Dockerized application. Added UI

.env.example

@@ -0,0 +1 @@
+OPENAI_API_KEY=your_api_key_here

.gitignore

@@ -5,14 +5,61 @@
 /lib
 /lib64
 /share
-/app/chroma_db
 /chunks
-/logs
+backend/chunks
+backend/logs/*
 /app/utils/__pycache__
+/node_modules
+backend/chroma_db/*
+backend/chunks/*
 
 # Ignore files #
 ################
 *.cfg
 *.bin
 *.keep
-.idea
+.idea
+__pycache__
+
+# Python #
+##########
+*.py[cod]
+*.pyo
+*.pyd
+*.env
+*.venv
+env/
+venv/
+ENV/
+VENV/
+*.egg
+*.egg-info
+dist/
+build/
+*.manifest
+*.spec
+
+# Jupyter Notebooks #
+#####################
+.ipynb_checkpoints
+
+# macOS #
+#########
+.DS_Store
+
+# Windows #
+###########
+Thumbs.db
+ehthumbs.db
+Desktop.ini
+$RECYCLE.BIN/
+
+# Logs and databases #
+######################
+*.log
+*.sql
+*.sqlite
+
+# VS Code #
+###########
+.vscode/

backend/Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . .
+
+ENV PYTHONPATH=/app
+
+# Expose the API port
+EXPOSE 8000
+
+# Run the FastAPI application
+CMD ["uvicorn", "api.base_api:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]

backend/app/api/base_api.py

@@ -0,0 +1,79 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+
+import sys
+sys.path.append("app")
+from ..main import NexusPJLLM
+from utils.ingerir import extractor, sintetizador_respuesta, guardar_nodos, embedding_model
+from utils.logs import logger
+
+app = FastAPI()
+
+# Configure CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"], 
+    allow_credentials=True,
+    allow_methods=["*"], 
+    allow_headers=["*"],
+)
+
+class ConsultaRequest(BaseModel):
+    consulta: str
+
+class Respuesta(BaseModel):
+    respuesta: str
+
+class NodosResponse(BaseModel):
+    nodos: list
+
+nexus = NexusPJLLM()
+
+@app.post("/extraer", response_model=NodosResponse)
+async def extraer(request: ConsultaRequest):
+    try:
+        consulta = request.consulta
+        nodes = extractor(consulta, embedding_model)
+
+        # Handle case where extractor returns None or empty results
+        if not nodes:
+            return {"nodos": []}
+
+        retrieved_nodes = nexus.procesar_consulta(consulta)
+        guardar_nodos(nodes)
+
+        return {
+            "nodos": [
+                {"metadata": node.metadata, "texto": node.text} 
+                for node in retrieved_nodes
+            ]
+        }
+    except Exception as e:
+        logger.error(f"Error procesando consulta: {str(e)}")
+        raise HTTPException(
+            status_code=500,
+            detail=f"Error procesando consulta: {str(e)}"
+        )
+
+@app.post("/sintetizar", response_model=Respuesta)
+async def sintetizar(request: ConsultaRequest):
+    try:
+        consulta = request.consulta
+        retrieved_nodes = nexus.procesar_consulta(consulta, reranker=True)
+        respuesta = sintetizador_respuesta(consulta, retrieved_nodes)
+        respuesta = str(respuesta)
+        return {"respuesta": respuesta}
+    except Exception as e:
+        logger.error(f"Error en opción 2: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Error en opción 2: {str(e)}")
+
+@app.post("/buscar", response_model=NodosResponse)
+async def buscar(request: ConsultaRequest):
+    try:
+        consulta = request.consulta
+        retrieved_nodes = nexus.procesar_consulta(consulta, reranker=True)
+        return {"nodos": [{"metadata": node.metadata, "texto": node.text} for node in retrieved_nodes]}
+    except Exception as e:
+        logger.error(f"Error en opción 3: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Error en opción 3: {str(e)}")

backend/requirements.txt

@@ -0,0 +1,176 @@
+aiohappyeyeballs==2.4.3 ; python_version >= "3.12" and python_version < "4.0"
+aiohttp==3.11.7 ; python_version >= "3.12" and python_version < "4.0"
+aiosignal==1.3.1 ; python_version >= "3.12" and python_version < "4.0"
+annotated-types==0.7.0 ; python_version >= "3.12" and python_version < "4.0"
+anyio==4.6.2.post1 ; python_version >= "3.12" and python_version < "4.0"
+asgiref==3.8.1 ; python_version >= "3.12" and python_version < "4.0"
+attrs==24.2.0 ; python_version >= "3.12" and python_version < "4.0"
+backoff==2.2.1 ; python_version >= "3.12" and python_version < "4.0"
+bcrypt==4.2.1 ; python_version >= "3.12" and python_version < "4.0"
+beautifulsoup4==4.12.3 ; python_version >= "3.12" and python_version < "4.0"
+build==1.2.2.post1 ; python_version >= "3.12" and python_version < "4.0"
+cachetools==5.5.0 ; python_version >= "3.12" and python_version < "4.0"
+certifi==2024.8.30 ; python_version >= "3.12" and python_version < "4.0"
+charset-normalizer==3.4.0 ; python_version >= "3.12" and python_version < "4.0"
+chroma-hnswlib==0.7.6 ; python_version >= "3.12" and python_version < "4.0"
+chroma==0.2.0 ; python_version >= "3.12" and python_version < "4.0"
+chromadb==0.5.20 ; python_version >= "3.12" and python_version < "4.0"
+click==8.1.7 ; python_version >= "3.12" and python_version < "4.0"
+colorama==0.4.6 ; python_version >= "3.12" and python_version < "4.0" and (sys_platform == "win32" or os_name == "nt" or platform_system == "Windows")
+coloredlogs==15.0.1 ; python_version >= "3.12" and python_version < "4.0"
+colorlog==6.9.0 ; python_version >= "3.12" and python_version < "4.0"
+dataclasses-json==0.6.7 ; python_version >= "3.12" and python_version < "4.0"
+deprecated==1.2.15 ; python_version >= "3.12" and python_version < "4.0"
+dirtyjson==1.0.8 ; python_version >= "3.12" and python_version < "4.0"
+distro==1.9.0 ; python_version >= "3.12" and python_version < "4.0"
+durationpy==0.9 ; python_version >= "3.12" and python_version < "4.0"
+fastapi==0.115.5 ; python_version >= "3.12" and python_version < "4.0"
+filelock==3.16.1 ; python_version >= "3.12" and python_version < "4.0"
+filetype==1.2.0 ; python_version >= "3.12" and python_version < "4.0"
+flatbuffers==24.3.25 ; python_version >= "3.12" and python_version < "4.0"
+frozenlist==1.5.0 ; python_version >= "3.12" and python_version < "4.0"
+fsspec==2024.10.0 ; python_version >= "3.12" and python_version < "4.0"
+google-auth==2.36.0 ; python_version >= "3.12" and python_version < "4.0"
+googleapis-common-protos==1.66.0 ; python_version >= "3.12" and python_version < "4.0"
+greenlet==3.1.1 ; python_version >= "3.12" and python_version < "4.0"
+grpcio==1.68.0 ; python_version >= "3.12" and python_version < "4.0"
+h11==0.14.0 ; python_version >= "3.12" and python_version < "4.0"
+httpcore==1.0.7 ; python_version >= "3.12" and python_version < "4.0"
+httptools==0.6.4 ; python_version >= "3.12" and python_version < "4.0"
+httpx==0.27.2 ; python_version >= "3.12" and python_version < "4.0"
+huggingface-hub==0.26.2 ; python_version >= "3.12" and python_version < "4.0"
+humanfriendly==10.0 ; python_version >= "3.12" and python_version < "4.0"
+idna==3.10 ; python_version >= "3.12" and python_version < "4.0"
+importlib-metadata==8.5.0 ; python_version >= "3.12" and python_version < "4.0"
+importlib-resources==6.4.5 ; python_version >= "3.12" and python_version < "4.0"
+jinja2==3.1.4 ; python_version >= "3.12" and python_version < "4.0"
+jiter==0.7.1 ; python_version >= "3.12" and python_version < "4.0"
+joblib==1.4.2 ; python_version >= "3.12" and python_version < "4.0"
+jsonpatch==1.33 ; python_version >= "3.12" and python_version < "4.0"
+jsonpointer==3.0.0 ; python_version >= "3.12" and python_version < "4.0"
+keybert==0.8.5 ; python_version >= "3.12" and python_version < "4.0"
+kubernetes==31.0.0 ; python_version >= "3.12" and python_version < "4.0"
+langchain-core==0.3.21 ; python_version >= "3.12" and python_version < "4.0"
+langchain-text-splitters==0.3.2 ; python_version >= "3.12" and python_version < "4.0"
+langchain==0.3.8 ; python_version >= "3.12" and python_version < "4.0"
+langsmith==0.1.146 ; python_version >= "3.12" and python_version < "4.0"
+llama-cloud==0.1.5 ; python_version >= "3.12" and python_version < "4"
+llama-index-agent-openai==0.4.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-cli==0.4.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-core==0.12.1 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-embeddings-ollama==0.4.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-embeddings-openai==0.3.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-indices-managed-llama-cloud==0.6.2 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-legacy==0.9.48.post4 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-llms-ollama==0.4.1 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-llms-openai==0.3.2 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-multi-modal-llms-openai==0.3.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-program-openai==0.3.1 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-question-gen-openai==0.3.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-readers-file==0.4.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-readers-llama-parse==0.4.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index-vector-stores-chroma==0.4.0 ; python_version >= "3.12" and python_version < "4.0"
+llama-index==0.12.1 ; python_version >= "3.12" and python_version < "4.0"
+llama-parse==0.5.15 ; python_version >= "3.12" and python_version < "4.0"
+markdown-it-py==3.0.0 ; python_version >= "3.12" and python_version < "4.0"
+markupsafe==3.0.2 ; python_version >= "3.12" and python_version < "4.0"
+marshmallow==3.23.1 ; python_version >= "3.12" and python_version < "4.0"
+mdurl==0.1.2 ; python_version >= "3.12" and python_version < "4.0"
+mmh3==5.0.1 ; python_version >= "3.12" and python_version < "4.0"
+monotonic==1.6 ; python_version >= "3.12" and python_version < "4.0"
+mpmath==1.3.0 ; python_version >= "3.12" and python_version < "4.0"
+multidict==6.1.0 ; python_version >= "3.12" and python_version < "4.0"
+mypy-extensions==1.0.0 ; python_version >= "3.12" and python_version < "4.0"
+nest-asyncio==1.6.0 ; python_version >= "3.12" and python_version < "4.0"
+networkx==3.4.2 ; python_version >= "3.12" and python_version < "4.0"
+nltk==3.9.1 ; python_version >= "3.12" and python_version < "4.0"
+numpy==1.26.4 ; python_version >= "3.12" and python_version < "4.0"
+nvidia-cublas-cu12==12.4.5.8 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cuda-cupti-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cuda-nvrtc-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cuda-runtime-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cudnn-cu12==9.1.0.70 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cufft-cu12==11.2.1.3 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-curand-cu12==10.3.5.147 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cusolver-cu12==11.6.1.9 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-cusparse-cu12==12.3.1.170 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-nccl-cu12==2.21.5 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-nvjitlink-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+nvidia-nvtx-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12" and python_version < "4.0"
+oauthlib==3.2.2 ; python_version >= "3.12" and python_version < "4.0"
+ollama==0.3.3 ; python_version >= "3.12" and python_version < "4.0"
+onnxruntime==1.20.1 ; python_version >= "3.12" and python_version < "4.0"
+openai==1.55.1 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-api==1.28.2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-exporter-otlp-proto-common==1.28.2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-exporter-otlp-proto-grpc==1.28.2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-instrumentation-asgi==0.49b2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-instrumentation-fastapi==0.49b2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-instrumentation==0.49b2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-proto==1.28.2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-sdk==1.28.2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-semantic-conventions==0.49b2 ; python_version >= "3.12" and python_version < "4.0"
+opentelemetry-util-http==0.49b2 ; python_version >= "3.12" and python_version < "4.0"
+orjson==3.10.12 ; python_version >= "3.12" and python_version < "4.0"
+overrides==7.7.0 ; python_version >= "3.12" and python_version < "4.0"
+packaging==24.2 ; python_version >= "3.12" and python_version < "4.0"
+pandas==2.2.3 ; python_version >= "3.12" and python_version < "4.0"
+pillow==11.0.0 ; python_version >= "3.12" and python_version < "4.0"
+posthog==3.7.3 ; python_version >= "3.12" and python_version < "4.0"
+propcache==0.2.0 ; python_version >= "3.12" and python_version < "4.0"
+protobuf==5.28.3 ; python_version >= "3.12" and python_version < "4.0"
+pyasn1-modules==0.4.1 ; python_version >= "3.12" and python_version < "4.0"
+pyasn1==0.6.1 ; python_version >= "3.12" and python_version < "4.0"
+pydantic-core==2.23.4 ; python_version >= "3.12" and python_version < "4.0"
+pydantic==2.9.2 ; python_version >= "3.12" and python_version < "4.0"
+pygments==2.18.0 ; python_version >= "3.12" and python_version < "4.0"
+pypdf==5.1.0 ; python_version >= "3.12" and python_version < "4.0"
+pypika==0.48.9 ; python_version >= "3.12" and python_version < "4.0"
+pyproject-hooks==1.2.0 ; python_version >= "3.12" and python_version < "4.0"
+pyreadline3==3.5.4 ; sys_platform == "win32" and python_version >= "3.12" and python_version < "4.0"
+python-dateutil==2.9.0.post0 ; python_version >= "3.12" and python_version < "4.0"
+python-dotenv==1.0.1 ; python_version >= "3.12" and python_version < "4.0"
+pytz==2024.2 ; python_version >= "3.12" and python_version < "4.0"
+pyyaml==6.0.2 ; python_version >= "3.12" and python_version < "4.0"
+regex==2024.11.6 ; python_version >= "3.12" and python_version < "4.0"
+requests-oauthlib==2.0.0 ; python_version >= "3.12" and python_version < "4.0"
+requests-toolbelt==1.0.0 ; python_version >= "3.12" and python_version < "4.0"
+requests==2.32.3 ; python_version >= "3.12" and python_version < "4.0"
+rich==13.9.4 ; python_version >= "3.12" and python_version < "4.0"
+rsa==4.9 ; python_version >= "3.12" and python_version < "4"
+safetensors==0.4.5 ; python_version >= "3.12" and python_version < "4.0"
+scikit-learn==1.5.2 ; python_version >= "3.12" and python_version < "4.0"
+scipy==1.14.1 ; python_version >= "3.12" and python_version < "4.0"
+sentence-transformers==3.3.1 ; python_version >= "3.12" and python_version < "4.0"
+setuptools==75.6.0 ; python_version >= "3.12" and python_version < "4.0"
+shellingham==1.5.4 ; python_version >= "3.12" and python_version < "4.0"
+six==1.16.0 ; python_version >= "3.12" and python_version < "4.0"
+sniffio==1.3.1 ; python_version >= "3.12" and python_version < "4.0"
+soupsieve==2.6 ; python_version >= "3.12" and python_version < "4.0"
+sqlalchemy==2.0.36 ; python_version >= "3.12" and python_version < "4.0"
+sqlalchemy[asyncio]==2.0.36 ; python_version >= "3.12" and python_version < "4.0"
+starlette==0.41.3 ; python_version >= "3.12" and python_version < "4.0"
+striprtf==0.0.26 ; python_version >= "3.12" and python_version < "4.0"
+sympy==1.13.1 ; python_version >= "3.12" and python_version < "4.0"
+tenacity==8.5.0 ; python_version >= "3.12" and python_version < "4.0"
+threadpoolctl==3.5.0 ; python_version >= "3.12" and python_version < "4.0"
+tiktoken==0.8.0 ; python_version >= "3.12" and python_version < "4.0"
+tokenizers==0.20.3 ; python_version >= "3.12" and python_version < "4.0"
+torch==2.5.1 ; python_version >= "3.12" and python_version < "4.0"
+tqdm==4.67.1 ; python_version >= "3.12" and python_version < "4.0"
+transformers==4.46.3 ; python_version >= "3.12" and python_version < "4.0"
+triton==3.1.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version < "3.13" and python_version >= "3.12"
+typer==0.13.1 ; python_version >= "3.12" and python_version < "4.0"
+typing-extensions==4.12.2 ; python_version >= "3.12" and python_version < "4.0"
+typing-inspect==0.9.0 ; python_version >= "3.12" and python_version < "4.0"
+tzdata==2024.2 ; python_version >= "3.12" and python_version < "4.0"
+urllib3==2.2.3 ; python_version >= "3.12" and python_version < "4.0"
+uvicorn==0.32.1 ; python_version >= "3.12" and python_version < "4.0"
+uvicorn[standard]==0.32.1 ; python_version >= "3.12" and python_version < "4.0"
+uvloop==0.21.0 ; (sys_platform != "win32" and sys_platform != "cygwin") and platform_python_implementation != "PyPy" and python_version >= "3.12" and python_version < "4.0"
+watchfiles==1.0.0 ; python_version >= "3.12" and python_version < "4.0"
+websocket-client==1.8.0 ; python_version >= "3.12" and python_version < "4.0"
+websockets==14.1 ; python_version >= "3.12" and python_version < "4.0"
+wrapt==1.17.0 ; python_version >= "3.12" and python_version < "4.0"
+yarl==1.18.0 ; python_version >= "3.12" and python_version < "4.0"
+zipp==3.21.0 ; python_version >= "3.12" and python_version < "4.0"