Dockerize full

README.md

@@ -1,12 +1,17 @@
-pip install llama-index
+El sistema funciona en un docker 
-pip install llama-index-llms-groq
+para generar:
-pip install llama-index-embeddings-huggingface
+
-pip install llama-parse
+docker build -t supertutor-app .
-pip install chromadb
-pip install llama-index-vector-stores-chroma
-pip install llama-index-embeddings-huggingface
-pip install python-fasthtml
-pip install grok
-pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
 
 
+
+para ejecutar:
+
+docker run -it -p 7884:7884 --rm fastapi-app
+
+
+
+si tienes problemas con permisos:
+
+sudo chmod 666 /var/run/docker.sock
+

dockerfile

@@ -0,0 +1,21 @@
+# Usar una imagen base de Python
+FROM python:3.11.10-bookworm
+# Establecer el directorio de trabajo en el contenedor
+WORKDIR /app
+
+# Copiar el archivo requirements.txt y otros archivos necesarios
+COPY requirements.txt ./
+
+# Instalar las dependencias de Python
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copiar todo el código de la aplicación al contenedor
+COPY . .
+
+# Expone el puerto que usará Uvicorn
+EXPOSE 7884
+
+# Especificar el comando 
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7884", "--reload"]
+

main.py

@@ -9,20 +9,23 @@ from llama_index.core import SummaryIndex
 from llama_index.llms.groq import Groq as GroqLLamaIndex
 from chromadb import PersistentClient
 from llama_index.core import Settings
-from llama_index.embeddings.huggingface_api import (
+#from llama_index.embeddings.huggingface_api import (
-    HuggingFaceInferenceAPIEmbedding,
+#    HuggingFaceInferenceAPIEmbedding,
-)
+#)
-
+import shutil
 import chromadb
 import os
 import threading
 import time
 from llama_index.core.memory import ChatMemoryBuffer
 import json
-from llama_index.llms.ollama import Ollama
+#from llama_index.llms.ollama import Ollama
 from llama_index.core.base.response.schema import Response
 from groq import Groq
-import shutil
+from fastapi import  File as FileFast
+from fastapi import UploadFile as UploadFileFast
+from fastapi import Form as FormFast
+#import shutil
 pwd = os.getcwd()
 def extractConfig(nameModel="SystemData",relPath=os.path.join(pwd,"conf/experiment_config.json"),dataOut="keyantrophics"):
     configPath=os.path.join(os.getcwd(),relPath)
@@ -50,8 +53,8 @@ Settings.llm = llm_localLlamma
 
 
 gridlink = Link(rel="stylesheet", href="https://cdnjs.cloudflare.com/ajax/libs/flexboxgrid/6.3.1/flexboxgrid.min.css", type="text/css")
-
+colorpico=Link(rel="stylesheet", href="https://cdn.jsdelivr.net/npm/@picocss/pico@2/css/pico.colors.min.css")
-app= FastHTML(hdrs=(picolink, gridlink))
+app= FastHTML(hdrs=(picolink, gridlink,colorpico))
 
 
 
@@ -78,9 +81,9 @@ def checkInfoSources(user:str):
         subdir = [Option(file.name,value="static/"+user+"/"+file.name) for file in files if  (file.is_dir() and file.name!="chroma_db") ]
     
     userdata=user
-    print("Cambio",userdata)
+
     return Form(
-    H3("Grupos de archivos",cls="col-xs-3"),
+    H3("Grupo de archivos",cls="col-xs-3"),
     Select(
     *subdir,name="data",cls="col-xs-3"),
     Input(id="name-db", name="collection", placeholder="Enter a collection name",cls="col-xs-4"),
@@ -163,7 +166,7 @@ def loadCollection(data:str):
 def queryPrompt(question:str):
     #index=load_create_db(collection="my_collection")
     
-    query_engine = index.as_query_engine(similarity_top_k=15,vector_store_query_mode="default",response_mode="tree_summarize")
+    query_engine = index.as_query_engine(similarity_top_k=5,vector_store_query_mode="default",response_mode="tree_summarize")
     summary_prompt = (
         "Por favor, genera un resumen completo y detallado del material dado. "
         "Incluye los principales temas, argumentos y conclusiones. "
@@ -191,7 +194,7 @@ def queryPrompt(question:str):
     response2 = query_engine.query(tematic_prompt)
     response3 = query_engine.query(issues_prompt)
     response4 = query_engine.query(Question_prompt)
-    Output="<H1>Summary</H1>"+str(response)+"<H1>Tematic</H1>"+str(response2)+"<H1>Issues</H1>"+str(response3)+"<H1>Questions</H1>"+str(response4)
+    Output="<H1>Resumen</H1>"+str(response)+"<H1>Tematica</H1>"+str(response2)+"<H1>Problemas</H1>"+str(response3)+"<H1>Preguntas</H1>"+str(response4)
 
     return Output
 
@@ -238,10 +241,6 @@ Evaluate the coherence and accuracy of previous response to respond %s in this e
 Verificate if previous context is related to the previous response, if not, say that you do not have information about that issue 
 The format of output is a json with keys 'coherencia', 'exactitud', 'relacion_con_el_contexto' and 'comentario' .
 'coherencia', 'exactitud', 'relacion_con_el_contexto' are numeric variables with max value is 10"""%(response,ContextNodes,message)
-        
-
-
-    print(chat_engine.__dict__)
 
     chat_completion = client.chat.completions.create(
     #
@@ -293,7 +292,7 @@ The format of output is a json with keys 'coherencia', 'exactitud', 'relacion_co
     )
 
 
-    return P(message),P(response),P(chat_completion.choices[0].message.content)
+    return H6(message),P(response,cls="pico-color-pink-500"),P(chat_completion.choices[0].message.content,cls="pico-color-pink-500")
 
 @app.get("/SummarySources")
 def SummarySources():
@@ -302,7 +301,7 @@ def SummarySources():
     return Form("Este es muy caro para documentos grandes y tarda mucho",
     Select(
     *subdir,name="data"),
-    Input( name="query", placeholder="Enter a query"),
+    Input( name="query", placeholder="Dar una pregunta"),
         Button("Submit",type="submit"), hx_post="/SummaryMake",hx_swap="innerHTML",hx_target="#summaryR" )
 
 @app.post("/SummaryMake")
@@ -374,18 +373,18 @@ def home():
                     Div(Div(id="options",hx_target="this",hx_swap="outerHTML",hx_get="/listmodelactives",hx_trigger="click from:#buttonMenuuser delay:3s"),cls="col-xs-12"),
                     Div(Div(id="Infomodel"),cls="col-xs-12"),
                     #Div("Resumen",Div(id="summary",hx_target="this",hx_swap="outerHTML",hx_get="/SummarySources",hx_trigger="click from:#buttonMenuuser"),Div(id="summaryR")),
-                    Div(
+                    Div(H3("Chat para preguntarle al material de estudios "),
                         Div(
                             Form(
-                                Input(id="question", name="message", placeholder="Enter a message"),
+                                Input(id="question", name="message", placeholder="Dar una pregunta"),
                                 Button("Submit",type="submit"), hx_post="/chatData",hx_swap="afterend",hx_target="#questionR" ),
                             Div(id="questionR")
                         ,id="questions"),
                     cls="col-xs-6"),
-                    Div(
+                    Div(H3("Este genera informacion general del material, pero es intensivo en unso del api. No USAR."),
                         Div(
                             Form(
-                                Input(id="query", name="question", placeholder="Enter a query"),
+                                Input(id="query", name="question", placeholder="Dar una pregunta"),
                                 Button("Submit",type="submit"), hx_post="/queryprompt",hx_swap="innerHTML",hx_target="#queryR" ),
                             Div(id="queryR"),
                             id="query"),
@@ -394,14 +393,71 @@ def home():
                 ))
     return page
 
-# @app.post("/upload")
+@app.get("/fileup")
-# def upload(data: UploadFile = File(...),user : str = Form(...), dir: str = Form(...)):
+def fileup():
-#     filename="static/"+user+dir+data.filename
+    return Div(
+        P('Upload data Super tutor'),
+        Div(H2("Subir Archivos"),Form(
+            Input(type='file', name='file',cls="col-xs-3"),
+            Input( name='dir',placeholder="Enter a directory",cls="col-xs-2"),
+            Input( name='user',placeholder="Enter a user",cls="col-xs-2"),
+            Button('Upload', type='submit',cls="col-xs-4"),
+            hx_post="/upload",
+            hx_target="#info",
+            hx_swap="innerHTML",
+            enctype="multipart/form-data",
+        ),cls="col-xs-12"),
+        Div(H2("Crear Usuario"),Form(
+            Input( name='user',placeholder="Enter a user",cls="col-xs-7"),
+            Button('Upload', type='submit',cls="col-xs-5"),
+            hx_post="/createuser",
+            hx_target="#info",
+            hx_swap="innerHTML",
+            enctype="multipart/form-data",
+        ),cls="col-xs-12"),
+        Div(H2("Crear grupo de Archivos"),Form(
+            Input( name='dir',placeholder="Enter a directory",cls="col-xs-4"),
+            Input( name='user',placeholder="Enter a user",cls="col-xs-3"),
+            Button('Upload', type='submit',cls="col-xs-5"),
+            hx_post="/creategroup",
+            hx_target="#info",
+            hx_swap="innerHTML",
+            enctype="multipart/form-data",
+        ),cls="col-xs-12"),
+        Div(id="info")
 
-#     with open(f"{filename}", "wb") as buffer:
-#         shutil.copyfileobj(data.file, buffer)
 
-# app.mount("/static", StaticFiles(directory="static"), name="static")
+    )
+    
+
+@app.post("/upload")
+def upload(file: UploadFile,dir : str = Form(...),user : str = Form(...)):
+    filenameB="static/"+user+"/"+dir+"/"+file.filename
+    pathB="static/"+user+"/"+dir
+    if not os.path.exists(pathB):
+        os.makedirs(pathB)
+    if not os.path.exists(filenameB):
+        with open(f"{filenameB}", "wb") as buffer:
+            shutil.copyfileobj(file.file, buffer)
+    return P("Se ha subido %s"%(filenameB))
+    
+
+@app.post("/createuser")
+def createuser(user : str = Form(...)):
+    pathB="static/"+user
+    if not os.path.exists(pathB):
+        os.makedirs(pathB)
+    return P("Se ha creado %s"%(pathB))
+
+@app.post("/creategroup")
+def createuser(user : str = Form(...),dir : str = Form(...)):
+    pathB="static/"+user+"/"+dir
+    if not os.path.exists(pathB):
+        os.makedirs(pathB)
+    return P("Se ha creado %s"%(pathB))
+
+
+app.mount("/static", StaticFiles(directory="static"), name="static")
 
 
 

requirements.txt

@@ -0,0 +1,146 @@
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.9
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.0
+asgiref==3.8.1
+attrs==24.2.0
+backoff==2.2.1
+bcrypt==4.2.0
+beautifulsoup4==4.12.3
+build==1.2.2.post1
+cachetools==5.5.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.6
+chromadb==0.5.7
+click==8.1.7
+coloredlogs==15.0.1
+dataclasses-json==0.6.7
+Deprecated==1.2.14
+dirtyjson==1.0.8
+distro==1.9.0
+durationpy==0.9
+fastapi==0.115.0
+fastcore==1.7.11
+fastlite==0.0.11
+filelock==3.16.1
+flatbuffers==24.3.25
+frozenlist==1.4.1
+fsspec==2024.9.0
+google-auth==2.35.0
+googleapis-common-protos==1.65.0
+greenlet==3.1.1
+groq==0.11.0
+grpcio==1.66.2
+h11==0.14.0
+httpcore==1.0.6
+httptools==0.6.1
+httpx==0.27.2
+huggingface-hub==0.25.1
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.4.0
+importlib_resources==6.4.5
+itsdangerous==2.2.0
+jiter==0.6.1
+joblib==1.4.2
+kubernetes==31.0.0
+llama-cloud==0.1.2
+llama-index==0.11.13
+llama-index-agent-openai==0.3.4
+llama-index-cli==0.3.1
+llama-index-core==0.11.16
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-openai==0.2.5
+llama-index-indices-managed-llama-cloud==0.4.0
+llama-index-legacy==0.9.48.post3
+llama-index-llms-openai==0.2.12
+llama-index-llms-groq==0.2.0
+llama-index-multi-modal-llms-openai==0.2.2
+llama-index-program-openai==0.2.0
+llama-index-question-gen-openai==0.2.0
+llama-index-readers-file==0.2.2
+llama-index-readers-llama-parse==0.3.0
+llama-index-vector-stores-chroma==0.2.0
+llama-parse==0.5.7
+markdown-it-py==3.0.0
+marshmallow==3.22.0
+mdurl==0.1.2
+mmh3==5.0.1
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+networkx==3.3
+nltk==3.9.1
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.19.2
+openai==1.51.1
+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==2.2.3
+pillow==10.4.0
+posthog==3.7.0
+propcache==0.2.0
+protobuf==4.25.5
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pydantic==2.9.2
+pydantic_core==2.23.4
+Pygments==2.18.0
+pypdf==4.3.1
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+pysqlite3-binary==0.5.3.post1
+pysqlite3-binary==0.5.3.post1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-fasthtml==0.6.7
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.9.2
+rsa==4.9
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.35
+sqlite-minutils==3.37.0.post3
+starlette==0.38.6
+striprtf==0.0.26
+sympy==1.13.3
+tenacity==8.5.0
+tiktoken==0.8.0
+tokenizers==0.20.0
+tqdm==4.66.5
+typer==0.12.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.31.0
+uvloop==0.20.0
+watchfiles==0.24.0
+websocket-client==1.8.0
+websockets==13.1
+wrapt==1.16.0
+yarl==1.14.0
+zipp==3.20.2

run.sh

@@ -0,0 +1 @@
+docker run -it -p 7884:7884 --rm fastapi-app

static/Ricardo/PCL/dockerfile

@@ -0,0 +1,21 @@
+# Usar una imagen base de Python
+FROM python:3.11.10-bookworm
+# Establecer el directorio de trabajo en el contenedor
+WORKDIR /app
+
+# Copiar el archivo requirements.txt y otros archivos necesarios
+COPY requirements.txt ./
+
+# Instalar las dependencias de Python
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copiar todo el código de la aplicación al contenedor
+COPY . .
+
+# Expone el puerto que usará Uvicorn
+EXPOSE 7884
+
+# Especificar el comando 
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7884", "--reload"]
+