not-again-ai 0.10.2__tar.gz → 0.11.0__tar.gz

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: not-again-ai
-Version: 0.10.2
+Version: 0.11.0
 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
@@ -21,18 +21,18 @@ Provides-Extra: llm
 Provides-Extra: local-llm
 Provides-Extra: statistics
 Provides-Extra: viz
-Requires-Dist: jinja2 (==3.1.4) ; extra == "local-llm"
+Requires-Dist: jinja2 (>=3.1,<4.0) ; extra == "local-llm"
 Requires-Dist: loguru (==0.7.2)
-Requires-Dist: numpy (==1.26.4) ; extra == "statistics" or extra == "viz"
-Requires-Dist: ollama (==0.2.1) ; extra == "local-llm"
-Requires-Dist: openai (==1.35.10) ; extra == "llm"
-Requires-Dist: pandas (==2.2.2) ; extra == "viz"
-Requires-Dist: python-liquid (==1.12.1) ; extra == "llm"
-Requires-Dist: scikit-learn (==1.5.1) ; extra == "statistics"
-Requires-Dist: scipy (==1.14.0) ; extra == "statistics"
-Requires-Dist: seaborn (==0.13.2) ; extra == "viz"
-Requires-Dist: tiktoken (==0.7.0) ; extra == "llm"
-Requires-Dist: transformers (==4.42.3) ; extra == "local-llm"
+Requires-Dist: numpy (>=1.26,<2.0) ; extra == "statistics" or extra == "viz"
+Requires-Dist: ollama (>=0.3,<0.4) ; extra == "local-llm"
+Requires-Dist: openai (>=1.37,<2.0) ; extra == "llm"
+Requires-Dist: pandas (>=2.2,<3.0) ; extra == "viz"
+Requires-Dist: python-liquid (>=1.12,<2.0) ; extra == "llm"
+Requires-Dist: scikit-learn (>=1.5,<2.0) ; extra == "statistics"
+Requires-Dist: scipy (>=1.14,<2.0) ; extra == "statistics"
+Requires-Dist: seaborn (>=0.13,<0.14) ; extra == "viz"
+Requires-Dist: tiktoken (>=0.7,<0.8) ; extra == "llm"
+Requires-Dist: transformers (>=4.43,<5.0) ; extra == "local-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
@@ -86,7 +86,8 @@ The package is split into subpackages, so you can install only the parts you nee
             ...
             Environment="OLLAMA_HOST=0.0.0.0"
             ```
-    1. HuggingFace transformers and other requirements are hardware dependent so for providers other than Ollama, this only installs some generic dependencies. Check the [notebooks](notebooks/local_llm/) for more details on what is available and how to install it.
+        1. It is recommended to always have the latest version of Ollama. To update Ollama check the [docs](https://github.com/ollama/ollama/blob/main/docs/). The command for Linux is: `curl -fsSL https://ollama.com/install.sh | sh`
+    2. HuggingFace transformers and other requirements are hardware dependent so for providers other than Ollama, this only installs some generic dependencies. Check the [notebooks](notebooks/local_llm/) for more details on what is available and how to install it.
 * **Statistics**: `pip install not_again_ai[statistics]`
 * **Visualization**: `pip install not_again_ai[viz]`
 
@@ -294,7 +295,7 @@ installed package to indicate that inline type annotations should be checked.
 
 ## Typos
 
-Checks for typos using [typos](https://github.com/crate-ci/typos)
+Check for typos using [typos](https://github.com/crate-ci/typos)
 
 ```bash
 (.venv) $ nox -s typos

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/README.md

@@ -47,7 +47,8 @@ The package is split into subpackages, so you can install only the parts you nee
             ...
             Environment="OLLAMA_HOST=0.0.0.0"
             ```
-    1. HuggingFace transformers and other requirements are hardware dependent so for providers other than Ollama, this only installs some generic dependencies. Check the [notebooks](notebooks/local_llm/) for more details on what is available and how to install it.
+        1. It is recommended to always have the latest version of Ollama. To update Ollama check the [docs](https://github.com/ollama/ollama/blob/main/docs/). The command for Linux is: `curl -fsSL https://ollama.com/install.sh | sh`
+    2. HuggingFace transformers and other requirements are hardware dependent so for providers other than Ollama, this only installs some generic dependencies. Check the [notebooks](notebooks/local_llm/) for more details on what is available and how to install it.
 * **Statistics**: `pip install not_again_ai[statistics]`
 * **Visualization**: `pip install not_again_ai[viz]`
 
@@ -255,7 +256,7 @@ installed package to indicate that inline type annotations should be checked.
 
 ## Typos
 
-Checks for typos using [typos](https://github.com/crate-ci/typos)
+Check for typos using [typos](https://github.com/crate-ci/typos)
 
 ```bash
 (.venv) $ nox -s typos

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "not-again-ai"
-version = "0.10.2"
+version = "0.11.0"
 description = "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."
 authors = ["DaveCoDev <dave.co.dev@gmail.com>"]
 license = "MIT"
@@ -29,17 +29,17 @@ python = "^3.11 || ^3.12"
 loguru = { version = "==0.7.2" }
 
 # Optional dependencies are defined here, and groupings are defined below.
-jinja2 = { version = "==3.1.4", optional = true }
-numpy = { version = "==1.26.4", optional = true }
-ollama = { version = "==0.2.1", optional = true }
-openai = { version = "==1.35.10", optional = true }
-pandas = { version = "==2.2.2", optional = true }
-python-liquid = { version = "==1.12.1", optional = true }
-scipy = { version = "==1.14.0", optional = true }
-scikit-learn = { version = "==1.5.1", optional = true }
-seaborn = { version = "==0.13.2", optional = true }
-tiktoken = { version = "==0.7.0", optional = true }
-transformers = { version = "==4.42.3", optional = true }
+jinja2 = { version = "^3.1", optional = true }
+numpy = { version = "^1.26", optional = true }
+ollama = { version = "^0.3", optional = true }
+openai = { version = "^1.37", optional = true }
+pandas = { version = "^2.2", optional = true }
+python-liquid = { version = "^1.12", optional = true }
+scipy = { version = "^1.14", optional = true }
+scikit-learn = { version = "^1.5", optional = true }
+seaborn = { version = "^0.13", optional = true }
+tiktoken = { version = "^0.7", optional = true }
+transformers = { version = "^4.43", optional = true }
 
 [tool.poetry.extras]
 llm = ["openai", "python-liquid", "tiktoken"]

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/src/not_again_ai/llm/openai_api/chat_completion.py

@@ -32,8 +32,8 @@ def chat_completion(
             https://platform.openai.com/docs/models/model-endpoint-compatibility
             for details on which models work with the Chat API.
         client (OpenAI): An instance of the OpenAI client.
-        tools (list[dict[str, Any]], optional): A list of tools the model may generate JSON inputs for.
-            Defaults to None.
+        tools (list[dict[str, Any]], optional):A list of tools the model may call.
+            Use this to provide a list of functions the model may generate JSON inputs for. Defaults to None.
         tool_choice (str, optional): The tool choice to use. Can be "auto", "required", "none", or a specific function name.
             Note the function name cannot be any of "auto", "required", or "none". Defaults to "auto".
         max_tokens (int, optional): The maximum number of tokens to generate in the chat completion.
@@ -58,21 +58,21 @@ def chat_completion(
 
     Returns:
         dict[str, Any]: A dictionary with the following keys:
-            'finish_reason' (str): The reason the model stopped generating further tokens.
+            finish_reason (str): The reason the model stopped generating further tokens.
                 Can be 'stop', 'length', or 'tool_calls'.
-            'tool_names' (list[str], optional): The names of the tools called by the model.
-            'tool_args_list' (list[dict], optional): The arguments of the tools called by the model.
-            'message' (str | dict): The content of the generated assistant message.
+            tool_names (list[str], optional): The names of the tools called by the model.
+            tool_args_list (list[dict], optional): The arguments of the tools called by the model.
+            message (str | dict): The content of the generated assistant message.
                 If json_mode is True, this will be a dictionary.
-            'logprobs' (list[dict[str, Any] | list[dict[str, Any]]]): If logprobs[1] is between 1 and 5, each element in the list
+            logprobs (list[dict[str, Any] | list[dict[str, Any]]]): If logprobs[1] is between 1 and 5, each element in the list
                 will be a list of dictionaries containing the token, logprob, and bytes for the top `logprobs[1]` logprobs. Otherwise,
                 this will be a list of dictionaries containing the token, logprob, and bytes for each token in the message.
-            'choices' (list[dict], optional): A list of chat completion choices if n > 1 where each dict contains the above fields.
-            'completion_tokens' (int): The number of tokens used by the model to generate the completion.
+            choices (list[dict], optional): A list of chat completion choices if n > 1 where each dict contains the above fields.
+            completion_tokens (int): The number of tokens used by the model to generate the completion.
                 NOTE: If n > 1 this is the sum of all completions.
-            'prompt_tokens' (int): The number of tokens in the messages sent to the model.
-            'system_fingerprint' (str, optional): If seed is set, a unique identifier for the model used to generate the response.
-            'response_duration' (float): The time, in seconds, taken to generate the response from the API.
+            prompt_tokens (int): The number of tokens in the messages sent to the model.
+            system_fingerprint (str, optional): If seed is set, a unique identifier for the model used to generate the response.
+            response_duration (float): The time, in seconds, taken to generate the response from the API.
     """
     response_format = {"type": "json_object"} if json_mode else None
 

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/src/not_again_ai/llm/openai_api/tokens.py

@@ -86,6 +86,8 @@ def num_tokens_from_messages(
         "gpt-4-turbo-2024-04-09",
         "gpt-4o",
         "gpt-4o-2024-05-13",
+        "gpt-4o-mini",
+        "gpt-4o-mini-2024-07-18",
     }:
         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

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/src/not_again_ai/local_llm/chat_completion.py

@@ -11,6 +11,7 @@ def chat_completion(
     messages: list[dict[str, Any]],
     model: str,
     client: OpenAI | Client,
+    tools: list[dict[str, Any]] | None = None,
     max_tokens: int | None = None,
     temperature: float = 0.7,
     json_mode: bool = False,
@@ -25,6 +26,8 @@ def chat_completion(
         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.
+        tools (list[dict[str, Any]], optional):A list of tools the model may call.
+            Use this to provide a list of functions the model may generate JSON inputs for. Defaults to None.
         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.
@@ -34,6 +37,9 @@ def chat_completion(
         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.
+            tool_names (list[str], optional): The names of the tools called by the model.
+                If the model does not support tools, a ResponseError is raised.
+            tool_args_list (list[dict], optional): The arguments of the tools called by the model.
             prompt_tokens (int): The number of tokens in the messages sent to the model.
             completion_tokens (int): The number of tokens used by the model to generate the completion.
             response_duration (float): The time, in seconds, taken to generate the response by using the model.
@@ -45,6 +51,7 @@ def chat_completion(
             messages=messages,
             model=model,
             client=client,
+            tools=tools,
             max_tokens=max_tokens,
             temperature=temperature,
             json_mode=json_mode,
@@ -56,6 +63,7 @@ def chat_completion(
             messages=messages,
             model=model,
             client=client,
+            tools=tools,
             max_tokens=max_tokens,
             temperature=temperature,
             json_mode=json_mode,
@@ -68,6 +76,9 @@ def chat_completion(
     # Parse the responses to be consistent
     response_data = {}
     response_data["message"] = response.get("message")
+    if response.get("tool_names") and response.get("tool_args_list"):
+        response_data["tool_names"] = response.get("tool_names")
+        response_data["tool_args_list"] = response.get("tool_args_list")
     response_data["completion_tokens"] = response.get("completion_tokens")
     response_data["prompt_tokens"] = response.get("prompt_tokens")
     response_data["response_duration"] = response.get("response_duration")

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/src/not_again_ai/local_llm/ollama/chat_completion.py

@@ -13,6 +13,7 @@ def chat_completion(
     messages: list[dict[str, Any]],
     model: str,
     client: Client,
+    tools: list[dict[str, Any]] | None = None,
     max_tokens: int | None = None,
     context_window: int | None = None,
     temperature: float = 0.8,
@@ -27,6 +28,8 @@ def chat_completion(
         messages (list[dict[str, Any]]): A list of messages to send to the model.
         model (str): The model to use.
         client (Client): The Ollama client.
+        tools (list[dict[str, Any]], optional):A list of tools the model may call.
+            Use this to provide a list of functions the model may generate JSON inputs for. Defaults to None.
         max_tokens (int, optional): The maximum number of tokens to generate. Ollama calls this `num_predict`.
         context_window (int, optional): The number of tokens to consider as context. Ollama calls this `num_ctx`.
         temperature (float, optional): The temperature of the model. Increasing the temperature will make the model answer more creatively.
@@ -38,6 +41,9 @@ def chat_completion(
         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.
+            tool_names (list[str], optional): The names of the tools called by the model.
+                If the model does not support tools, a ResponseError is raised.
+            tool_args_list (list[dict], optional): The arguments of the tools called by the model.
             prompt_tokens (int): The number of tokens in the messages sent to the model.
             completion_tokens (int): The number of tokens used by the model to generate the completion.
             response_duration (float): The time, in seconds, taken to generate the response by using the model.
@@ -59,6 +65,8 @@ def chat_completion(
     }
     if json_mode:
         all_args["format"] = "json"
+    if tools:
+        all_args["tools"] = tools
 
     try:
         start_time = time.time()
@@ -78,19 +86,26 @@ def chat_completion(
     response_data: dict[str, Any] = {}
 
     # Handle getting the message returned by the model
-    message = response["message"].get("content", None)  # type: ignore
+    message = response["message"].get("content", "")
     if message and json_mode:
         with contextlib.suppress(json.JSONDecodeError):
             message = json.loads(message)
-    if message:
-        response_data["message"] = message
+    response_data["message"] = message
+
+    # Try getting tool calls
+    if response["message"].get("tool_calls"):
+        tool_calls = response["message"]["tool_calls"]
+        tool_names = [tool_call["function"]["name"] for tool_call in tool_calls]
+        tool_args_list = [tool_call["function"]["arguments"] for tool_call in tool_calls]
+        response_data["tool_names"] = tool_names
+        response_data["tool_args_list"] = tool_args_list
 
     tokenizer = load_tokenizer(model)
     prompt_tokens = num_tokens_from_messages(messages, tokenizer)
     response_data["prompt_tokens"] = prompt_tokens
 
     # Get the number of tokens generated
-    response_data["completion_tokens"] = response.get("eval_count", None)  # type: ignore
+    response_data["completion_tokens"] = response.get("eval_count", None)
     if response_data["completion_tokens"] is None:
         response_data["completion_tokens"] = num_tokens_in_string(str(response_data["message"]), tokenizer)
 

{not_again_ai-0.10.2 → not_again_ai-0.11.0}/src/not_again_ai/local_llm/ollama/model_mapping.py

@@ -7,6 +7,7 @@ i.e. all phi3 models will start with "phi3".
 OLLAMA_MODEL_MAPPING = {
     "phi3": "microsoft/Phi-3-mini-4k-instruct",
     "llama3:": "nvidia/Llama3-ChatQA-1.5-8B",  # Using this version to get around needed to accept an agreement to get access to the tokenizer
+    "llama3.1": "unsloth/Meta-Llama-3.1-8B-Instruct",
     "gemma": "google/gemma-1.1-7b-it",  # Requires HF_TOKEN set and accepting the agreement on the HF model page
     "qwen2": "Qwen/Qwen2-7B-Instruct",
     "granite-code": "ibm-granite/granite-34b-code-instruct",