updated

.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+.chainlit/
+.venv/ 
+.env

Dockerfile

@@ -0,0 +1,31 @@
+
+# Get a distribution that has uv already installed
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
+
+# Add user - this is the user that will run the app
+# If you do not set user, the app will run as root (undesirable)
+RUN useradd -m -u 1000 user
+USER user
+
+# Set the home directory and path
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH        
+
+ENV UVICORN_WS_PROTOCOL=websockets
+
+
+# Set the working directory
+WORKDIR $HOME/app
+
+# Copy the app to the container
+COPY --chown=user . $HOME/app
+
+# Install the dependencies
+# RUN uv sync --frozen
+RUN uv sync
+
+# Expose the port
+EXPOSE 7860
+
+# Run the app
+CMD ["uv", "run", "chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]

aimakerspace/openai_utils/chatmodel.py

@@ -0,0 +1,45 @@
+from openai import OpenAI, AsyncOpenAI
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+
+class ChatOpenAI:
+    def __init__(self, model_name: str = "gpt-4o-mini"):
+        self.model_name = model_name
+        self.openai_api_key = os.getenv("OPENAI_API_KEY")
+        if self.openai_api_key is None:
+            raise ValueError("OPENAI_API_KEY is not set")
+
+    def run(self, messages, text_only: bool = True, **kwargs):
+        if not isinstance(messages, list):
+            raise ValueError("messages must be a list")
+
+        client = OpenAI()
+        response = client.chat.completions.create(
+            model=self.model_name, messages=messages, **kwargs
+        )
+
+        if text_only:
+            return response.choices[0].message.content
+
+        return response
+    
+    async def astream(self, messages, **kwargs):
+        if not isinstance(messages, list):
+            raise ValueError("messages must be a list")
+        
+        client = AsyncOpenAI()
+
+        stream = await client.chat.completions.create(
+            model=self.model_name,
+            messages=messages,
+            stream=True,
+            **kwargs
+        )
+
+        async for chunk in stream:
+            content = chunk.choices[0].delta.content
+            if content is not None:
+                yield content

aimakerspace/openai_utils/embedding.py

@@ -0,0 +1,59 @@
+from dotenv import load_dotenv
+from openai import AsyncOpenAI, OpenAI
+import openai
+from typing import List
+import os
+import asyncio
+
+
+class EmbeddingModel:
+    def __init__(self, embeddings_model_name: str = "text-embedding-3-small"):
+        load_dotenv()
+        self.openai_api_key = os.getenv("OPENAI_API_KEY")
+        self.async_client = AsyncOpenAI()
+        self.client = OpenAI()
+
+        if self.openai_api_key is None:
+            raise ValueError(
+                "OPENAI_API_KEY environment variable is not set. Please set it to your OpenAI API key."
+            )
+        openai.api_key = self.openai_api_key
+        self.embeddings_model_name = embeddings_model_name
+
+    async def async_get_embeddings(self, list_of_text: List[str]) -> List[List[float]]:
+        embedding_response = await self.async_client.embeddings.create(
+            input=list_of_text, model=self.embeddings_model_name
+        )
+
+        return [embeddings.embedding for embeddings in embedding_response.data]
+
+    async def async_get_embedding(self, text: str) -> List[float]:
+        embedding = await self.async_client.embeddings.create(
+            input=text, model=self.embeddings_model_name
+        )
+
+        return embedding.data[0].embedding
+
+    def get_embeddings(self, list_of_text: List[str]) -> List[List[float]]:
+        embedding_response = self.client.embeddings.create(
+            input=list_of_text, model=self.embeddings_model_name
+        )
+
+        return [embeddings.embedding for embeddings in embedding_response.data]
+
+    def get_embedding(self, text: str) -> List[float]:
+        embedding = self.client.embeddings.create(
+            input=text, model=self.embeddings_model_name
+        )
+
+        return embedding.data[0].embedding
+
+
+if __name__ == "__main__":
+    embedding_model = EmbeddingModel()
+    print(asyncio.run(embedding_model.async_get_embedding("Hello, world!")))
+    print(
+        asyncio.run(
+            embedding_model.async_get_embeddings(["Hello, world!", "Goodbye, world!"])
+        )
+    )

aimakerspace/openai_utils/prompts.py

@@ -0,0 +1,78 @@
+import re
+
+
+class BasePrompt:
+    def __init__(self, prompt):
+        """
+        Initializes the BasePrompt object with a prompt template.
+
+        :param prompt: A string that can contain placeholders within curly braces
+        """
+        self.prompt = prompt
+        self._pattern = re.compile(r"\{([^}]+)\}")
+
+    def format_prompt(self, **kwargs):
+        """
+        Formats the prompt string using the keyword arguments provided.
+
+        :param kwargs: The values to substitute into the prompt string
+        :return: The formatted prompt string
+        """
+        matches = self._pattern.findall(self.prompt)
+        return self.prompt.format(**{match: kwargs.get(match, "") for match in matches})
+
+    def get_input_variables(self):
+        """
+        Gets the list of input variable names from the prompt string.
+
+        :return: List of input variable names
+        """
+        return self._pattern.findall(self.prompt)
+
+
+class RolePrompt(BasePrompt):
+    def __init__(self, prompt, role: str):
+        """
+        Initializes the RolePrompt object with a prompt template and a role.
+
+        :param prompt: A string that can contain placeholders within curly braces
+        :param role: The role for the message ('system', 'user', or 'assistant')
+        """
+        super().__init__(prompt)
+        self.role = role
+
+    def create_message(self, format=True, **kwargs):
+        """
+        Creates a message dictionary with a role and a formatted message.
+
+        :param kwargs: The values to substitute into the prompt string
+        :return: Dictionary containing the role and the formatted message
+        """
+        if format:
+            return {"role": self.role, "content": self.format_prompt(**kwargs)}
+        
+        return {"role": self.role, "content": self.prompt}
+
+
+class SystemRolePrompt(RolePrompt):
+    def __init__(self, prompt: str):
+        super().__init__(prompt, "system")
+
+
+class UserRolePrompt(RolePrompt):
+    def __init__(self, prompt: str):
+        super().__init__(prompt, "user")
+
+
+class AssistantRolePrompt(RolePrompt):
+    def __init__(self, prompt: str):
+        super().__init__(prompt, "assistant")
+
+
+if __name__ == "__main__":
+    prompt = BasePrompt("Hello {name}, you are {age} years old")
+    print(prompt.format_prompt(name="John", age=30))
+
+    prompt = SystemRolePrompt("Hello {name}, you are {age} years old")
+    print(prompt.create_message(name="John", age=30))
+    print(prompt.get_input_variables())

aimakerspace/text_utils.py

@@ -0,0 +1,136 @@
+import os
+from typing import List
+import PyPDF2
+
+
+class TextFileLoader:
+    def __init__(self, path: str, encoding: str = "utf-8"):
+        self.documents = []
+        self.path = path
+        self.encoding = encoding
+
+    def load(self):
+        if os.path.isdir(self.path):
+            self.load_directory()
+        elif os.path.isfile(self.path) and self.path.endswith(".txt"):
+            self.load_file()
+        else:
+            raise ValueError(
+                "Provided path is neither a valid directory nor a .txt file."
+            )
+
+    def load_file(self):
+        with open(self.path, "r", encoding=self.encoding) as f:
+            self.documents.append(f.read())
+
+    def load_directory(self):
+        for root, _, files in os.walk(self.path):
+            for file in files:
+                if file.endswith(".txt"):
+                    with open(
+                        os.path.join(root, file), "r", encoding=self.encoding
+                    ) as f:
+                        self.documents.append(f.read())
+
+    def load_documents(self):
+        self.load()
+        return self.documents
+
+
+class CharacterTextSplitter:
+    def __init__(
+        self,
+        chunk_size: int = 1000,
+        chunk_overlap: int = 200,
+    ):
+        assert (
+            chunk_size > chunk_overlap
+        ), "Chunk size must be greater than chunk overlap"
+
+        self.chunk_size = chunk_size
+        self.chunk_overlap = chunk_overlap
+
+    def split(self, text: str) -> List[str]:
+        chunks = []
+        for i in range(0, len(text), self.chunk_size - self.chunk_overlap):
+            chunks.append(text[i : i + self.chunk_size])
+        return chunks
+
+    def split_texts(self, texts: List[str]) -> List[str]:
+        chunks = []
+        for text in texts:
+            chunks.extend(self.split(text))
+        return chunks
+
+
+class PDFLoader:
+    def __init__(self, path: str):
+        self.documents = []
+        self.path = path
+        print(f"PDFLoader initialized with path: {self.path}")
+
+    def load(self):
+        print(f"Loading PDF from path: {self.path}")
+        print(f"Path exists: {os.path.exists(self.path)}")
+        print(f"Is file: {os.path.isfile(self.path)}")
+        print(f"Is directory: {os.path.isdir(self.path)}")
+        print(f"File permissions: {oct(os.stat(self.path).st_mode)[-3:]}")
+        
+        try:
+            # Try to open the file first to verify access
+            with open(self.path, 'rb') as test_file:
+                pass
+            
+            # If we can open it, proceed with loading
+            self.load_file()
+            
+        except IOError as e:
+            raise ValueError(f"Cannot access file at '{self.path}': {str(e)}")
+        except Exception as e:
+            raise ValueError(f"Error processing file at '{self.path}': {str(e)}")
+
+    def load_file(self):
+        with open(self.path, 'rb') as file:
+            # Create PDF reader object
+            pdf_reader = PyPDF2.PdfReader(file)
+            
+            # Extract text from each page
+            text = ""
+            for page in pdf_reader.pages:
+                text += page.extract_text() + "\n"
+            
+            self.documents.append(text)
+
+    def load_directory(self):
+        for root, _, files in os.walk(self.path):
+            for file in files:
+                if file.lower().endswith('.pdf'):
+                    file_path = os.path.join(root, file)
+                    with open(file_path, 'rb') as f:
+                        pdf_reader = PyPDF2.PdfReader(f)
+                        
+                        # Extract text from each page
+                        text = ""
+                        for page in pdf_reader.pages:
+                            text += page.extract_text() + "\n"
+                        
+                        self.documents.append(text)
+
+    def load_documents(self):
+        self.load()
+        return self.documents
+
+
+if __name__ == "__main__":
+    loader = TextFileLoader("data/KingLear.txt")
+    loader.load()
+    splitter = CharacterTextSplitter()
+    chunks = splitter.split_texts(loader.documents)
+    print(len(chunks))
+    print(chunks[0])
+    print("--------")
+    print(chunks[1])
+    print("--------")
+    print(chunks[-2])
+    print("--------")
+    print(chunks[-1])

aimakerspace/vectordatabase.py

@@ -0,0 +1,81 @@
+import numpy as np
+from collections import defaultdict
+from typing import List, Tuple, Callable
+from aimakerspace.openai_utils.embedding import EmbeddingModel
+import asyncio
+
+
+def cosine_similarity(vector_a: np.array, vector_b: np.array) -> float:
+    """Computes the cosine similarity between two vectors."""
+    dot_product = np.dot(vector_a, vector_b)
+    norm_a = np.linalg.norm(vector_a)
+    norm_b = np.linalg.norm(vector_b)
+    return dot_product / (norm_a * norm_b)
+
+
+class VectorDatabase:
+    def __init__(self, embedding_model: EmbeddingModel = None):
+        self.vectors = defaultdict(np.array)
+        self.embedding_model = embedding_model or EmbeddingModel()
+
+    def insert(self, key: str, vector: np.array) -> None:
+        self.vectors[key] = vector
+
+    def search(
+        self,
+        query_vector: np.array,
+        k: int,
+        distance_measure: Callable = cosine_similarity,
+    ) -> List[Tuple[str, float]]:
+        scores = [
+            (key, distance_measure(query_vector, vector))
+            for key, vector in self.vectors.items()
+        ]
+        return sorted(scores, key=lambda x: x[1], reverse=True)[:k]
+
+    def search_by_text(
+        self,
+        query_text: str,
+        k: int,
+        distance_measure: Callable = cosine_similarity,
+        return_as_text: bool = False,
+    ) -> List[Tuple[str, float]]:
+        query_vector = self.embedding_model.get_embedding(query_text)
+        results = self.search(query_vector, k, distance_measure)
+        return [result[0] for result in results] if return_as_text else results
+
+    def retrieve_from_key(self, key: str) -> np.array:
+        return self.vectors.get(key, None)
+
+    async def abuild_from_list(self, list_of_text: List[str]) -> "VectorDatabase":
+        embeddings = await self.embedding_model.async_get_embeddings(list_of_text)
+        for text, embedding in zip(list_of_text, embeddings):
+            self.insert(text, np.array(embedding))
+        return self
+
+
+if __name__ == "__main__":
+    list_of_text = [
+        "I like to eat broccoli and bananas.",
+        "I ate a banana and spinach smoothie for breakfast.",
+        "Chinchillas and kittens are cute.",
+        "My sister adopted a kitten yesterday.",
+        "Look at this cute hamster munching on a piece of broccoli.",
+    ]
+
+    vector_db = VectorDatabase()
+    vector_db = asyncio.run(vector_db.abuild_from_list(list_of_text))
+    k = 2
+
+    searched_vector = vector_db.search_by_text("I think fruit is awesome!", k=k)
+    print(f"Closest {k} vector(s):", searched_vector)
+
+    retrieved_vector = vector_db.retrieve_from_key(
+        "I like to eat broccoli and bananas."
+    )
+    print("Retrieved vector:", retrieved_vector)
+
+    relevant_texts = vector_db.search_by_text(
+        "I think fruit is awesome!", k=k, return_as_text=True
+    )
+    print(f"Closest {k} text(s):", relevant_texts)

app.py

@@ -0,0 +1,139 @@
+import os
+from typing import List
+from chainlit.types import AskFileResponse
+from aimakerspace.text_utils import CharacterTextSplitter, TextFileLoader, PDFLoader
+from aimakerspace.openai_utils.prompts import (
+    UserRolePrompt,
+    SystemRolePrompt,
+    AssistantRolePrompt,
+)
+from aimakerspace.openai_utils.embedding import EmbeddingModel
+from aimakerspace.vectordatabase import VectorDatabase
+from aimakerspace.openai_utils.chatmodel import ChatOpenAI
+import chainlit as cl
+
+system_template = """\
+Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
+system_role_prompt = SystemRolePrompt(system_template)
+
+user_prompt_template = """\
+Context:
+{context}
+
+Question:
+{question}
+"""
+user_role_prompt = UserRolePrompt(user_prompt_template)
+
+class RetrievalAugmentedQAPipeline:
+    def __init__(self, llm: ChatOpenAI, vector_db_retriever: VectorDatabase) -> None:
+        self.llm = llm
+        self.vector_db_retriever = vector_db_retriever
+
+    async def arun_pipeline(self, user_query: str):
+        context_list = self.vector_db_retriever.search_by_text(user_query, k=4)
+
+        context_prompt = ""
+        for context in context_list:
+            context_prompt += context[0] + "\n"
+
+        formatted_system_prompt = system_role_prompt.create_message()
+
+        formatted_user_prompt = user_role_prompt.create_message(question=user_query, context=context_prompt)
+
+        async def generate_response():
+            async for chunk in self.llm.astream([formatted_system_prompt, formatted_user_prompt]):
+                yield chunk
+
+        return {"response": generate_response(), "context": context_list}
+
+text_splitter = CharacterTextSplitter()
+
+
+def process_file(file: AskFileResponse):
+    import tempfile
+    import shutil
+    
+    print(f"Processing file: {file.name}")
+    
+    # Create a temporary file with the correct extension
+    suffix = f".{file.name.split('.')[-1]}"
+    with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as temp_file:
+        # Copy the uploaded file content to the temporary file
+        shutil.copyfile(file.path, temp_file.name)
+        print(f"Created temporary file at: {temp_file.name}")
+        
+        # Create appropriate loader
+        if file.name.lower().endswith('.pdf'):
+            loader = PDFLoader(temp_file.name)
+        else:
+            loader = TextFileLoader(temp_file.name)
+            
+        try:
+            # Load and process the documents
+            documents = loader.load_documents()
+            texts = text_splitter.split_texts(documents)
+            return texts
+        finally:
+            # Clean up the temporary file
+            try:
+                os.unlink(temp_file.name)
+            except Exception as e:
+                print(f"Error cleaning up temporary file: {e}")
+
+
+@cl.on_chat_start
+async def on_chat_start():
+    files = None
+
+    # Wait for the user to upload a file
+    while files == None:
+        files = await cl.AskFileMessage(
+            content="Please upload a Text or PDF file to begin!",
+            accept=["text/plain", "application/pdf"],
+            max_size_mb=2,
+            timeout=180,
+        ).send()
+
+    file = files[0]
+
+    msg = cl.Message(
+        content=f"Processing `{file.name}`..."
+    )
+    await msg.send()
+
+    # load the file
+    texts = process_file(file)
+
+    print(f"Processing {len(texts)} text chunks")
+
+    # Create a dict vector store
+    vector_db = VectorDatabase()
+    vector_db = await vector_db.abuild_from_list(texts)
+    
+    chat_openai = ChatOpenAI()
+
+    # Create a chain
+    retrieval_augmented_qa_pipeline = RetrievalAugmentedQAPipeline(
+        vector_db_retriever=vector_db,
+        llm=chat_openai
+    )
+    
+    # Let the user know that the system is ready
+    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
+    await msg.update()
+
+    cl.user_session.set("chain", retrieval_augmented_qa_pipeline)
+
+
+@cl.on_message
+async def main(message):
+    chain = cl.user_session.get("chain")
+
+    msg = cl.Message(content="")
+    result = await chain.arun_pipeline(message.content)
+
+    async for stream_resp in result["response"]:
+        await msg.stream_token(stream_resp)
+
+    await msg.send()

pyproject.toml

@@ -0,0 +1,14 @@
+[project]
+name = "aie5-deploypythonicrag"
+version = "0.1.0"
+description = "Simple Pythonic RAG App"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "chainlit>=2.0.4",
+    "numpy>=2.2.2",
+    "openai>=1.59.9",
+    "pydantic==2.10.1",
+    "pypdf2>=3.0.1",
+    "websockets>=14.2",
+]