first commit

app.py

@@ -0,0 +1,156 @@
+import gradio as gr
+from langchain_community.vectorstores import Chroma
+from langchain.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain, create_history_aware_retriever
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import MessagesPlaceholder
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain_core.runnables.history import RunnableWithMessageHistory
+import torch
+import chromadb
+from typing import List
+from langchain_core.documents import Document
+from langchain_core.retrievers import BaseRetriever
+from langchain_core.callbacks import CallbackManagerForRetrieverRun
+from langchain_core.vectorstores import VectorStoreRetriever
+
+from langchain_openai import ChatOpenAI
+from mixedbread_ai.client import MixedbreadAI
+
+from langchain.callbacks.tracers import ConsoleCallbackHandler
+from langchain_huggingface import HuggingFaceEmbeddings 
+import os
+from chroma_datasets.utils import import_into_chroma
+from datasets import load_dataset
+
+# Global params
+CHROMA_PATH = "chromadb_mem10_mxbai_800_complete"
+MODEL_EMB = "mxbai-embed-large"
+MODEL_RRK = "mixedbread-ai/mxbai-rerank-large-v1"
+LLM_NAME = "gpt-4o-mini"
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
+MXBAI_API_KEY = os.environ.get("MXBAI_API_KEY")
+
+# Load the reranker model
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+mxbai_client = MixedbreadAI(api_key=MXBAI_API_KEY)
+model_emb = "mixedbread-ai/mxbai-embed-large-v1"  
+
+# Set up ChromaDB
+client = chromadb.Client()
+dataset = load_dataset("eliot-hub/memoires_vec_800", split="data")
+# client = chromadb.PersistentClient(path=os.path.join(os.path.abspath(os.getcwd()), "01_Notebooks", "RAG-ollama", "chatbot_actuariat_APP", CHROMA_PATH))
+
+
+db = import_into_chroma(
+    chroma_client=client,
+    dataset=dataset,
+    embedding_function=HuggingFaceEmbeddings(model_name=model_emb)
+    )
+# db = Chroma(
+#     client=client,
+#     collection_name=f"embeddings_mxbai",
+#     embedding_function= HuggingFaceEmbeddings(model_name=model_emb) 
+# )
+
+
+# Reranker class
+class Reranker(BaseRetriever):
+    retriever: VectorStoreRetriever
+    # model: CrossEncoder
+    k: int
+
+    def _get_relevant_documents(
+        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
+    ) -> List[Document]:
+        docs = self.retriever.invoke(query)
+        results = mxbai_client.reranking(model="mixedbread-ai/mxbai-rerank-large-v1", query=query, input=[doc.page_content for doc in docs], return_input=True, top_k=self.k)
+        return [Document(page_content=res.input) for res in results.data]
+
+# Set up reranker + LLM
+retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 25})
+reranker = Reranker(retriever=retriever, k=4)  #Reranker(retriever=retriever, model=model, k=4)
+llm = ChatOpenAI(model=LLM_NAME, api_key=OPENAI_API_KEY, verbose=True)
+
+# Set up the contextualize question prompt
+contextualize_q_system_prompt = (
+    "Compte tenu de l'historique des discussions et de la dernière question de l'utilisateur "
+    "qui peut faire référence à un contexte dans l'historique du chat, "
+    "formuler une question autonome qui peut être comprise "
+    "sans l'historique du chat. Ne répondez PAS à la question, "
+    "juste la reformuler si nécessaire et sinon la renvoyer telle quelle."
+)
+
+contextualize_q_prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", contextualize_q_system_prompt),
+        MessagesPlaceholder("chat_history"),
+        ("human", "{input}"),
+    ]
+)
+
+# Create the history-aware retriever
+history_aware_retriever = create_history_aware_retriever(
+    llm, reranker, contextualize_q_prompt
+)
+
+# Set up the QA prompt
+system_prompt = (
+    "Réponds à la question en te basant uniquement sur le contexte suivant: \n\n {context}"
+)
+qa_prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", system_prompt),
+        MessagesPlaceholder("chat_history"),
+        ("human", "{input}"),
+    ]
+)
+
+# Create the question-answer chain
+question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
+rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)
+
+# Set up the conversation history
+store = {}
+
+def get_session_history(session_id: str) -> ChatMessageHistory:
+    if session_id not in store:
+        store[session_id] = ChatMessageHistory()
+    return store[session_id]
+
+conversational_rag_chain = RunnableWithMessageHistory(
+    rag_chain,
+    get_session_history,
+    input_messages_key="input",
+    history_messages_key="chat_history",
+    output_messages_key="answer",
+)
+
+# Gradio interface
+def chatbot(message, history):
+    session_id = "gradio_session"
+    response = conversational_rag_chain.invoke(
+        {"input": message},
+        config={
+            "configurable": {"session_id": session_id},
+            "callbacks": [ConsoleCallbackHandler()]
+        },
+    )["answer"]
+    return response
+
+iface = gr.ChatInterface(
+    chatbot,
+    title="Assurance Chatbot",
+    description="Posez vos questions sur l'assurance",
+    theme="soft",
+    examples=[
+        "Qu'est-ce que l'assurance multirisque habitation ?",
+        "Qu'est-ce que la garantie DTA ?",
+    ],
+    retry_btn=None,
+    undo_btn=None,
+    clear_btn="Effacer la conversation",
+)
+
+if __name__ == "__main__":
+    iface.launch()  # share=True

requirements.txt

@@ -0,0 +1,194 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiosignal==1.3.1
+altair==5.4.1
+annotated-types==0.7.0
+anyio==4.4.0
+asgiref==3.8.1
+asttokens==2.4.1
+attrs==24.2.0
+backoff==2.2.1
+bcrypt==4.2.0
+blinker==1.8.2
+build==1.2.1
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+chroma-datasets==0.1.5
+chroma-hnswlib==0.7.6
+chromadb==0.5.7
+click==8.1.7
+colorama==0.4.6
+coloredlogs==15.0.1
+comm==0.2.2
+contourpy==1.3.0
+cycler==0.12.1
+dataclasses-json==0.6.7
+datasets==3.0.0
+debugpy==1.8.5
+decorator==5.1.1
+Deprecated==1.2.14
+dill==0.3.8
+distro==1.9.0
+executing==2.1.0
+fastapi==0.112.2
+ffmpy==0.4.0
+filelock==3.15.4
+flatbuffers==24.3.25
+fonttools==4.54.0
+frozenlist==1.4.1
+fsspec==2024.6.1
+gitdb==4.0.11
+GitPython==3.1.43
+google-auth==2.34.0
+googleapis-common-protos==1.65.0
+gradio==4.44.0
+gradio_client==1.3.0
+greenlet==3.0.3
+grpcio==1.66.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.2
+httpx-sse==0.4.0
+huggingface-hub==0.24.6
+humanfriendly==10.0
+idna==3.8
+importlib_metadata==8.4.0
+importlib_resources==6.4.4
+ipykernel==6.29.5
+ipython==8.27.0
+jedi==0.19.1
+Jinja2==3.1.4
+jiter==0.5.0
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+jupyter_client==8.6.2
+jupyter_core==5.7.2
+kiwisolver==1.4.7
+kubernetes==30.1.0
+langchain==0.3.0
+langchain-chroma==0.1.4
+langchain-community==0.3.0
+langchain-core==0.3.5
+langchain-huggingface==0.1.0
+langchain-openai==0.2.0
+langchain-text-splitters==0.3.0
+langsmith==0.1.126
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.22.0
+matplotlib==3.9.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mixedbread-ai==2.2.6
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+multiprocess==0.70.16
+mypy-extensions==1.0.0
+narwhals==1.6.0
+nest-asyncio==1.6.0
+networkx==3.3
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.19.0
+openai==1.43.0
+opentelemetry-api==1.27.0
+opentelemetry-exporter-otlp-proto-common==1.27.0
+opentelemetry-exporter-otlp-proto-grpc==1.27.0
+opentelemetry-instrumentation==0.48b0
+opentelemetry-instrumentation-asgi==0.48b0
+opentelemetry-instrumentation-fastapi==0.48b0
+opentelemetry-proto==1.27.0
+opentelemetry-sdk==1.27.0
+opentelemetry-semantic-conventions==0.48b0
+opentelemetry-util-http==0.48b0
+orjson==3.10.7
+overrides==7.7.0
+packaging==24.1
+pandas==2.2.2
+parso==0.8.4
+pillow==10.4.0
+platformdirs==4.3.2
+posthog==3.6.0
+prompt_toolkit==3.0.47
+protobuf==4.25.4
+psutil==6.0.0
+pure_eval==0.2.3
+pyarrow==17.0.0
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
+pydantic==2.8.2
+pydantic-settings==2.5.2
+pydantic_core==2.20.1
+pydeck==0.9.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+pypdf==4.3.1
+PyPika==0.48.9
+pyproject_hooks==1.1.0
+pyreadline3==3.4.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.10
+pytz==2024.1
+pywin32==306
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.7.24
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.8.0
+rpds-py==0.20.0
+rsa==4.9
+ruff==0.6.7
+safetensors==0.4.4
+scikit-learn==1.5.2
+scipy==1.14.1
+semantic-version==2.10.0
+sentence-transformers==3.1.1
+sentencepiece==0.2.0
+setuptools==72.1.0
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+SQLAlchemy==2.0.32
+stack-data==0.6.3
+starlette==0.38.4
+sympy==1.13.2
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tiktoken==0.7.0
+tokenizers==0.19.1
+toml==0.10.2
+tomlkit==0.12.0
+torch==2.4.0
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.44.2
+typer==0.12.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.6
+watchdog==4.0.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websocket-client==1.8.0
+websockets==12.0
+wheel==0.43.0
+wrapt==1.16.0
+xxhash==3.5.0
+yarl==1.9.7
+zipp==3.20.1