757 lines
23 KiB
Python
757 lines
23 KiB
Python
import fastapi
|
|
from fastapi import FastAPI, Request
|
|
from fastapi.responses import HTMLResponse,JSONResponse
|
|
from pydantic import BaseModel
|
|
import time
|
|
from fastapi.staticfiles import StaticFiles
|
|
from fastapi import FastAPI, Query, File, UploadFile,HTTPException
|
|
#from fastapi.middleware.cors import CORSMiddleware
|
|
from starlette.middleware.cors import CORSMiddleware
|
|
import main
|
|
import os
|
|
from databases import db
|
|
import audioread
|
|
import pandas as pd
|
|
import statistics
|
|
import hashlib
|
|
from datetime import datetime
|
|
import json
|
|
pwd = os.getcwd()
|
|
pathAud="example/audio"
|
|
pathFact="example/factura"
|
|
pathText="example/texto"
|
|
|
|
def extractConfig(nameModel="SystemData",relPath=os.path.join(pwd,"conf/experiment_config.json"),dataOut="keyantrophics"):
|
|
configPath=os.path.join(os.getcwd(),relPath)
|
|
with open(configPath, 'r', encoding='utf-8') as file:
|
|
config = json.load(file)[nameModel]
|
|
Output= config[dataOut]
|
|
return Output
|
|
mode_list=extractConfig(nameModel="SystemData",dataOut="mode_list")
|
|
|
|
|
|
app = FastAPI()
|
|
#app.mount("/statics", StaticFiles(directory="statics"), name="statics")
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
class Response(BaseModel):
|
|
"""Structure of data to querry of make post from X or article blog
|
|
"""
|
|
path: str = Query("", description="Style and sentiments of text")
|
|
model : str = Query("whisper", description="Style and sentiments of text")
|
|
class Response1(BaseModel):
|
|
path: str = Query("", description="path file")
|
|
task_prompt: str = Query("", description="task of model")
|
|
model: str = Query("", description="model")
|
|
TrustedOCR: str = Query("", description="truted OCR model")
|
|
option: str = Query("", description="OCR model option")
|
|
class Response2(BaseModel):
|
|
path: str = Query("", description="path file")
|
|
task_prompt: str = Query("", description="task of model")
|
|
system: str = Query("", description="prompt system LLM model with ocr and image claude")
|
|
content: str = Query("%s", description="prompt content LLM model with ocr")
|
|
max_tokens: int = Query(1024, description="maxtoken LLM OCR model")
|
|
model: str = Query("Claude-sonnet", description="model")
|
|
prompt: str = Query("", description="prompt in claude with image")
|
|
TrustedLLmjson: str = Query("", description="truted OCR model")
|
|
|
|
class Response3(BaseModel):
|
|
"""Structure of data to querry of make post from X or article blog
|
|
"""
|
|
path: str = Query("", description="Style and sentiments of text")
|
|
Trusted: str = Query("", description="Style and sentiments of text")
|
|
mode : str = Query("whisper", description="Style and sentiments of text")
|
|
|
|
#Funcionales
|
|
@app.get("/addTrusted")
|
|
@app.post("/addTrusted")
|
|
def addTrusted(response:Response3):
|
|
"""Api to add information of Trusted data
|
|
|
|
Args:
|
|
response (Response3): 3 params:
|
|
path : path of archive on system if is a file OR text if is text.
|
|
Trusted : information Trusted or better information in a process.
|
|
mode: llm_compra,llm_factura,llm_generaciontexto,llm_rag,ocr,voice,
|
|
|
|
Returns:
|
|
_type_: _description_
|
|
"""
|
|
path=response.path
|
|
Trusted=response.Trusted
|
|
mode=response.mode
|
|
last_modified=datetime.now()
|
|
if mode not in mode_list.keys():
|
|
return JSONResponse(
|
|
status_code=404,
|
|
content={"content": "mode no found" }
|
|
)
|
|
if mode == "llm_factura" or mode == "ocr" or mode == "voice":
|
|
if not os.path.isfile(path):
|
|
return JSONResponse(
|
|
status_code=404,
|
|
content={"content": "file no found" }
|
|
)
|
|
if mode_list[mode]=="texto":
|
|
hash1 = hashlib.sha256(path.encode()).hexdigest()+".txt"
|
|
f = open("example/texto/"+hash1, "w")
|
|
f.write(path)
|
|
f.close()
|
|
path=pwd+"/"+pathText+hash1
|
|
length=len(Trusted)
|
|
size=0
|
|
duration=0
|
|
elif mode_list[mode]=="factura":
|
|
file_stats = os.stat(path)
|
|
size=file_stats.st_size / (1024 * 1024)
|
|
length=0
|
|
duration=0
|
|
elif mode_list[mode]=="audio":
|
|
with audioread.audio_open(path) as f:
|
|
duration = f.duration
|
|
length=0
|
|
size=0
|
|
|
|
if db((db.trusted.path == path)&(db.trusted.mode == mode)).count()==0:
|
|
db.trusted.insert(path=path,trusted=Trusted,mode=mode,size=size,duration=duration,last_modified=last_modified,length=length )
|
|
db.commit()
|
|
return "Add %s in mode %s"%(path,mode)
|
|
else:
|
|
item=db((db.trusted.path == path)&(db.trusted.mode == mode)).select().last()
|
|
modification_count=item.modification_count + 1
|
|
db((db.trusted.path == path)&(db.trusted.mode == mode)).update(trusted=Trusted,size=size,duration =duration,length=length,last_modified=last_modified,modification_count= modification_count)
|
|
db.commit()
|
|
return "Update %s in mode %s"%(path,mode)
|
|
|
|
@app.get("/EvalVoice")
|
|
@app.post("/EvalVoice")
|
|
def EvalVoice(response:Response):
|
|
path=response.path
|
|
model=response.model
|
|
if db((db.trusted.path == path ) & ( db.trusted.mode == "voice")).count()==0:
|
|
return JSONResponse(
|
|
status_code=404,
|
|
content={"content": "Trusted no found" }
|
|
)
|
|
|
|
Trusted=db((db.trusted.path == path ) & ( db.trusted.mode == "voice")).select().last().trusted
|
|
print(Trusted)
|
|
if model=="whisper":
|
|
Sal=main.EvalWhisper(path,Trusted)
|
|
else:
|
|
Sal=main.EvalVosk(path,Trusted)
|
|
Sal["last_modified"]=datetime.now()
|
|
if db(db.analitic_voice.path == Sal["path"] and db.analitic_voice.model == Sal["model"]).count()==0:
|
|
db.analitic_voice.insert(**Sal)
|
|
db.commit()
|
|
else:
|
|
db(db.analitic_voice.path == Sal["path"] and db.analitic_voice.model == Sal["model"]).update(similarity= Sal["similarity"],similaritypartial= Sal["similaritypartial"],last_modified=Sal["last_modified"])
|
|
db.commit()
|
|
return Sal
|
|
|
|
|
|
|
|
def list2tablehtml(listdata,model):
|
|
html="""<h2>Table of {0}</h2>
|
|
<table style="width:100%">
|
|
<tr>
|
|
<th>path</th>
|
|
<th>time</th>
|
|
<th>similarity</th>
|
|
<th>similaritypartial</th>
|
|
</tr>""".format(model)
|
|
|
|
for i in listdata:
|
|
html=html+""" <tr>
|
|
<td>%s</td>
|
|
<td>%s</td>
|
|
<td>%s</td>
|
|
<td>%s</td>
|
|
</tr>
|
|
"""%(i["path"],i["time"],i["similarity"],i["similaritypartial"])
|
|
html=html+"""</table>
|
|
"""
|
|
return html
|
|
|
|
|
|
def tableVoice(model):
|
|
rows = db(db.analitic_voice.model==model).select()
|
|
rows_list = rows.as_list()
|
|
data=pd.DataFrame(rows_list)
|
|
durationL=list()
|
|
for i in rows_list:
|
|
durationL.append(db(db.trusted.path == i["path"] ).select().last().duration)
|
|
duration=statistics.mean(durationL)
|
|
time=pd.pivot_table(data,values=['time','similarity', 'similaritypartial'],index="model")['time'].values[0]
|
|
similarity=pd.pivot_table(data,values=['time','similarity', 'similaritypartial'],index="model")['similarity'].values[0]
|
|
similaritypartial=pd.pivot_table(data,values=['time','similarity', 'similaritypartial'],index="model")['similaritypartial'].values[0]
|
|
efectivetime=time/duration
|
|
card="""<div class="flip-card">
|
|
<div class="flip-card-inner">
|
|
<div class="flip-card-front">
|
|
<p style="width:300px;height:300px;">{0} </p>
|
|
</div>
|
|
<div class="flip-card-back">
|
|
<h1>time of process (sg)</h1>
|
|
<p>{1}</p>
|
|
<h1>similarity</h1>
|
|
<p>{2}</p>
|
|
<h1>similaritypartial</h1>
|
|
<p>{3}</p>
|
|
<h1>time of audio(sg)</h1>
|
|
<p>{4}</p>
|
|
<h1>time in process</h1>
|
|
<p>{5}</p>
|
|
</div>
|
|
</div>
|
|
</div>""".format(model,time,similarity,similaritypartial,duration,efectivetime)
|
|
return {"duration":duration,"time":time,"similarity":similarity,"similaritypartial":similaritypartial,"card":card,"data":list2tablehtml(rows_list,model)}
|
|
|
|
|
|
@app.get("/getmetricsvoice")
|
|
def getMetricsVoice():
|
|
pass
|
|
models=list()
|
|
for row in db().select(db.analitic_voice.model, distinct=True):
|
|
models.append(row.model)
|
|
cards=""
|
|
dataAll=""
|
|
for model in models:
|
|
|
|
Sal=tableVoice(model)
|
|
cards=cards+Sal["card"]
|
|
dataAll=dataAll+Sal["data"]
|
|
|
|
|
|
htmlhead="""<!DOCTYPE html>
|
|
<html lang="es">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Evaluacion de modelos voice2txt</title>
|
|
<style>
|
|
. container{
|
|
|
|
display:flex;
|
|
|
|
}
|
|
/* The flip card container - set the width and height to whatever you want. We have added the border property to demonstrate that the flip itself goes out of the box on hover (remove perspective if you don't want the 3D effect */
|
|
.flip-card {
|
|
background-color: transparent;
|
|
width: 500px;
|
|
height: 500px;
|
|
border: 1px solid #f1f1f1;
|
|
perspective: 1000px; /* Remove this if you don't want the 3D effect */
|
|
}
|
|
|
|
/* This container is needed to position the front and back side */
|
|
.flip-card-inner {
|
|
position: relative;
|
|
width: 100%;
|
|
height: 100%;
|
|
text-align: center;
|
|
transition: transform 0.8s;
|
|
transform-style: preserve-3d;
|
|
}
|
|
|
|
/* Do an horizontal flip when you move the mouse over the flip box container */
|
|
.flip-card:hover .flip-card-inner {
|
|
transform: rotateY(180deg);
|
|
}
|
|
|
|
/* Position the front and back side */
|
|
.flip-card-front, .flip-card-back {
|
|
position: absolute;
|
|
width: 100%;
|
|
height: 100%;
|
|
-webkit-backface-visibility: hidden; /* Safari */
|
|
backface-visibility: hidden;
|
|
}
|
|
|
|
/* Style the front side (fallback if image is missing) */
|
|
.flip-card-front {
|
|
background-color: #bbb;
|
|
color: black;
|
|
}
|
|
|
|
/* Style the back side */
|
|
.flip-card-back {
|
|
background-color: dodgerblue;
|
|
color: white;
|
|
transform: rotateY(180deg);
|
|
}
|
|
</style>
|
|
</head>"""
|
|
|
|
htmlbody="""<body>
|
|
<h1>Estadisticas modelos de voice</h1>
|
|
<div class=”container”>
|
|
{0}
|
|
</div>
|
|
{1}
|
|
</body>
|
|
</html>
|
|
""".format(cards,dataAll)
|
|
html=htmlhead+htmlbody
|
|
return HTMLResponse(content=html, status_code=200)
|
|
|
|
|
|
|
|
@app.get("/EvalFact")
|
|
@app.post("/EvalFact")
|
|
def EvalFact(response:Response1):
|
|
path=response.path
|
|
task_prompt=response.task_prompt
|
|
option=response.model
|
|
TrustedOCR=response.TrustedOCR
|
|
Trusted=TrustedOCR
|
|
if task_prompt=="":
|
|
if Trusted=="":
|
|
row=db(db.trusted.path == path and db.trusted.mode == "OCR").select().first()
|
|
try:
|
|
Trusted=row.trusted
|
|
except:
|
|
pass
|
|
Sal=main.EvalFacturas(path,task_prompt,TrustedOCR,option)
|
|
Sal["path"]=path
|
|
if db(db.analitic_ocr.path == Sal["path"] and db.analitic_ocr.model == Sal["model"]).count()==0:
|
|
db.analitic_ocr.insert(**Sal)
|
|
db.commit()
|
|
else:
|
|
db(db.analitic_ocr.path == Sal["path"] and db.analitic_ocr.model == Sal["model"]).update(similarity= Sal["similarity"],similaritypartial= Sal["similaritypartial"],jsonok=Sal["jsonok"])
|
|
db.commit()
|
|
|
|
|
|
return Sal
|
|
|
|
@app.get("/EvalLLMFact")
|
|
@app.post("/EvalLLMFact")
|
|
def EvalLLMFact(response:Response2):
|
|
path=response.path
|
|
task_prompt=response.task_prompt
|
|
system=response.system
|
|
content=response.content
|
|
max_tokens=response.max_tokens
|
|
model=response.model
|
|
prompt=response.prompt
|
|
TrustedLLmjson=response.TrustedLLmjson
|
|
|
|
Sal=main.EvalllmFacturas(path,task_prompt,system,content,max_tokens,model,prompt,TrustedLLmjson)
|
|
return Sal
|
|
|
|
@app.get("/evalvoicehtml")
|
|
def EvalVoicehtml():
|
|
dir_list = os.listdir(pathAud)
|
|
Sal=""
|
|
t=1
|
|
for i in dir_list:
|
|
|
|
temp="""<option value="%s">Opción %s, %s</option>
|
|
"""%(str(pwd+"/"+pathAud+"/"+i),str(t),str(i))
|
|
Sal=Sal+temp
|
|
t=t+1
|
|
|
|
|
|
html="""<!DOCTYPE html>
|
|
<html lang="es">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Evaluacion de modelos voice2txt</title>
|
|
<style>
|
|
body {
|
|
font-family: Arial, sans-serif;
|
|
margin: 20px;
|
|
}
|
|
input, button {
|
|
margin: 10px 0;
|
|
padding: 5px;
|
|
}
|
|
#respuesta {
|
|
margin-top: 20px;
|
|
padding: 10px;
|
|
border: 1px solid #ccc;
|
|
background-color: #f9f9f9;
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<h1>Petición POST a API</h1>
|
|
|
|
<select id="texto1">
|
|
%s
|
|
</select>
|
|
|
|
<br>
|
|
<select id="texto2">
|
|
<option value="whisper">whisper</option>
|
|
<option value="vosk">vosk</option>
|
|
</select>
|
|
<br>
|
|
<button onclick="enviarPeticion()">Enviar petición</button>
|
|
<div id="respuesta"></div>
|
|
|
|
<script>
|
|
function enviarPeticion() {
|
|
const texto1 = document.getElementById('texto1').value;
|
|
const texto2 = document.getElementById('texto2').value;
|
|
const datos = {
|
|
path: texto1,
|
|
model: texto2
|
|
};
|
|
|
|
fetch('/EvalVoice', {
|
|
method: 'POST',
|
|
headers: {
|
|
'Content-Type': 'application/json'
|
|
},
|
|
body: JSON.stringify(datos)
|
|
})
|
|
.then(response => response.json())
|
|
.then(data => {
|
|
document.getElementById('respuesta').innerHTML = JSON.stringify(data, null, 2);
|
|
})
|
|
.catch(error => {
|
|
document.getElementById('respuesta').innerHTML = 'Error: ' + error;
|
|
});
|
|
}
|
|
</script>
|
|
</body>
|
|
</html>
|
|
"""%(Sal)
|
|
return HTMLResponse(content=html, status_code=200)
|
|
|
|
|
|
@app.get("/evalocrfactura")
|
|
def EvalOCRFactura():
|
|
dir_list = os.listdir(pathFact)
|
|
Sal=""
|
|
t=1
|
|
for i in dir_list:
|
|
temp="""<option value="%s">Opción %s, %s</option>
|
|
"""%(str(pwd+"/"+pathFact+"/"+i),str(t),str(i))
|
|
Sal=Sal+temp
|
|
t=t+1
|
|
html="""<!DOCTYPE html>
|
|
<html lang="es">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Evaluacion de modelos OCR</title>
|
|
<style>
|
|
body {
|
|
font-family: Arial, sans-serif;
|
|
margin: 20px;
|
|
}
|
|
input, button {
|
|
margin: 10px 0;
|
|
padding: 5px;
|
|
}
|
|
#respuesta {
|
|
margin-top: 20px;
|
|
padding: 10px;
|
|
border: 1px solid #ccc;
|
|
background-color: #f9f9f9;
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<h1>Petición POST a API</h1>
|
|
<select id="texto1">
|
|
%s
|
|
</select>
|
|
<br>
|
|
|
|
<select id="texto2">
|
|
<option value="More Detailed Caption">More Detailed Caption</option>
|
|
<option value="OCR">OCR</option>
|
|
<option value="parsed">parsed</option>
|
|
<option value="scan">scan</option>
|
|
</select>
|
|
<br>
|
|
<input type="text" id="texto3" placeholder="TrustedOCR">
|
|
<br>
|
|
<input type="text" id="texto4" placeholder="option">
|
|
<br>
|
|
<button onclick="enviarPeticion()">Enviar petición</button>
|
|
<div id="respuesta"></div>
|
|
|
|
<script>
|
|
function enviarPeticion() {
|
|
const texto1 = document.getElementById('texto1').value;
|
|
const texto2 = document.getElementById('texto2').value;
|
|
const texto3 = document.getElementById('texto3').value;
|
|
const texto4 = document.getElementById('texto4').value;
|
|
const datos = {
|
|
path: texto1,
|
|
task_prompt: texto2,
|
|
TrustedOCR: texto3,
|
|
option: texto4
|
|
};
|
|
|
|
fetch('/EvalFact', {
|
|
method: 'POST',
|
|
headers: {
|
|
'Content-Type': 'application/json'
|
|
},
|
|
body: JSON.stringify(datos)
|
|
})
|
|
.then(response => response.json())
|
|
.then(data => {
|
|
document.getElementById('respuesta').innerHTML = JSON.stringify(data, null, 2);
|
|
})
|
|
.catch(error => {
|
|
document.getElementById('respuesta').innerHTML = 'Error: ' + error;
|
|
});
|
|
}
|
|
</script>
|
|
</body>
|
|
</html>
|
|
"""%(Sal)
|
|
return HTMLResponse(content=html, status_code=200)
|
|
|
|
def list2tablehtmlOCR(listdata,model):
|
|
html="""<h2>Table of {0}</h2>
|
|
<table style="width:100%">
|
|
<tr>
|
|
<th>path</th>
|
|
<th>time</th>
|
|
<th>similarity</th>
|
|
<th>similaritypartial</th>
|
|
</tr>""".format(model)
|
|
|
|
for i in listdata:
|
|
html=html+""" <tr>
|
|
<td>%s</td>
|
|
<td>%s</td>
|
|
<td>%s</td>
|
|
<td>%s</td>
|
|
</tr>
|
|
"""%(i["path"],i["time"],i["similarity"],i["similaritypartial"])
|
|
html=html+"""</table>
|
|
"""
|
|
return html
|
|
|
|
|
|
def tableOCR(model):
|
|
rows = db(db.analitic_ocr.model==model).select()
|
|
rows_list = rows.as_list()
|
|
data=pd.DataFrame(rows_list)
|
|
time=pd.pivot_table(data,values=['time','similarity', 'similaritypartial'],index="model")['time'].values[0]
|
|
similarity=pd.pivot_table(data,values=['time','similarity', 'similaritypartial'],index="model")['similarity'].values[0]
|
|
similaritypartial=pd.pivot_table(data,values=['time','similarity', 'similaritypartial'],index="model")['similaritypartial'].values[0]
|
|
card="""<div class="flip-card">
|
|
<div class="flip-card-inner">
|
|
<div class="flip-card-front">
|
|
<p style="width:300px;height:300px;">{0} </p>
|
|
</div>
|
|
<div class="flip-card-back">
|
|
<h1>time of process (sg)</h1>
|
|
<p>{1}</p>
|
|
<h1>similarity</h1>
|
|
<p>{2}</p>
|
|
<h1>similaritypartial</h1>
|
|
<p>{3}</p>
|
|
</div>
|
|
</div>
|
|
</div>""".format(model,time,similarity,similaritypartial)
|
|
return {"time":time,"similarity":similarity,"similaritypartial":similaritypartial,"card":card,"data":list2tablehtmlOCR(rows_list,model)}
|
|
|
|
|
|
|
|
@app.get("/getmetricsocr")
|
|
def getMetricsOCR():
|
|
models=list()
|
|
for row in db().select(db.analitic_ocr.model, distinct=True):
|
|
models.append(row.model)
|
|
cards=""
|
|
dataAll=""
|
|
for model in models:
|
|
Sal=tableOCR(model)
|
|
cards=cards+Sal["card"]
|
|
dataAll=dataAll+Sal["data"]
|
|
htmlhead="""<!DOCTYPE html>
|
|
<html lang="es">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Evaluacion de modelos voice2txt</title>
|
|
<style>
|
|
. container{
|
|
|
|
display:flex;
|
|
|
|
}
|
|
/* The flip card container - set the width and height to whatever you want. We have added the border property to demonstrate that the flip itself goes out of the box on hover (remove perspective if you don't want the 3D effect */
|
|
.flip-card {
|
|
background-color: transparent;
|
|
width: 500px;
|
|
height: 500px;
|
|
border: 1px solid #f1f1f1;
|
|
perspective: 1000px; /* Remove this if you don't want the 3D effect */
|
|
}
|
|
|
|
/* This container is needed to position the front and back side */
|
|
.flip-card-inner {
|
|
position: relative;
|
|
width: 100%;
|
|
height: 100%;
|
|
text-align: center;
|
|
transition: transform 0.8s;
|
|
transform-style: preserve-3d;
|
|
}
|
|
|
|
/* Do an horizontal flip when you move the mouse over the flip box container */
|
|
.flip-card:hover .flip-card-inner {
|
|
transform: rotateY(180deg);
|
|
}
|
|
|
|
/* Position the front and back side */
|
|
.flip-card-front, .flip-card-back {
|
|
position: absolute;
|
|
width: 100%;
|
|
height: 100%;
|
|
-webkit-backface-visibility: hidden; /* Safari */
|
|
backface-visibility: hidden;
|
|
}
|
|
|
|
/* Style the front side (fallback if image is missing) */
|
|
.flip-card-front {
|
|
background-color: #bbb;
|
|
color: black;
|
|
}
|
|
|
|
/* Style the back side */
|
|
.flip-card-back {
|
|
background-color: dodgerblue;
|
|
color: white;
|
|
transform: rotateY(180deg);
|
|
}
|
|
</style>
|
|
</head>"""
|
|
|
|
htmlbody="""<body>
|
|
<h1>Estadisticas modelos de OCR</h1>
|
|
<div class=”container”>
|
|
{0}
|
|
</div>
|
|
{1}
|
|
</body>
|
|
</html>
|
|
""".format(cards,dataAll)
|
|
html=htmlhead+htmlbody
|
|
return HTMLResponse(content=html, status_code=200)
|
|
|
|
|
|
|
|
@app.get("/evalllmfacturas")
|
|
def EvalllmFacturas():
|
|
dir_list = os.listdir(pathFact)
|
|
Sal=""
|
|
t=1
|
|
for i in dir_list:
|
|
temp="""<option value="%s">Opción %s, %s</option>
|
|
"""%(str(pwd+"/"+pathFact+"/"+i),str(t),str(i))
|
|
Sal=Sal+temp
|
|
t=t+1
|
|
html="""<!DOCTYPE html>
|
|
<html lang="es">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Evaluacion modelos LLM</title>
|
|
<style>
|
|
body {
|
|
font-family: Arial, sans-serif;
|
|
margin: 20px;
|
|
}
|
|
input, button {
|
|
margin: 10px 0;
|
|
padding: 5px;
|
|
}
|
|
#respuesta {
|
|
margin-top: 20px;
|
|
padding: 10px;
|
|
border: 1px solid #ccc;
|
|
background-color: #f9f9f9;
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<h1>Petición POST a API</h1>
|
|
<select id="texto1">
|
|
%s
|
|
</select>
|
|
<br>
|
|
|
|
<select id="texto2">
|
|
<option value="">N.A.</option>
|
|
<option value="More Detailed Caption">More Detailed Caption</option>
|
|
<option value="OCR">OCR</option>
|
|
<option value="parsed">parsed</option>
|
|
<option value="scan">scan</option>
|
|
</select>
|
|
<br>
|
|
<input type="text" id="texto3" placeholder="system" value="Eres un chatbot amable">
|
|
<br>
|
|
<input type="text" id="texto4" placeholder="content" value="%s">
|
|
<br>
|
|
<input type="number" id="texto5" placeholder="max_tokens" value=1024>
|
|
<br>
|
|
<input type="text" id="texto6" placeholder="model" value="Claude-sonnet">
|
|
<br>
|
|
<input type="text" id="texto7" placeholder="prompt" value="Analiza la factura">
|
|
<br>
|
|
<input type="text" id="texto8" placeholder="TrustedLLmjson" value="{'A':''}">
|
|
<br>
|
|
<button onclick="enviarPeticion()">Enviar petición</button>
|
|
<div id="respuesta"></div>
|
|
|
|
<script>
|
|
function enviarPeticion() {
|
|
const texto1 = document.getElementById('texto1').value;
|
|
const texto2 = document.getElementById('texto2').value;
|
|
const texto3 = document.getElementById('texto3').value;
|
|
const texto4 = document.getElementById('texto4').value;
|
|
const texto5 = document.getElementById('texto5').value;
|
|
const texto6 = document.getElementById('texto6').value;
|
|
const texto7 = document.getElementById('texto7').value;
|
|
const texto8 = document.getElementById('texto8').value;
|
|
|
|
const datos = {
|
|
path: texto1,
|
|
task_prompt: texto2,
|
|
system: texto3,
|
|
content:texto4,
|
|
max_tokens:texto5,
|
|
model:texto6,
|
|
prompt:texto7,
|
|
TrustedLLmjson:texto8,
|
|
};
|
|
|
|
fetch('/EvalLLMFact', {
|
|
method: 'POST',
|
|
headers: {
|
|
'Content-Type': 'application/json'
|
|
},
|
|
body: JSON.stringify(datos)
|
|
})
|
|
.then(response => response.json())
|
|
.then(data => {
|
|
document.getElementById('respuesta').innerHTML = JSON.stringify(data, null, 2);
|
|
})
|
|
.catch(error => {
|
|
document.getElementById('respuesta').innerHTML = 'Error: ' + error;
|
|
});
|
|
}
|
|
</script>
|
|
</body>
|
|
</html>
|
|
"""%(Sal,"%s")
|
|
return HTMLResponse(content=html, status_code=200) |