Update with Mistral and rag PDF

.gitignore

@@ -0,0 +1,162 @@
+.idea/
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# 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__/
+
+# 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/

HOW_TO.md

@@ -0,0 +1,31 @@
+# INSTALLING
+
+> Clone the project in a local folder 'viti'
+
+> Go to the project folder
+
+`python -m venv .venv`
+
+`source .venv/bin/activate`
+
+`pip install -r requirements.txt`
+
+Test the installation
+
+`streamlit run app.py`
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# REF
+
+https://github.com/couchbase-examples/rag-demo-llama-index/blob/main/chat_with_pdf.py
+
+https://lightning.ai/maxidiazbattan/studios/rag-streamlit-llamaindex-ollama?tab=files&layout=column&path=cloudspaces%2F01hwfjrdss66hkje94vb7enf15&y=2&x=0
+
+https://medium.com/@sindhu.madicherla/rag-chatbot-using-chromadb-llamaindex-open-ai-and-streamlit-d3fb87df415f
+
+https://github.com/jacttp/simpleRAG/blob/main/rag.py
+
+https://github.com/naimkatiman/RAG-using-Llama-3.1-WebUi-on-Streamlit/blob/main/app.py
+
+

README.md

@@ -1,8 +1,8 @@
 ---
-title: Gc
-emoji: 🏆
-colorFrom: indigo
-colorTo: pink
+title: GC
+emoji: 💻
+colorFrom: green
+colorTo: red
 sdk: streamlit
 sdk_version: 1.38.0
 app_file: app.py

app.py

@@ -0,0 +1,89 @@
+import os
+import tempfile
+import streamlit as st
+from streamlit_chat import message
+from rag import ChatPDF
+
+title = "Simulateur IA Grandes cultures"
+subtitle = "Poser vos questions"
+description = "Demonstrateur GC"
+LOGO = "images/agir.png"
+form_help ="Vous pouvez compléter les informations ci-dessous pour personnaliser votre expérience"
+placeholder = (
+    "Vous pouvez me posez une question sur vos attentes, appuyer sur Entrée pour valider"
+)
+placeholder_doc = (
+    "Vous pouvez charger un grand livre ou des écritures comptables au format PDF"
+)
+placeholder_url = "Récupérer les données de ce lien."
+
+# st.title(title)
+
+st.set_page_config(page_title=title)
+
+def display_messages():
+    st.subheader(subtitle)
+    for i, (msg, is_user) in enumerate(st.session_state["messages"]):
+        message(msg, is_user=is_user, key=str(i))
+    st.session_state["thinking_spinner"] = st.empty()
+
+
+def process_input():
+    if st.session_state["user_input"] and len(st.session_state["user_input"].strip()) > 0:
+        user_text = st.session_state["user_input"].strip()
+        with st.session_state["thinking_spinner"], st.spinner(f"Je réfléchis"):
+            agent_text = st.session_state["assistant"].ask(user_text)
+
+        st.session_state["messages"].append((user_text, True))
+        st.session_state["messages"].append((agent_text, False))
+
+
+def read_and_save_file():
+    st.session_state["assistant"].clear()
+    st.session_state["messages"] = []
+    st.session_state["user_input"] = ""
+
+    for file in st.session_state["file_uploader"]:
+        with tempfile.NamedTemporaryFile(delete=False) as tf:
+            tf.write(file.getbuffer())
+            file_path = tf.name
+
+        with st.session_state["ingestion_spinner"], st.spinner(f"Chargement {file.name}"):
+            st.session_state["assistant"].ingest(file_path)
+        os.remove(file_path)
+
+
+def page():
+    if len(st.session_state) == 0:
+        st.session_state["messages"] = []
+        st.session_state["assistant"] = ChatPDF()
+
+    
+    st.logo(LOGO)
+    st.sidebar.markdown(form_help)
+    info1 = st.sidebar.text_input("Info 1", type="default")
+    info1 = st.sidebar.text_input("Info 2", type="default")
+    info1 = st.sidebar.text_input("Info 3", type="default")
+
+    st.header(title)
+
+    st.subheader("Charger un ou plusieurs documents")
+    st.caption(placeholder_doc)
+    st.file_uploader(
+        "Charger un document",
+        type=["pdf"],
+        key="file_uploader",
+        on_change=read_and_save_file,
+        label_visibility="collapsed",
+        accept_multiple_files=True,
+    )
+
+    st.session_state["ingestion_spinner"] = st.empty()
+
+    display_messages()
+    st.caption(placeholder)
+    st.text_input("Message", key="user_input", on_change=process_input)
+
+
+if __name__ == "__main__":
+    page()

rag.py

@@ -0,0 +1,81 @@
+import os
+# __import__('pysqlite3')
+# import sys
+# sys.modules['sqlite3'] = sys.modules.pop('pysqlite3')
+from dotenv import load_dotenv
+from langchain_community.vectorstores import FAISS
+from langchain_mistralai.chat_models import ChatMistralAI
+from langchain_mistralai.embeddings import MistralAIEmbeddings
+from langchain.schema.output_parser import StrOutputParser
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.schema.runnable import RunnablePassthrough
+from langchain.prompts import PromptTemplate
+from langchain_community.vectorstores.utils import filter_complex_metadata
+#add new import
+from langchain_community.document_loaders.csv_loader import CSVLoader
+
+# load .env in local dev
+load_dotenv()
+env_api_key = os.environ.get("MISTRAL_API_KEY")
+llm_model = "open-mixtral-8x7b"
+
+class ChatPDF:
+    vector_store = None
+    retriever = None
+    chain = None
+
+    def __init__(self):
+        # https://python.langchain.com/docs/integrations/chat/mistralai/
+        self.model = ChatMistralAI(model=llm_model)
+        self.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1024, chunk_overlap=100)
+        self.prompt = PromptTemplate.from_template(
+            """
+            <s> [INST] Vous échangez en français et avec précision.
+            Vous êtes un assistant comptable spécialisé dans la comptabilité agricole en grandes cultures.
+            Vous devez analyser les documents ci-dessous et calculer les couts de productions.
+            Les documents fournis représente la comptabilité de l'exploitation agricole.
+            Vous devez répondre sous forme de tableaux et de textes.
+            Vous devez répondre de façon synthétique et argumentée.
+            [/INST] </s> 
+            [INST] 
+            Question: {question} 
+            Context: {context} 
+            Answer: [/INST]
+            """
+        )
+
+    def ingest(self, pdf_file_path: str):
+        docs = PyPDFLoader(file_path=pdf_file_path).load()
+       
+        
+        chunks = self.text_splitter.split_documents(docs)
+        chunks = filter_complex_metadata(chunks)
+
+        embeddings = MistralAIEmbeddings(model="mistral-embed", mistral_api_key=env_api_key)
+
+        vector_store = FAISS.from_documents(chunks, embeddings)
+        # vector_store = Chroma.from_documents(documents=chunks, embedding=embeddings)
+        self.retriever = vector_store.as_retriever(
+            search_type="similarity_score_threshold",
+            search_kwargs={
+                "k": 3,
+                "score_threshold": 0.5,
+            },
+        )
+
+        self.chain = ({"context": self.retriever, "question": RunnablePassthrough()}
+                      | self.prompt
+                      | self.model
+                      | StrOutputParser())
+
+    def ask(self, query: str):
+        if not self.chain:
+            return "Ajouter un document PDF d'abord."
+
+        return self.chain.invoke(query)
+
+    def clear(self):
+        self.vector_store = None
+        self.retriever = None
+        self.chain = None

requirements.txt

@@ -0,0 +1,8 @@
+langchain
+langchain_mistralai
+langchain-community
+streamlit==1.38.0
+streamlit-chat
+pypdf
+fastembed
+faiss-gpu