initial commit

.gitignore

@@ -0,0 +1,169 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# misc
+.DS_Store
+.chainlit
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Ignore weights & biases folder
+wandb/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+.DS_Store

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

aimakerspace/openai_utils/chatmodel.py

@@ -0,0 +1,27 @@
+from openai import OpenAI
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+
+class ChatOpenAI:
+    def __init__(self, model_name: str = "gpt-3.5-turbo"):
+        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):
+        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
+        )
+
+        if text_only:
+            return response.choices[0].message.content
+
+        return response

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-ada-002"):
+        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 +1,75 @@
+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, **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
+        """
+        return {"role": self.role, "content": self.format_prompt(**kwargs)}
+
+
+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 +1,77 @@
+import os
+from typing import List
+
+
+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
+
+
+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 +1,124 @@
+# You can find this code for Chainlit python streaming here (https://docs.chainlit.io/concepts/streaming/python)
+
+# OpenAI Chat completion
+import os
+from openai import AsyncOpenAI  # importing openai for API usage
+import chainlit as cl  # importing chainlit for our app
+from chainlit.prompt import Prompt, PromptMessage  # importing prompt tools
+from chainlit.playground.providers import ChatOpenAI  # importing ChatOpenAI tools
+from dotenv import load_dotenv
+
+import asyncio
+
+from aimakerspace.text_utils import TextFileLoader, CharacterTextSplitter
+from aimakerspace.vectordatabase import VectorDatabase
+from aimakerspace.openai_utils.prompts import (
+    UserRolePrompt,
+    SystemRolePrompt,
+    AssistantRolePrompt,
+)
+
+load_dotenv()
+
+RAQA_PROMPT_TEMPLATE = """
+Use the provided context to answer the user's query. 
+
+You may not answer the user's query unless there is specific context in the following text.
+
+If you do not know the answer, or cannot answer, please respond with "I don't know".
+
+Context:
+{context}
+"""
+
+USER_PROMPT_TEMPLATE = """
+User Query:
+{user_query}
+"""
+
+def load_vector_db_from_local_file(file_path="data/KingLear.txt"):
+    """generates the vector database object base on a local file"""
+    
+    # load text file and split into chunk of documents
+    text_loader = TextFileLoader(file_path)
+    documents = text_loader.load_documents()
+    text_splitter = CharacterTextSplitter()
+    split_documents = text_splitter.split_texts(documents)
+    
+    # initialize vector db and build from list of documents
+    vector_db = VectorDatabase()
+    vector_db = asyncio.run(vector_db.abuild_from_list(split_documents))
+    return vector_db
+    
+    
+def get_formatted_prompts(vector_db_retriever: VectorDatabase, user_query: str):
+
+    raqa_prompt = SystemRolePrompt(RAQA_PROMPT_TEMPLATE)
+    user_prompt = UserRolePrompt(USER_PROMPT_TEMPLATE)
+
+    context_list = 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 = raqa_prompt.create_message(context=context_prompt)
+
+    formatted_user_prompt = user_prompt.create_message(user_query=user_query)
+    
+    return formatted_system_prompt, formatted_user_prompt
+
+@cl.on_chat_start  # marks a function that will be executed at the start of a user session
+async def start_chat():
+
+    settings = {
+        "model": "gpt-3.5-turbo",
+        "temperature": 0,
+        "max_tokens": 500,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+    }
+
+    cl.user_session.set("settings", settings)
+
+
+@cl.on_message  # marks a function that should be run each time the chatbot receives a message from a user
+async def main(message: cl.Message):
+
+    settings = cl.user_session.get("settings")
+
+    client = AsyncOpenAI()
+
+    # print(f"This is the message received by the user : {message.content}")
+
+    # this the loading of the vector database
+    vector_db = load_vector_db_from_local_file()
+
+    formatted_system_prompt, formatted_user_prompt = list(
+        get_formatted_prompts(
+            vector_db_retriever=vector_db,
+            user_query=message.content
+            )
+            )
+    
+    # print(f"formatted_system_prompt : {formatted_system_prompt}")
+    # print(f"formatted_user_prompt : {formatted_user_prompt}")
+
+    formatted_messages =[formatted_system_prompt, formatted_user_prompt]
+
+    msg = cl.Message(content="")
+
+    # Call OpenAI
+    async for stream_resp in await client.chat.completions.create(
+        messages=formatted_messages, stream=True, **settings
+    ):
+        token = stream_resp.choices[0].delta.content
+        if not token:
+            token = ""
+        await msg.stream_token(token)
+
+    # print(f"This is the message sent by the model : {msg.content}")
+
+    # Send and close the message stream
+    await msg.send()

chainlit.md

@@ -0,0 +1,3 @@
+# Pythonic RAGA Application
+
+This application leverages Chainlit, OpenAI and Hugging Face to build a basic RAQA (Retrieval Augmented Question Answering) application based on a local text file containing the entire text of King Lear.

requirements.txt

@@ -0,0 +1,6 @@
+chainlit==0.7.700
+cohere==4.37
+openai==1.3.5
+tiktoken==0.5.1
+python-dotenv==1.0.0
+numpy==1.25.2