First run

.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 +1,17 @@
+# 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

app.py

@@ -1,78 +1,120 @@
 import os
+import json
 import time
 from pathlib import Path
-
+from dotenv import load_dotenv
 import numpy as np
 import streamlit as st
-import leafmap.foliumap as leafmap
-from faiss import IndexFlatL2
-from mistralai.client import MistralClient
-from mistralai.models.chat_completion import ChatMessage
-from pypdf import PdfReader
-
-@st.cache_resource
-def get_client():
-    """Returns a cached instance of the MistralClient."""
-    api_key = os.environ["MISTRAL_API_KEY"]
-    return MistralClient(api_key=api_key)
-
-
-CLIENT: MistralClient = get_client()
-
-PROMPT = """
-An excerpt from a document is given below.
-
----------------------
-{context}
----------------------
-
-Given the document excerpt, answer the following query.
-If the context does not provide enough information, decline to answer.
-Do not output anything that can't be answered from the context.
-
-Query: {query}
-Answer:
-"""
-
-def app():
-    st.title("Search Basemaps")
-    st.markdown(
-        """
-    This app is a demonstration of searching and loading basemaps from [xyzservices](https://github.com/geopandas/xyzservices) and [Quick Map Services (QMS)](https://github.com/nextgis/quickmapservices). Selecting from 1000+ basemaps with a few clicks.
+from mistralai import Mistral, UserMessage
+import json
+import faiss
+
+# load .env in local dev
+load_dotenv()
+
+title = "Simulateur IA Viti"
+description = "Demonstrateur Viti"
+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 la transmission de votre domaine, appuyer sur Entrée pour valider"
+)
+placeholder_url = "Récupérer les données de ce lien."
+llm_model = "open-mixtral-8x7b"
+
+env_api_key = os.environ.get("MISTRAL_API_KEY")
+query_engine = None
+
+# Define LLMs
+client = Mistral(api_key=env_api_key)
+
+st.title(title)
+
+st.caption(placeholder)
+st.logo(LOGO)
+st.sidebar.markdown(form_help)
+age = st.sidebar.text_input("Votre age", type="default")
+
+def load_json(rep:str):
+    f = open(rep, encoding='UTF-8')
+    return json.load(f)
+
+def split_chunk(data, chunk_size):
+    data_str = [json.dumps(entry) for entry in data]
+    chunk_size = chunk_size
+    chunks = [data_str[i:i + chunk_size] for i in range(0, len(data_str), chunk_size)]
+    print(f"Nb. chunks = {len(chunks)}")
+    return chunks
+    
+def get_text_embedding(input):
+    embeddings_batch_response = client.embeddings(
+          model='mistral-embed',
+          input=input
+      )
+    return embeddings_batch_response.data[0].embedding
+
+def load_vector_db(text_embedded):
+    d = text_embedded.shape[1]
+    index = faiss.IndexFlatL2(d)
+    index.add(text_embedded)
+    return index
+
+def find_similar_chunk(index, question_embeddings, chunks):
+    D, I = index.search(question_embeddings, k=2) # distance, index
+    return [chunks[i] for i in I.tolist()[0]]
+
+def prompt_chat(retrieved_chunk, question):
+    return f"""
+    Les informations contextuelles sont les suivantes.
+    ---------------------
+    {retrieved_chunk}
+    ---------------------
+    Compte tenu des informations contextuelles et sans connaissances préalables,
+    réponds en français à la question suivante de manière concise.
+    Utilise des listes pour plus de lisibilité. 
+    Question: {question}
+    Réponse:
     """
-    )
-
-    with st.expander("See demo"):
-        st.image("https://i.imgur.com/0SkUhZh.gif")
-
-    row1_col1, row1_col2 = st.columns([3, 1])
-    width = 800
-    height = 600
-    tiles = None
-
-    with row1_col2:
-
-        checkbox = st.checkbox("Search Quick Map Services (QMS)")
-        keyword = st.text_input("Enter a keyword to search and press Enter:")
-        empty = st.empty()
-
-        if keyword:
-            options = leafmap.search_xyz_services(keyword=keyword)
-            if checkbox:
-                qms = leafmap.search_qms(keyword=keyword)
-                if qms is not None:
-                    options = options + qms
-
-            tiles = empty.multiselect("Select XYZ tiles to add to the map:", options)
-
-        with row1_col1:
-            m = leafmap.Map()
-
-            if tiles is not None:
-                for tile in tiles:
-                    m.add_xyz_service(tile)
-
-            m.to_streamlit(height=height)
-
 
-app()
+# Chargement des données
+# data = load_json('catalogue_2024.json')
+# chunks = split_chunk(data, 3)
+# text_embeddings = np.load("catalogue_embeddings.npy")
+# index = load_vector_db(text_embeddings)
+
+if "messages" not in st.session_state:
+    st.session_state["messages"] = [{"role": "assistant", "content": "Comment puis-je vous aider?"}]
+    st.session_state["History"] = []
+    st.session_state.History.append({"role": "assitant", "content": "Comment puis-je vous aider?"})
+
+for msg in st.session_state.messages:
+    st.chat_message(msg["role"]).write(msg["content"])
+
+if prompt := st.chat_input():
+    # question_embeddings = np.array([get_text_embedding(prompt)])
+    # retrieved_chunk = find_similar_chunk(index, question_embeddings, chunks)
+    # p = prompt_chat(retrieved_chunk=retrieved_chunk, question=prompt)
+
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    # st.session_state.History.append({"role": "user", "content": p})
+    st.chat_message("user").write(prompt)
+
+    with st.chat_message("assistant"):
+        message_placeholder = st.empty()
+        full_response = ""
+        chat_response = client.chat.complete(
+            model=llm_model,
+            messages=st.session_state.messages[1:]
+        )
+
+        print(chat_response.choices[0])
+    
+        for choice in chat_response.choices:
+            print(choice)
+            full_response += (choice.message.content or "")
+            message_placeholder.markdown(full_response + "|")
+        
+        message_placeholder.markdown(full_response)
+        
+        st.session_state.History.append({"role": "assistant", "content": full_response})
+        st.session_state.messages.append({"role": "assistant", "content": full_response})

requirements.txt

@@ -1,13 +1,261 @@
-streamlit
-faiss-cpu
-pypdf
-mistralai
-fiona
-folium #==0.13.0
-geopandas
-leafmap>=0.35.2
-streamlit-folium
-owslib
-palettable
-plotly
-git+https://github.com/giswqs/geemap
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiosignal==1.3.1
+altair==5.4.1
+annotated-types==0.7.0
+anyio==4.5.0
+anywidget==0.9.13
+asgiref==3.8.1
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==24.2.0
+backoff==2.2.1
+bcrypt==4.2.0
+beautifulsoup4==4.12.3
+blinker==1.8.2
+bqplot==0.12.43
+branca==0.7.2
+build==1.2.2
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.6
+chromadb==0.5.7
+chromedriver-autoinstaller==0.6.4
+click==8.1.7
+click-plugins==1.1.1
+cligj==0.7.2
+coloredlogs==15.0.1
+colour==0.1.5
+comm==0.2.2
+contourpy==1.3.0
+cssselect==1.2.0
+cycler==0.12.1
+dataclasses-json==0.6.7
+decorator==5.1.1
+Deprecated==1.2.14
+dirtyjson==1.0.8
+distro==1.9.0
+duckdb==1.1.0
+earthengine-api==1.1.0
+eerepr==0.0.4
+eval_type_backport==0.2.0
+exceptiongroup==1.2.2
+executing==2.1.0
+faiss-cpu==1.8.0.post1
+fastapi==0.115.0
+feedfinder2==0.0.4
+feedparser==6.0.11
+filelock==3.16.1
+fiona==1.10.1
+flatbuffers==24.3.25
+folium==0.17.0
+fonttools==4.53.1
+frozenlist==1.4.1
+fsspec==2024.9.0
+future==1.0.0
+gdown==5.2.0
+geemap @ git+https://github.com/giswqs/geemap@1adb1a53b5bbb716199637e096f105ca8c727657
+geocoder==1.38.1
+geojson==3.1.0
+geopandas==1.0.1
+gitdb==4.0.11
+GitPython==3.1.43
+google-api-core==2.19.2
+google-api-python-client==2.146.0
+google-auth==2.34.0
+google-auth-httplib2==0.2.0
+google-cloud-core==2.4.1
+google-cloud-storage==2.18.2
+google-crc32c==1.6.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.65.0
+greenlet==3.0.3
+grpcio==1.66.1
+h11==0.14.0
+html2text==2024.2.26
+httpcore==1.0.5
+httplib2==0.22.0
+httptools==0.6.1
+httpx==0.27.2
+huggingface-hub==0.25.0
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.4.0
+importlib_resources==6.4.5
+ipyevents==2.0.2
+ipyfilechooser==0.6.0
+ipyleaflet==0.19.2
+ipython==8.27.0
+ipytree==0.2.2
+ipyvue==1.11.1
+ipyvuetify==1.10.0
+ipywidgets==8.1.5
+jedi==0.19.1
+jieba3k==0.35.1
+Jinja2==3.1.4
+jiter==0.5.0
+joblib==1.4.2
+jsonpath-python==1.0.6
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+jupyter-leaflet==0.19.2
+jupyterlab_widgets==3.0.13
+kiwisolver==1.4.7
+kubernetes==30.1.0
+leafmap==0.37.3
+llama-cloud==0.0.17
+llama-index==0.11.10
+llama-index-agent-openai==0.3.3
+llama-index-cli==0.3.1
+llama-index-core==0.11.10
+llama-index-embeddings-mistralai==0.2.0
+llama-index-embeddings-openai==0.2.5
+llama-index-indices-managed-llama-cloud==0.3.1
+llama-index-legacy==0.9.48.post3
+llama-index-llms-mistralai==0.2.5
+llama-index-llms-openai==0.2.9
+llama-index-multi-modal-llms-openai==0.2.1
+llama-index-program-openai==0.2.0
+llama-index-question-gen-openai==0.2.0
+llama-index-readers-file==0.2.1
+llama-index-readers-llama-parse==0.3.0
+llama-index-readers-web==0.2.2
+llama-index-vector-stores-chroma==0.2.0
+llama-parse==0.5.5
+lxml==5.3.0
+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
+mistralai==1.1.0
+mmh3==5.0.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+narwhals==1.8.1
+nest-asyncio==1.6.0
+networkx==3.3
+newspaper3k==0.2.8
+nltk==3.9.1
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.19.2
+openai==1.46.0
+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
+outcome==1.3.0.post0
+overrides==7.7.0
+OWSLib==0.31.0
+packaging==24.1
+palettable==3.3.3
+pandas==2.2.2
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.4.0
+playwright==1.47.0
+plotly==5.24.1
+posthog==3.6.6
+prompt_toolkit==3.0.47
+proto-plus==1.24.0
+protobuf==4.25.5
+psygnal==0.11.1
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==17.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydeck==0.9.1
+pyee==12.0.0
+Pygments==2.18.0
+pyogrio==0.9.0
+pyparsing==3.1.4
+pypdf==4.3.1
+pyperclip==1.9.0
+PyPika==0.48.9
+pyproj==3.6.1
+pyproject_hooks==1.1.0
+pyshp==2.3.1
+PySocks==1.7.1
+pystac==1.10.1
+pystac-client==0.8.3
+python-box==7.2.0
+python-dateutil==2.8.2
+python-dotenv==1.0.1
+pytz==2024.2
+PyYAML==6.0.2
+ratelim==0.1.6
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+requests-file==2.1.0
+requests-oauthlib==2.0.0
+rich==13.8.1
+rpds-py==0.20.0
+rsa==4.9
+scooby==0.10.0
+selenium==4.24.0
+sgmllib3k==1.0.0
+shapely==2.0.6
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+sortedcontainers==2.4.0
+soupsieve==2.6
+spider-client==0.0.27
+SQLAlchemy==2.0.35
+stack-data==0.6.3
+starlette==0.38.5
+streamlit==1.38.0
+streamlit_folium==0.22.1
+striprtf==0.0.26
+sympy==1.13.3
+tenacity==8.5.0
+tiktoken==0.7.0
+tinysegmenter==0.3
+tldextract==5.1.2
+tokenizers==0.20.0
+toml==0.10.2
+tomli==2.0.1
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+traittypes==0.2.1
+trio==0.26.2
+trio-websocket==0.11.1
+typer==0.12.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.1
+uritemplate==4.1.1
+urllib3==2.2.3
+uvicorn==0.30.6
+uvloop==0.20.0
+watchdog==4.0.2
+watchfiles==0.24.0
+wcwidth==0.2.13
+websocket-client==1.8.0
+websockets==13.0.1
+whitebox==2.3.5
+whiteboxgui==2.3.0
+widgetsnbextension==4.0.13
+wrapt==1.16.0
+wsproto==1.2.0
+xyzservices==2024.9.0
+yarl==1.11.1
+zipp==3.20.2