not-again-ai 0.10.0__tar.gz → 0.10.1__tar.gz

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: not-again-ai
-Version: 0.10.0
+Version: 0.10.1
 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
@@ -74,7 +74,7 @@ The package is split into subpackages, so you can install only the parts you nee
     1. If you wish to use OpenAI
         1. Go to https://platform.openai.com/settings/profile?tab=api-keys to get your API key.
         1. (Optional) Set the `OPENAI_API_KEY` and the `OPENAI_ORG_ID` environment variables.
-* **Local LLM**: `pip install not_again_ai[llm,llm_local]`
+* **Local LLM**: `pip install not_again_ai[llm,local_llm]`
     1. Some HuggingFace transformers tokenizers are gated behind access requests. If you wish to use these, you will need to request access from HuggingFace on the model card.
        1. Then set the `HF_TOKEN` environment variable to your HuggingFace API token which can be found here: https://huggingface.co/settings/tokens
     1. If you wish to use Ollama:
@@ -292,6 +292,14 @@ provides further examples on how to do this.
 Mypy looks for the existence of a file named [`py.typed`](./src/not-again-ai/py.typed) in the root of the
 installed package to indicate that inline type annotations should be checked.
 
+## Typos
+
+Checks for typos using [typos](https://github.com/crate-ci/typos)
+
+```bash
+(.venv) $ nox -s typos
+```
+
 ## Continuous Integration
 
 Continuous integration is provided by [GitHub Actions](https://github.com/features/actions). This

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/README.md

@@ -35,7 +35,7 @@ The package is split into subpackages, so you can install only the parts you nee
     1. If you wish to use OpenAI
         1. Go to https://platform.openai.com/settings/profile?tab=api-keys to get your API key.
         1. (Optional) Set the `OPENAI_API_KEY` and the `OPENAI_ORG_ID` environment variables.
-* **Local LLM**: `pip install not_again_ai[llm,llm_local]`
+* **Local LLM**: `pip install not_again_ai[llm,local_llm]`
     1. Some HuggingFace transformers tokenizers are gated behind access requests. If you wish to use these, you will need to request access from HuggingFace on the model card.
        1. Then set the `HF_TOKEN` environment variable to your HuggingFace API token which can be found here: https://huggingface.co/settings/tokens
     1. If you wish to use Ollama:
@@ -253,6 +253,14 @@ provides further examples on how to do this.
 Mypy looks for the existence of a file named [`py.typed`](./src/not-again-ai/py.typed) in the root of the
 installed package to indicate that inline type annotations should be checked.
 
+## Typos
+
+Checks for typos using [typos](https://github.com/crate-ci/typos)
+
+```bash
+(.venv) $ nox -s typos
+```
+
 ## Continuous Integration
 
 Continuous integration is provided by [GitHub Actions](https://github.com/features/actions). This

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "not-again-ai"
-version = "0.10.0"
+version = "0.10.1"
 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"
@@ -78,6 +78,9 @@ mkdocstrings = { version = "*", extras = ["python"] }
 mkdocs-gen-files = "*"
 mkdocs-literate-nav = "*"
 
+[tool.poetry.group.typos.dependencies]
+typos = "*"
+
 [tool.poetry.scripts]
 not-again-ai = "not_again_ai.cli:entry_point"
 

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/src/not_again_ai/llm/openai_api/chat_completion.py

@@ -165,7 +165,7 @@ def chat_completion(
     if seed is not None and response.system_fingerprint is not None:
         response_data["system_fingerprint"] = response.system_fingerprint
 
-    response_data["response_duration"] = response_duration
+    response_data["response_duration"] = round(response_duration, 4)
 
     if len(response_data["choices"]) == 1:
         response_data.update(response_data["choices"][0])

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/src/not_again_ai/llm/openai_api/context_management.py

@@ -33,7 +33,7 @@ def priority_truncation(
     Args:
         messages_unformatted: A list of dictionaries where each dictionary
             represents a message. Each message must have 'role' and 'content'
-            keys with string values, where content is a string with any number of occurances of {{variable_name}}.
+            keys with string values, where content is a string with any number of occurrences of {{variable_name}}.
         variables: A dictionary where each key-value pair represents a variable name and its value to inject.
         priority: A list of variable names in their order of priority.
         token_limit: The maximum number of tokens allowed in the messages.

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/src/not_again_ai/local_llm/__init__.py

@@ -21,3 +21,7 @@ else:
     import openai  # noqa: F401
     import tiktoken  # noqa: F401
     import transformers  # noqa: F401
+    from transformers.utils import logging
+
+    logging.disable_progress_bar()
+    logging.set_verbosity_error()

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/src/not_again_ai/local_llm/ollama/chat_completion.py

@@ -95,6 +95,6 @@ def chat_completion(
         response_data["completion_tokens"] = num_tokens_in_string(str(response_data["message"]), tokenizer)
 
     # Get the latency of the response
-    response_data["response_duration"] = response_duration
+    response_data["response_duration"] = round(response_duration, 4)
 
     return response_data

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/src/not_again_ai/local_llm/ollama/model_mapping.py

@@ -12,4 +12,5 @@ OLLAMA_MODEL_MAPPING = {
     "granite-code": "ibm-granite/granite-34b-code-instruct",
     "llama3-gradient": "nvidia/Llama3-ChatQA-1.5-8B",
     "command-r": "CohereForAI/c4ai-command-r-v01",
+    "deepseek-coder-v2": "deepseek-ai/DeepSeek-Coder-V2-Lite-Base",
 }

{not_again_ai-0.10.0 → not_again_ai-0.10.1}/src/not_again_ai/local_llm/ollama/tokens.py

@@ -1,19 +1,13 @@
 """By default use the associated huggingface transformer tokenizer.
 If it does not exist in the mapping, default to tiktoken with some buffer (const + percentage)"""
 
-import os
-
 from loguru import logger
 import tiktoken
+from transformers import AutoTokenizer
 
 from not_again_ai.llm.openai_api.tokens import num_tokens_from_messages as openai_num_tokens_from_messages
 from not_again_ai.local_llm.ollama.model_mapping import OLLAMA_MODEL_MAPPING
 
-# Prevents the transformers library from printing advisories that are not relevant to this code like not having torch installed.
-os.environ["TRANSFORMERS_NO_ADVISORY_WARNINGS"] = "1"
-
-from transformers import AutoTokenizer  # noqa: E402
-
 TIKTOKEN_NUM_TOKENS_BUFFER = 10
 TIKTOKEN_PERCENT_TOKENS_BUFFER = 1.1