V1 of my Assistant powered by RAG

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+chromadb/**/*.bin filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,168 @@
+import os
+import gradio as gr
+import cohere
+from typing import Generator
+from langchain_chroma import Chroma
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.schema.document import Document
+from typing import List
+
+
+class HFSpaceChatBot:
+    """
+    A chatbot powered by Retrieval Augmented Generation (RAG) aimed
+    to be deployed on the Hugging Face Space platform.
+    """
+
+    def __init__(self,
+                 embedding_model_path: str,
+                 vector_database_path: str,
+                 top_k: int = 10,
+                 embedding_model_name: str = os.getenv("EMBEDDING_MODEL"),
+                 api_key: str = os.getenv("CO_API_KEY"),
+                 device: str = os.getenv("DEVICE"),
+                 system_prompt: str = "Answer the user's question",
+                 **kwargs) -> None:
+        """
+        Constructor for the HFSpaceChatBot class.
+
+        Args:
+            embedding_model_path (str): The path to the embedding model.
+            vector_database_path (str): The path to the vector database.
+            top_k (int): The number of top documents to retrieve.
+            embedding_model_name (str): The name of the embedding model.
+            api_key (str): The API key for the cohere API.
+            device (str): The device to run the model on.
+            system_prompt (str): The system prompt for the chatbot.
+            **kwargs: Additional keyword arguments (for the cohere API)
+        """
+
+        self.chat_history = []
+        self.cclient = cohere.Client(api_key=api_key)
+
+        self.embedding_model = HuggingFaceEmbeddings(
+            model_name=embedding_model_name,
+            model_kwargs={"device": device},
+            encode_kwargs={"normalize_embeddings": True},
+            cache_folder=embedding_model_path
+        )
+
+        self.vector_database = Chroma(
+            persist_directory=vector_database_path,
+            embedding_function=self.embedding_model
+        )
+
+        self.top_k = top_k
+
+        self.system_prompt = system_prompt
+
+        self.model_params = kwargs
+
+    def _get_relevant_information(self,
+                                  message: str) -> List[Document]:
+        """
+        Get the relevant information from the chat history.
+
+        Args:
+            message (str): The message to search for.
+
+        Returns:
+            List[Document]: A list of relevant documents.
+        """
+
+        return self.vector_database.similarity_search(message, self.top_k)
+
+    def _fetch_response(self,
+                        message: str,
+                        *args) -> Generator[str, None, None]:
+        """
+        Fetch the reponse from the cohere API.
+
+        Args:
+            message (str): The message of the user.
+
+        Returns:
+            Generator[str, None, None]: A generator yielding the output tokens.
+        """
+
+        docs = self._get_relevant_information(message)
+
+        relevant_information = "\n".join(
+            [doc.page_content
+             for doc in docs])
+
+        final_message = f"{self.system_prompt}\nWith the help of the\
+                        following context:\n{relevant_information}\n\
+                        Answer the following question:\n{message}"
+
+        response = self.cclient.chat_stream(
+            message=final_message,
+            chat_history=self.chat_history,
+            **self.model_params
+        )
+
+        current_text = ""
+        for event in response:
+            if event.event_type == "text-generation":
+                current_text += event.text
+                yield current_text
+
+        self.chat_history.append({
+            "role": "USER",
+            "text": message
+        })
+
+        self.chat_history.append({
+            "role": "CHATBOT",
+            "text": current_text
+        })
+
+    def launch(self,
+               title: str,
+               description: str) -> None:
+        """
+        Launch the chat interface.
+
+        Args:
+            title (str): The title of the chat interface.
+            description (str): The description of the chat interface.
+        """
+
+        gr.ChatInterface(
+            fn=self._fetch_response,
+            title=title,
+            description=description
+        ).launch()
+
+
+if __name__ == "__main__":
+
+    embedding_model_path = os.path.join(os.getcwd(), "model")
+    system_prompt = """You are now assuming the role of the personal assistant
+                       of Ilan ALIOUCHOUCHE, a French Computer Science student.
+                       Your task is to assist users by answering their
+                       questions about Ilan. You have access to comprehensive
+                       details about Ilan's education, skills, professional
+                       experience, and interests.
+                    """.replace("\n", "")
+
+    chatbot = HFSpaceChatBot(
+        embedding_model_path=embedding_model_path,
+        vector_database_path=os.path.join(os.getcwd(), "chromadb"),
+        system_prompt=system_prompt,
+        temperature=0.4
+    )
+
+    title = "🤖 Ilan's Personal Agent 🤖"
+
+    description = """
+    You can ask my assistant (almost) anything about me! :D
+
+    You are currently using the Hugging Face Space version 🤗. A Docker image 🐳 for local use, utilizing a GGUF model is also available [here](https://github.com/ilanaliouchouche/my-ai-cv/pkgs/container/my-cv)
+
+    """
+
+    chatbot.launch(
+        title=title,
+        description=description
+    )

chromadb/c94c08ce-73f6-4e33-9eb4-4e32e42ae999/data_level0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95042e844cfb77b20e578cf65635282a99d7c4dd20e589ac062f38bc389f8e58
+size 4236000

chromadb/c94c08ce-73f6-4e33-9eb4-4e32e42ae999/header.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcc596bc1909f7cc610d5839236c90513b4fbad06776c253fa1b21bfd712e940
+size 100

chromadb/c94c08ce-73f6-4e33-9eb4-4e32e42ae999/length.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc19b1997119425765295aeab72d76faa6927d4f83985d328c26f20468d6cc76
+size 4000

requirements.txt

@@ -0,0 +1,151 @@
+aiofiles==23.2.1
+aiohttp==3.9.5
+aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.7.0
+anyio==4.4.0
+asgiref==3.8.1
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.1.3
+boto3==1.34.122
+botocore==1.34.122
+build==1.2.1
+cachetools==5.3.3
+certifi==2024.6.2
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.5.0
+click==8.1.7
+cohere==5.5.6
+coloredlogs==15.0.1
+contourpy==1.2.1
+cycler==0.12.1
+dataclasses-json==0.6.6
+Deprecated==1.2.14
+dnspython==2.6.1
+email_validator==2.1.1
+fastapi==0.111.0
+fastapi-cli==0.0.4
+fastavro==1.9.4
+ffmpy==0.3.2
+filelock==3.14.0
+flatbuffers==24.3.25
+fonttools==4.53.0
+frozenlist==1.4.1
+fsspec==2024.6.0
+google-auth==2.30.0
+googleapis-common-protos==1.63.1
+grpcio==1.64.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+httpx-sse==0.4.0
+huggingface-hub==0.23.3
+humanfriendly==10.0
+idna==3.7
+importlib_resources==6.4.0
+ipywidgets==8.1.3
+Jinja2==3.1.4
+jmespath==1.0.1
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+jupyterlab_widgets==3.0.11
+kiwisolver==1.4.5
+kubernetes==30.1.0
+langchain==0.2.3
+langchain-chroma==0.1.1
+langchain-community==0.2.4
+langchain-core==0.2.5
+langchain-huggingface==0.0.3
+langchain-text-splitters==0.2.1
+langsmith==0.1.75
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.3
+matplotlib==3.9.0
+mdurl==0.1.2
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+networkx==3.3
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.18.0
+opentelemetry-api==1.25.0
+opentelemetry-exporter-otlp-proto-common==1.25.0
+opentelemetry-exporter-otlp-proto-grpc==1.25.0
+opentelemetry-instrumentation==0.46b0
+opentelemetry-instrumentation-asgi==0.46b0
+opentelemetry-instrumentation-fastapi==0.46b0
+opentelemetry-proto==1.25.0
+opentelemetry-sdk==1.25.0
+opentelemetry-semantic-conventions==0.46b0
+opentelemetry-util-http==0.46b0
+orjson==3.10.3
+overrides==7.7.0
+packaging==23.2
+pandas==2.2.2
+parameterized==0.9.0
+pillow==10.3.0
+posthog==3.5.0
+protobuf==4.25.3
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
+pydantic==2.7.3
+pydantic_core==2.18.4
+pydub==0.25.1
+pyparsing==3.1.2
+PyPika==0.48.9
+pyproject_hooks==1.1.0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+regex==2024.5.15
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.7.1
+rpds-py==0.18.1
+rsa==4.9
+ruff==0.4.8
+s3transfer==0.10.1
+safetensors==0.4.3
+scikit-learn==1.5.0
+scipy==1.13.1
+semantic-version==2.10.0
+sentence-transformers==3.0.1
+shellingham==1.5.4
+sniffio==1.3.1
+SQLAlchemy==2.0.30
+starlette==0.37.2
+sympy==1.12.1
+tenacity==8.3.0
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.3.1
+tqdm==4.66.4
+transformers==4.41.2
+typer==0.12.3
+types-requests==2.32.0.20240602
+typing-inspect==0.9.0
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.1
+uvicorn==0.30.1
+uvloop==0.19.0
+watchfiles==0.22.0
+websocket-client==1.8.0
+websockets==11.0.3
+widgetsnbextension==4.0.11
+wrapt==1.16.0
+yarl==1.9.4