not-again-ai 0.7.0__py3-none-any.whl → 0.8.1__py3-none-any.whl

not_again_ai/llm/chat_completion.py

@@ -0,0 +1,76 @@
+from typing import Any
+
+from ollama import Client
+from openai import OpenAI
+
+from not_again_ai.llm.ollama import chat_completion as chat_completion_ollama
+from not_again_ai.llm.openai_api import chat_completion as chat_completion_openai
+
+
+def chat_completion(
+    messages: list[dict[str, Any]],
+    model: str,
+    client: OpenAI | Client,
+    max_tokens: int | None = None,
+    temperature: float = 0.7,
+    json_mode: bool = False,
+    seed: int | None = None,
+    **kwargs: Any,
+) -> dict[str, Any]:
+    """Creates a common wrapper around chat completion models from different providers.
+    Currently supports the OpenAI API and Ollama local models.
+    All input parameters are supported by all providers in similar ways and the output is standardized.
+
+    Args:
+        messages (list[dict[str, Any]]): A list of messages to send to the model.
+        model (str): The model name to use.
+        client (OpenAI | Client): The client object to use for chat completion.
+        max_tokens (int, optional): The maximum number of tokens to generate.
+        temperature (float, optional): The temperature of the model. Increasing the temperature will make the model answer more creatively.
+        json_mode (bool, optional): This will structure the response as a valid JSON object.
+        seed (int, optional): The seed to use for the model for reproducible outputs.
+
+    Returns:
+        dict[str, Any]: A dictionary with the following keys
+            message (str | dict): The content of the generated assistant message.
+                If json_mode is True, this will be a dictionary.
+            completion_tokens (int): The number of tokens used by the model to generate the completion.
+            extras (dict): This will contain any additional fields returned by corresponding provider.
+    """
+    # Determine which chat_completion function to call based on the client type
+    if isinstance(client, OpenAI):
+        response = chat_completion_openai.chat_completion(
+            messages=messages,
+            model=model,
+            client=client,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            json_mode=json_mode,
+            seed=seed,
+            **kwargs,
+        )
+    elif isinstance(client, Client):
+        response = chat_completion_ollama.chat_completion(
+            messages=messages,
+            model=model,
+            client=client,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            json_mode=json_mode,
+            seed=seed,
+            **kwargs,
+        )
+    else:
+        raise ValueError("Invalid client type")
+
+    # Parse the responses to be consistent
+    response_data = {}
+    response_data["message"] = response.get("message", None)
+    response_data["completion_tokens"] = response.get("completion_tokens", None)
+
+    # Return any additional fields from the response in an "extras" dictionary
+    extras = {k: v for k, v in response.items() if k not in response_data}
+    if extras:
+        response_data["extras"] = extras
+
+    return response_data

not_again_ai/llm/{openai → openai_api}/context_management.py

@@ -1,6 +1,6 @@
 import copy
 
-from not_again_ai.llm.openai.tokens import num_tokens_from_messages, truncate_str
+from not_again_ai.llm.openai_api.tokens import num_tokens_from_messages, truncate_str
 
 
 def _inject_variable(

not_again_ai/llm/{openai → openai_api}/tokens.py

@@ -82,6 +82,8 @@ def num_tokens_from_messages(messages: list[dict[str, str]], model: str = "gpt-3
         "gpt-4-0125-preview",
         "gpt-4-turbo",
         "gpt-4-turbo-2024-04-09",
+        "gpt-4o",
+        "gpt-4o-2024-05-13",
     }:
         tokens_per_message = 3  # every message follows <|start|>{role/name}\n{content}<|end|>\n
         tokens_per_name = 1  # if there's a name, the role is omitted
@@ -91,6 +93,8 @@ def num_tokens_from_messages(messages: list[dict[str, str]], model: str = "gpt-3
     # Approximate catch-all. Assumes future versions of 3.5 and 4 will have the same token counts as the 0613 versions.
     elif "gpt-3.5-turbo" in model:
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613")
+    elif "gpt-4o" in model:
+        return num_tokens_from_messages(messages, model="gpt-4o-2024-05-13")
     elif "gpt-4" in model:
         return num_tokens_from_messages(messages, model="gpt-4-0613")
     else:

{not_again_ai-0.7.0.dist-info → not_again_ai-0.8.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: not-again-ai
-Version: 0.7.0
+Version: 0.8.1
 Summary: Designed to once and for all collect all the little things that come up over and over again in AI projects and put them in one place.
 Home-page: https://github.com/DaveCoDev/not-again-ai
 License: MIT
@@ -21,14 +21,14 @@ Provides-Extra: llm
 Provides-Extra: statistics
 Provides-Extra: viz
 Requires-Dist: numpy (>=1.26.4,<2.0.0) ; extra == "statistics" or extra == "viz"
-Requires-Dist: ollama (>=0.1.9,<0.2.0) ; extra == "llm"
-Requires-Dist: openai (>=1.25.1,<2.0.0) ; extra == "llm"
+Requires-Dist: ollama (>=0.2.0,<0.3.0) ; extra == "llm"
+Requires-Dist: openai (>=1.29.0,<2.0.0) ; extra == "llm"
 Requires-Dist: pandas (>=2.2.2,<3.0.0) ; extra == "viz"
 Requires-Dist: python-liquid (>=1.12.1,<2.0.0) ; extra == "llm"
 Requires-Dist: scikit-learn (>=1.4.2,<2.0.0) ; extra == "statistics"
 Requires-Dist: scipy (>=1.13.0,<2.0.0) ; extra == "statistics"
 Requires-Dist: seaborn (>=0.13.2,<0.14.0) ; extra == "viz"
-Requires-Dist: tiktoken (>=0.6.0,<0.7.0) ; extra == "llm"
+Requires-Dist: tiktoken (>=0.7.0,<0.8.0) ; extra == "llm"
 Project-URL: Documentation, https://github.com/DaveCoDev/not-again-ai
 Project-URL: Repository, https://github.com/DaveCoDev/not-again-ai
 Description-Content-Type: text/markdown

{not_again_ai-0.7.0.dist-info → not_again_ai-0.8.1.dist-info}/RECORD

@@ -3,17 +3,18 @@ not_again_ai/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 not_again_ai/base/file_system.py,sha256=KNQmacO4Q__CQuq2oPzWrg3rQO48n3evglc9bNiP7KM,949
 not_again_ai/base/parallel.py,sha256=fcYhKBYBWvob84iKp3O93wvFFdXeidljZsShgBLTNGA,3448
 not_again_ai/llm/__init__.py,sha256=_wNUL6FDaT369Z8W48FsaC_NkcOZ-ib2MMUvnaLOS-0,451
+not_again_ai/llm/chat_completion.py,sha256=a5jqce5qQzwdDFK8W7XRqGjTdFHAqKcWDmrTDtKls9U,3070
 not_again_ai/llm/ollama/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 not_again_ai/llm/ollama/chat_completion.py,sha256=EKvqpHztsEISH9skYaLgKABEeoDhUlUyrakz_v6zvTw,3682
 not_again_ai/llm/ollama/ollama_client.py,sha256=dktyw7aKFq4EA3dU7Le5UpfsSq3Oh_POmYSrAI4qLi8,765
 not_again_ai/llm/ollama/service.py,sha256=XczbxISTAp4KHnIkqRZaMsfBohH-TAHrjZ8T9x3cRAY,2900
-not_again_ai/llm/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-not_again_ai/llm/openai/chat_completion.py,sha256=UJljrAV1lS2UvA5Sjt6N7S-9DaAgKRBpswLNDDP9RBI,8623
-not_again_ai/llm/openai/context_management.py,sha256=Aj3vIsKgTlfja101ybYg3Ps24LF2BoJ23KjeqkyEEU0,3431
-not_again_ai/llm/openai/embeddings.py,sha256=4OBnxZicrY6q4dQhuPqMdAnifyjwrsKMTDj-kVre0yc,2500
-not_again_ai/llm/openai/openai_client.py,sha256=6pZw2xw9X-ceV22rhApwFJ2tAKCxi-SxkjxBsTBZ2Nw,2470
-not_again_ai/llm/openai/prompts.py,sha256=7cDfvIKCTYM0t5lK34FLLqYf-SR_cynDXIXw3zWDizA,7094
-not_again_ai/llm/openai/tokens.py,sha256=2WGHzZJ0mIFAGpkuS_otjFzwhqjaSMgLoP2FVMnJTiE,4301
+not_again_ai/llm/openai_api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+not_again_ai/llm/openai_api/chat_completion.py,sha256=UJljrAV1lS2UvA5Sjt6N7S-9DaAgKRBpswLNDDP9RBI,8623
+not_again_ai/llm/openai_api/context_management.py,sha256=SKksCHs-C-UXtSksvXSvWWR4eeUyuyVc6XIhGgqJUF4,3435
+not_again_ai/llm/openai_api/embeddings.py,sha256=4OBnxZicrY6q4dQhuPqMdAnifyjwrsKMTDj-kVre0yc,2500
+not_again_ai/llm/openai_api/openai_client.py,sha256=6pZw2xw9X-ceV22rhApwFJ2tAKCxi-SxkjxBsTBZ2Nw,2470
+not_again_ai/llm/openai_api/prompts.py,sha256=7cDfvIKCTYM0t5lK34FLLqYf-SR_cynDXIXw3zWDizA,7094
+not_again_ai/llm/openai_api/tokens.py,sha256=pshGOSYAKvDAe2vnkib_vwENT5on8xQznC8ErLvciK4,4453
 not_again_ai/py.typed,sha256=UaCuPFa3H8UAakbt-5G8SPacldTOGvJv18pPjUJ5gDY,93
 not_again_ai/statistics/__init__.py,sha256=gA8r9JQFbFSN0ykrHy4G1IQgcky4f2eM5Oo24oVI5Ik,466
 not_again_ai/statistics/dependence.py,sha256=yZDk_e3ng96mp4hu8dDtQ0-uIn6KdSuGRS9uyM0O3x0,4429
@@ -23,8 +24,8 @@ not_again_ai/viz/distributions.py,sha256=OyWwJaNI6lMRm_iSrhq-CORLNvXfeuLSgDtVo3u
 not_again_ai/viz/scatterplot.py,sha256=eBtIf0Tf_1EcN-akRNJgvwLU0zpRx1zOl0VF9QTnbZA,2290
 not_again_ai/viz/time_series.py,sha256=pOGZqXp_2nd6nKo-PUQNCtmMh__69jxQ6bQibTGLwZA,5212
 not_again_ai/viz/utils.py,sha256=hN7gwxtBt3U6jQni2K8j5m5pCXpaJDoNzGhBBikEU28,238
-not_again_ai-0.7.0.dist-info/LICENSE,sha256=btjOgNGpp-ux5xOo1Gx1MddxeWtT9sof3s3Nui29QfA,1071
-not_again_ai-0.7.0.dist-info/METADATA,sha256=58-RwfLn8dNRqMTK2Qp8gcPSAYAes3OFVBFbSLobvpo,14203
-not_again_ai-0.7.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-not_again_ai-0.7.0.dist-info/entry_points.txt,sha256=EMJegugnmJUd-jMUA_qIRMIPAasbei8gP6O4-ER0BxQ,61
-not_again_ai-0.7.0.dist-info/RECORD,,
+not_again_ai-0.8.1.dist-info/LICENSE,sha256=btjOgNGpp-ux5xOo1Gx1MddxeWtT9sof3s3Nui29QfA,1071
+not_again_ai-0.8.1.dist-info/METADATA,sha256=XjBBZSVDW8tdwDy8hJY6R-xXo9Mec2i6N-5YFs0eRW8,14203
+not_again_ai-0.8.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+not_again_ai-0.8.1.dist-info/entry_points.txt,sha256=EMJegugnmJUd-jMUA_qIRMIPAasbei8gP6O4-ER0BxQ,61
+not_again_ai-0.8.1.dist-info/RECORD,,