies"
 author = "Frello Technologies"
-release = "8.0.5"
+release = "8.0.6"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "tuneapi"
-version = "8.0.5"
+version = "8.0.6"
 description = "Tune AI APIs."
 authors = ["Frello Technology Private Limited <[email protected]>"]
 license = "MIT"

tuneapi/apis/model_gemini.py

@@ -257,13 +257,14 @@ def stream_chat(
         self,
         chats: tt.Thread | str,
         model: Optional[str] = None,
-        max_tokens: int = 4096,
+        max_tokens: int = None,
         temperature: float = 1,
         token: Optional[str] = None,
-        debug: bool = False,
+        timeout=(5, 60),
+        usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
         raw: bool = False,
-        timeout=(5, 60),
         **kwargs,
     ):
         url, headers, data = self._process_input(
@@ -297,11 +298,13 @@ def chat(
         self,
         chats: tt.Thread | str,
         model: Optional[str] = None,
-        max_tokens: int = 4096,
+        max_tokens: int = None,
         temperature: float = 1,
         token: Optional[str] = None,
-        timeout=None,
+        usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
+        timeout=(5, 60),
         **kwargs,
     ) -> Any:
         output = ""
@@ -338,10 +341,10 @@ async def stream_chat_async(
         max_tokens: int = 4096,
         temperature: float = 1,
         token: Optional[str] = None,
-        timeout=(5, 60),
         raw: bool = False,
         debug: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        timeout=(5, 60),
         **kwargs,
     ):
         url, headers, data = self._process_input(
@@ -383,8 +386,8 @@ async def chat_async(
         max_tokens: int = None,
         temperature: float = 1,
         token: Optional[str] = None,
-        timeout=None,
         extra_headers: Optional[Dict[str, str]] = None,
+        timeout=(5, 60),
         **kwargs,
     ) -> Any:
         output = ""

tuneapi/apis/model_openai.py

@@ -249,13 +249,13 @@ def stream_chat(
         model: Optional[str] = None,
         max_tokens: int = None,
         temperature: float = 1,
-        parallel_tool_calls: bool = False,
         token: Optional[str] = None,
         timeout=(5, 60),
         usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
         debug: bool = False,
         raw: bool = False,
+        parallel_tool_calls: bool = False,
         **kwargs,
     ):
         headers, data = self._process_input(
@@ -295,10 +295,12 @@ def chat(
         model: Optional[str] = None,
         max_tokens: int = None,
         temperature: float = 1,
-        parallel_tool_calls: bool = False,
         token: Optional[str] = None,
         usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
+        timeout=(5, 60),
+        parallel_tool_calls: bool = False,
         **kwargs,
     ) -> Any:
         output = ""
@@ -313,6 +315,8 @@ def chat(
                 token=token,
                 extra_headers=extra_headers,
                 raw=False,
+                debug=debug,
+                timeout=timeout,
                 **kwargs,
             ):
                 if isinstance(x, dict):
@@ -340,11 +344,11 @@ async def stream_chat_async(
         temperature: float = 1,
         parallel_tool_calls: bool = False,
         token: Optional[str] = None,
-        timeout=(5, 60),
         usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
         debug: bool = False,
         raw: bool = False,
+        timeout=(5, 60),
         **kwargs,
     ):
         headers, data = self._process_input(
@@ -391,6 +395,7 @@ async def chat_async(
         token: Optional[str] = None,
         usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        timeout=(5, 60),
         **kwargs,
     ) -> Any:
         output = ""
@@ -404,6 +409,7 @@ async def chat_async(
             token=token,
             extra_headers=extra_headers,
             raw=False,
+            timeout=timeout,
             **kwargs,
         ):
             if isinstance(x, dict):
@@ -1208,6 +1214,7 @@ def __init__(
         base_url: str = "https://api.mistral.ai/v1/chat/completions",
         extra_headers: Optional[Dict[str, str]] = None,
         api_token: Optional[str] = None,
+        **kwargs,
     ):
         super().__init__(
             id=id,
@@ -1247,6 +1254,7 @@ def __init__(
         base_url: str = "https://api.groq.com/openai/v1/chat/completions",
         extra_headers: Optional[Dict[str, str]] = None,
         api_token: Optional[str] = None,
+        **kwargs,
     ):
         super().__init__(
             id=id,
@@ -1287,6 +1295,7 @@ def __init__(
         org_id: Optional[str] = None,
         extra_headers: Optional[Dict[str, str]] = None,
         api_token: Optional[str] = None,
+        **kwargs,
     ):
         if extra_headers is None:
             extra_headers = {}
@@ -1348,6 +1357,7 @@ def __init__(
         self,
         id: str,
         base_url: str = "http://localhost:11434/v1/chat/completions",
+        **kwargs,
     ):
         super().__init__(
             id=id,

tuneapi/apis/turbo.py

@@ -55,10 +55,11 @@ def distributed_chat(
         TypeError: If model is not an instance of ModelInterface
 
     Example:
-        >>> model = ChatModel(api_token="...")
+        >>> from tuneapi import ta, tt
+        >>> model = ta.Gemini()
         >>> prompts = [
-        ...     Thread([Message("What is 2+2?")]),
-        ...     Thread([Message("What is Python?")])
+        ...     tt.Thread([tt.human("What is 2+2?")]),
+        ...     tt.Thread([tt.human("What is Python?")])
         ... ]
         >>> responses = distributed_chat(model, prompts, max_threads=5)
         >>> for prompt, response in zip(prompts, responses):

tuneapi/types/chats.py

@@ -322,56 +322,67 @@ def set_api_token(self, token: str) -> None:
 
     def stream_chat(
         self,
-        chats: "Thread",
+        chats: Union["Thread", str],
         model: Optional[str] = None,
-        max_tokens: int = 1024,
+        max_tokens: int = None,
         temperature: float = 1,
         token: Optional[str] = None,
-        timeout=(5, 60),
-        raw: bool = False,
-        debug: bool = False,
+        usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
+        raw: bool = False,
+        timeout=(5, 60),
+        **kwargs,
     ):
         """This is the blocking function to stream chat with the model where each token is iteratively generated"""
         raise NotImplementedError("This model has no operation for this.")
 
     def chat(
         self,
-        chats: "Thread",
+        chats: Union["Thread", str],
         model: Optional[str] = None,
-        max_tokens: int = 1024,
+        max_tokens: int = None,
         temperature: float = 1,
+        parallel_tool_calls: bool = False,
         token: Optional[str] = None,
-        timeout=(5, 30),
+        usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
+        timeout=(5, 60),
         **kwargs,
     ) -> str | Dict[str, Any]:
         """This is the blocking function to block chat with the model"""
         raise NotImplementedError("This model has no operation for this.")
 
     async def stream_chat_async(
         self,
-        chats: "Thread",
+        chats: Union["Thread", str],
         model: Optional[str] = None,
-        max_tokens: int = 1024,
+        max_tokens: int = None,
         temperature: float = 1,
         token: Optional[str] = None,
-        timeout=(5, 30),
+        usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
+        raw: bool = False,
+        timeout=(5, 60),
         **kwargs,
     ) -> str | Dict[str, Any]:
         """This is the async function to stream chat with the model where each token is iteratively generated"""
         raise NotImplementedError("This model has no operation for this.")
 
     async def chat_async(
         self,
-        chats: "Thread",
+        chats: Union["Thread", str],
         model: Optional[str] = None,
-        max_tokens: int = 1024,
+        max_tokens: int = None,
         temperature: float = 1,
+        parallel_tool_calls: bool = False,
         token: Optional[str] = None,
-        timeout=(5, 30),
+        usage: bool = False,
         extra_headers: Optional[Dict[str, str]] = None,
+        debug: bool = False,
+        timeout=(5, 60),
         **kwargs,
     ) -> str | Dict[str, Any]:
         """This is the async function to block chat with the model"""
@@ -384,6 +395,7 @@ def distributed_chat(
         max_threads: int = 10,
         retry: int = 3,
         pbar=True,
+        debug=False,
         **kwargs,
     ):
         """This is the blocking function to chat with the model in a distributed manner"""
@@ -396,6 +408,7 @@ async def distributed_chat_async(
         max_threads: int = 10,
         retry: int = 3,
         pbar=True,
+        debug=False,
         **kwargs,
     ):
         """This is the async function to chat with the model in a distributed manner"""