llm-ie 0.4.2__py3-none-any.whl → 0.4.3__py3-none-any.whl

llm_ie/__init__.py

@@ -1,9 +1,9 @@
 from .data_types import LLMInformationExtractionFrame, LLMInformationExtractionDocument
-from .engines import LlamaCppInferenceEngine, OllamaInferenceEngine, HuggingFaceHubInferenceEngine, OpenAIInferenceEngine, LiteLLMInferenceEngine
+from .engines import LlamaCppInferenceEngine, OllamaInferenceEngine, HuggingFaceHubInferenceEngine, OpenAIInferenceEngine, AzureOpenAIInferenceEngine, LiteLLMInferenceEngine
 from .extractors import BasicFrameExtractor, ReviewFrameExtractor, SentenceFrameExtractor, SentenceReviewFrameExtractor, SentenceCoTFrameExtractor, BinaryRelationExtractor, MultiClassRelationExtractor
 from .prompt_editor import PromptEditor
 
 __all__ = ["LLMInformationExtractionFrame", "LLMInformationExtractionDocument",
-           "LlamaCppInferenceEngine", "OllamaInferenceEngine", "HuggingFaceHubInferenceEngine", "OpenAIInferenceEngine", "LiteLLMInferenceEngine",
+           "LlamaCppInferenceEngine", "OllamaInferenceEngine", "HuggingFaceHubInferenceEngine", "OpenAIInferenceEngine", "AzureOpenAIInferenceEngine", "LiteLLMInferenceEngine",
            "BasicFrameExtractor", "ReviewFrameExtractor", "SentenceFrameExtractor", "SentenceReviewFrameExtractor", "SentenceCoTFrameExtractor", "BinaryRelationExtractor", "MultiClassRelationExtractor",
            "PromptEditor"]

llm_ie/engines.py

@@ -290,9 +290,88 @@ class OpenAIInferenceEngine(InferenceEngine):
         if stream:
             res = ''
             for chunk in response:
-                if chunk.choices[0].delta.content is not None:
-                    res += chunk.choices[0].delta.content
-                    print(chunk.choices[0].delta.content, end="", flush=True)
+                if len(chunk.choices) > 0:
+                    if chunk.choices[0].delta.content is not None:
+                        res += chunk.choices[0].delta.content
+                        print(chunk.choices[0].delta.content, end="", flush=True)
+            return res
+        
+        return response.choices[0].message.content
+    
+
+    async def chat_async(self, messages:List[Dict[str,str]], max_new_tokens:int=2048, temperature:float=0.0, **kwrs) -> str:
+        """
+        Async version of chat method. Streaming is not supported.
+        """
+        response = await self.async_client.chat.completions.create(
+            model=self.model,
+            messages=messages,
+            max_tokens=max_new_tokens,
+            temperature=temperature,
+            stream=False,
+            **kwrs
+        )
+        
+        return response.choices[0].message.content
+    
+
+class AzureOpenAIInferenceEngine(InferenceEngine):
+    def __init__(self, model:str, api_version:str, **kwrs):
+        """
+        The Azure OpenAI API inference engine.
+        For parameters and documentation, refer to 
+        - https://azure.microsoft.com/en-us/products/ai-services/openai-service
+        - https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart
+        
+        Parameters:
+        ----------
+        model : str
+            model name as described in https://platform.openai.com/docs/models
+        api_version : str
+            the Azure OpenAI API version
+        """
+        if importlib.util.find_spec("openai") is None:
+            raise ImportError("OpenAI Python API library not found. Please install OpanAI (```pip install openai```).")
+        
+        from openai import AzureOpenAI, AsyncAzureOpenAI
+        self.model = model
+        self.api_version = api_version
+        self.client = AzureOpenAI(api_version=self.api_version, 
+                                  **kwrs)
+        self.async_client = AsyncAzureOpenAI(api_version=self.api_version, 
+                                             **kwrs)
+
+    def chat(self, messages:List[Dict[str,str]], max_new_tokens:int=2048, temperature:float=0.0, stream:bool=False, **kwrs) -> str:
+        """
+        This method inputs chat messages and outputs LLM generated text.
+
+        Parameters:
+        ----------
+        messages : List[Dict[str,str]]
+            a list of dict with role and content. role must be one of {"system", "user", "assistant"}
+        max_new_tokens : str, Optional
+            the max number of new tokens LLM can generate. 
+        temperature : float, Optional
+            the temperature for token sampling. 
+        stream : bool, Optional
+            if True, LLM generated text will be printed in terminal in real-time. 
+        """
+        response = self.client.chat.completions.create(
+            model=self.model,
+            messages=messages,
+            max_tokens=max_new_tokens,
+            temperature=temperature,
+            stream=stream,
+            **kwrs
+        )
+
+        if stream:
+            res = ''
+            for chunk in response:
+                if len(chunk.choices) > 0:
+                    if chunk.choices[0].delta.content is not None:
+                        res += chunk.choices[0].delta.content
+                        print(chunk.choices[0].delta.content, end="", flush=True)
             return res
         
         return response.choices[0].message.content
@@ -312,6 +391,7 @@ class OpenAIInferenceEngine(InferenceEngine):
         )
         
         return response.choices[0].message.content
+
     
 class LiteLLMInferenceEngine(InferenceEngine):
     def __init__(self, model:str=None, base_url:str=None, api_key:str=None):

llm_ie/prompt_editor.py

@@ -67,7 +67,7 @@ class PromptEditor:
         return prompt
     
 
-    def rewrite(self, draft:str) -> str:
+    def rewrite(self, draft:str, **kwrs) -> str:
         """
         This method inputs a prompt draft and rewrites it following the extractor's guideline.
         """
@@ -79,10 +79,10 @@ class PromptEditor:
                                              prompt_template=rewrite_prompt_template)
         messages = [{"role": "system", "content": self.system_prompt},
                     {"role": "user", "content": prompt}]
-        res = self.inference_engine.chat(messages, stream=True)
+        res = self.inference_engine.chat(messages, stream=True, **kwrs)
         return res
     
-    def comment(self, draft:str) -> str:
+    def comment(self, draft:str, **kwrs) -> str:
         """
         This method inputs a prompt draft and comment following the extractor's guideline.
         """
@@ -94,11 +94,11 @@ class PromptEditor:
                                              prompt_template=comment_prompt_template)
         messages = [{"role": "system", "content": self.system_prompt},
                     {"role": "user", "content": prompt}]
-        res = self.inference_engine.chat(messages, stream=True)
+        res = self.inference_engine.chat(messages, stream=True, **kwrs)
         return res
     
 
-    def _terminal_chat(self):
+    def _terminal_chat(self, **kwrs):
         """
         This method runs an interactive chat session in the terminal to help users write prompt templates.
         """
@@ -126,11 +126,11 @@ class PromptEditor:
             # Chat
             messages.append({"role": "user", "content": user_input})
             print(f"{Fore.BLUE}Assistant: {Style.RESET_ALL}", end="")
-            response = self.inference_engine.chat(messages, stream=True)
+            response = self.inference_engine.chat(messages, stream=True, **kwrs)
             messages.append({"role": "assistant", "content": response})
             
 
-    def _IPython_chat(self):
+    def _IPython_chat(self, **kwrs):
         """
         This method runs an interactive chat session in Jupyter/IPython using ipywidgets to help users write prompt templates.
         """
@@ -186,7 +186,7 @@ class PromptEditor:
 
             # Get assistant's response and append it to conversation
             print("Assistant: ", end="")
-            response = self.inference_engine.chat(messages, stream=True)
+            response = self.inference_engine.chat(messages, stream=True, **kwrs)
             messages.append({"role": "assistant", "content": response})
 
             # Display the assistant's response
@@ -200,11 +200,11 @@ class PromptEditor:
         display(input_box)
         display(output_area)
 
-    def chat(self):
+    def chat(self, **kwrs):
         """
         External method that detects the environment and calls the appropriate chat method.
         """
         if 'ipykernel' in sys.modules:
-            self._IPython_chat()
+            self._IPython_chat(**kwrs)
         else:
-            self._terminal_chat()
+            self._terminal_chat(**kwrs)

{llm_ie-0.4.2.dist-info → llm_ie-0.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llm-ie
-Version: 0.4.2
+Version: 0.4.3
 Summary: An LLM-powered tool that transforms everyday language into robust information extraction pipelines.
 License: MIT
 Author: Enshuo (David) Hsu
@@ -11,6 +11,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: colorama (>=0.4.6,<0.5.0)
 Requires-Dist: json_repair (>=0.30,<0.31)
+Requires-Dist: nest_asyncio (>=0.1.6,<0.2.0)
 Requires-Dist: nltk (>=3.8,<4.0)
 Description-Content-Type: text/markdown
 
@@ -39,6 +40,7 @@ An LLM-powered tool that transforms everyday language into robust information ex
     - Concurrent LLM inferencing to speed up frame and relation extraction. 
     - Support for LiteLLM.
 - [v0.4.1](https://github.com/daviden1013/llm-ie/releases/tag/v0.4.1) (Jan 25, 2025): Added filters, table view, and some new features to visualization tool (make sure to update [ie-viz](https://github.com/daviden1013/ie-viz)).
+- [v0.4.3](https://github.com/daviden1013/llm-ie/releases/tag/v0.4.3) (Feb 7, 2025): Added Azure OpenAI support. 
 
 ## Table of Contents
 - [Overview](#overview)
@@ -99,6 +101,20 @@ inference_engine = OpenAIInferenceEngine(model="gpt-4o-mini")
 ```
 </details>
 
+<details>
+<summary><img src=doc_asset/readme_img/Azure_icon.png width=32 /> Azure OpenAI API</summary>
+
+Follow the [Azure AI Services Quickstart](https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Ckeyless%2Ctypescript-keyless%2Cpython-new&pivots=programming-language-python) to set up Endpoint and API key.
+
+```python
+from llm_ie.engines import AzureOpenAIInferenceEngine
+
+inference_engine = AzureOpenAIInferenceEngine(model="gpt-4o-mini", 
+                                              api_version="<your api version>")
+```
+
+</details>
+
 <details>
 <summary>🤗 Huggingface_hub</summary>
 
@@ -324,6 +340,22 @@ from llm_ie.engines import OpenAIInferenceEngine
 inference_engine = OpenAIInferenceEngine(model="gpt-4o-mini")
 ```
 
+#### <img src=doc_asset/readme_img/Azure_icon.png width=32 /> Azure OpenAI API
+In bash, save the endpoint name and API key to environmental variables `AZURE_OPENAI_ENDPOINT` and `AZURE_OPENAI_API_KEY`.
+```
+export AZURE_OPENAI_API_KEY="<your_API_key>"
+export AZURE_OPENAI_ENDPOINT="<your_endpoint>"
+```
+
+In Python, create inference engine and specify model name. For the available models, refer to [OpenAI webpage](https://platform.openai.com/docs/models). 
+For more parameters, see [Azure OpenAI reference](https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart).
+
+```python
+from llm_ie.engines import AzureOpenAIInferenceEngine
+
+inference_engine = AzureOpenAIInferenceEngine(model="gpt-4o-mini")
+```
+
 #### 🤗 huggingface_hub
 The ```model``` can be a model id hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint. Refer to the [Inference Client](https://huggingface.co/docs/huggingface_hub/en/package_reference/inference_client) documentation for more details. 
 

{llm_ie-0.4.2.dist-info → llm_ie-0.4.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-llm_ie/__init__.py,sha256=zzxVgfX0Nrx3LgDDZl1XsJychb70LfQnYc5WUxL7gbo,932
+llm_ie/__init__.py,sha256=FnpYVn9C7t1q8EJbTup4FtxmGd1m8ZyaCXH6nRqbroY,990
 llm_ie/asset/PromptEditor_prompts/chat.txt,sha256=Fq62voV0JQ8xBRcxS1Nmdd7DkHs1fGYb-tmNwctZZK0,118
 llm_ie/asset/PromptEditor_prompts/comment.txt,sha256=C_lxx-dlOlFJ__jkHKosZ8HsNAeV1aowh2B36nIipBY,159
 llm_ie/asset/PromptEditor_prompts/rewrite.txt,sha256=JAwY9vm1jSmKf2qcLBYUvrSmME2EJH36bALmkwZDWYQ,178
@@ -15,9 +15,9 @@ llm_ie/asset/prompt_guide/SentenceCoTFrameExtractor_prompt_guide.txt,sha256=T4Ns
 llm_ie/asset/prompt_guide/SentenceFrameExtractor_prompt_guide.txt,sha256=oKH_QeDgpw771ZdHk3L7DYz2Jvfm7OolUoTiJyMJI30,9541
 llm_ie/asset/prompt_guide/SentenceReviewFrameExtractor_prompt_guide.txt,sha256=oKH_QeDgpw771ZdHk3L7DYz2Jvfm7OolUoTiJyMJI30,9541
 llm_ie/data_types.py,sha256=_Kt4Er1SMj1jg8U8TCXFJH_64prur-IbFngHKmZgWr8,15717
-llm_ie/engines.py,sha256=lz2HODoqlndgezdT76diXKN_wgb7mjl6hX3JuCwsH-g,15191
+llm_ie/engines.py,sha256=qESKa2f_2VZ-HSCDZ6R2gKFwPBN0j2qv1vcTYpWXJTM,18319
 llm_ie/extractors.py,sha256=ueSt8jBKLnqOxu8FuqyYqEERugzd6FsI0r-pY8EboHw,85426
-llm_ie/prompt_editor.py,sha256=pw_FOsEeWxFJ1p5lYR93cTNMqKQ-YZHzgBmRbPm7aNE,9486
-llm_ie-0.4.2.dist-info/METADATA,sha256=DASy47RtSsT1d7s3nzncjUHLIyJEPV8rTrqr1jRTFnY,52527
-llm_ie-0.4.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-llm_ie-0.4.2.dist-info/RECORD,,
+llm_ie/prompt_editor.py,sha256=pHRbg_yFZdoV63r3pvf0TsLfgH2EVJvzUQEVDH1Hj0s,9570
+llm_ie-0.4.3.dist-info/METADATA,sha256=ErEWRa3WYFakjwcUmQvHUomp_EiZho7nlB9XQFgGu9A,53980
+llm_ie-0.4.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+llm_ie-0.4.3.dist-info/RECORD,,