github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-06-29 08:47:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated with routes for pdf_ocr

Browse Source
This commit is contained in:
Saurab-Shrestha 2024-02-15 14:32:13 +05:45
parent a29e0f4253
commit 91ebce47d4
7 changed files with 54 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored
View File

@ -31,4 +31,6 @@ __pycache__/
*.pdf *.pdf
*.doc *.doc
*.docx *.docx
*.png

83
poetry.lock generated
View File

@ -2897,12 +2897,12 @@ nvidia-nvjitlink-cu12 = "*"
[[package]] [[package]]
name = "nvidia-nccl-cu12" name = "nvidia-nccl-cu12"
version = "2.19.3" version = "2.18.1"
description = "NVIDIA Collective Communication Library (NCCL) Runtime" description = "NVIDIA Collective Communication Library (NCCL) Runtime"
optional = false optional = false
python-versions = ">=3" python-versions = ">=3"
files = [ files = [
{file = "nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl", hash = "sha256:a9734707a2c96443331c1e48c717024aa6678a0e2a4cb66b2c364d18cee6b48d"}, {file = "nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:1a6c4acefcbebfa6de320f412bf7866de856e786e0462326ba1bac40de0b5e71"},
] ]
[[package]] [[package]]
@ -5426,36 +5426,31 @@ files = [
[[package]] [[package]]
name = "torch" name = "torch"
version = "2.2.0" version = "2.1.2"
description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration" description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
optional = false optional = false
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = [
{file = "torch-2.2.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:d366158d6503a3447e67f8c0ad1328d54e6c181d88572d688a625fac61b13a97"}, {file = "torch-2.1.2-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:3a871edd6c02dae77ad810335c0833391c1a4ce49af21ea8cf0f6a5d2096eea8"},
{file = "torch-2.2.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:707f2f80402981e9f90d0038d7d481678586251e6642a7a6ef67fc93511cb446"}, {file = "torch-2.1.2-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:bef6996c27d8f6e92ea4e13a772d89611da0e103b48790de78131e308cf73076"},
{file = "torch-2.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:15c8f0a105c66b28496092fca1520346082e734095f8eaf47b5786bac24b8a31"}, {file = "torch-2.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:0e13034fd5fb323cbbc29e56d0637a3791e50dd589616f40c79adfa36a5a35a1"},
{file = "torch-2.2.0-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:0ca4df4b728515ad009b79f5107b00bcb2c63dc202d991412b9eb3b6a4f24349"}, {file = "torch-2.1.2-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:d9b535cad0df3d13997dbe8bd68ac33e0e3ae5377639c9881948e40794a61403"},
{file = "torch-2.2.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:3d3eea2d5969b9a1c9401429ca79efc668120314d443d3463edc3289d7f003c7"}, {file = "torch-2.1.2-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:f9a55d55af02826ebfbadf4e9b682f0f27766bc33df8236b48d28d705587868f"},
{file = "torch-2.2.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:0d1c580e379c0d48f0f0a08ea28d8e373295aa254de4f9ad0631f9ed8bc04c24"}, {file = "torch-2.1.2-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:a6ebbe517097ef289cc7952783588c72de071d4b15ce0f8b285093f0916b1162"},
{file = "torch-2.2.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:9328e3c1ce628a281d2707526b4d1080eae7c4afab4f81cea75bde1f9441dc78"}, {file = "torch-2.1.2-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:8f32ce591616a30304f37a7d5ea80b69ca9e1b94bba7f308184bf616fdaea155"},
{file = "torch-2.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:03c8e660907ac1b8ee07f6d929c4e15cd95be2fb764368799cca02c725a212b8"}, {file = "torch-2.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:e0ee6cf90c8970e05760f898d58f9ac65821c37ffe8b04269ec787aa70962b69"},
{file = "torch-2.2.0-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:da0cefe7f84ece3e3b56c11c773b59d1cb2c0fd83ddf6b5f7f1fd1a987b15c3e"}, {file = "torch-2.1.2-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:76d37967c31c99548ad2c4d3f2cf191db48476f2e69b35a0937137116da356a1"},
{file = "torch-2.2.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:f81d23227034221a4a4ff8ef24cc6cec7901edd98d9e64e32822778ff01be85e"}, {file = "torch-2.1.2-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:e2d83f07b4aac983453ea5bf8f9aa9dacf2278a8d31247f5d9037f37befc60e4"},
{file = "torch-2.2.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:dcbfb2192ac41ca93c756ebe9e2af29df0a4c14ee0e7a0dd78f82c67a63d91d4"}, {file = "torch-2.1.2-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:f41fe0c7ecbf903a568c73486139a75cfab287a0f6c17ed0698fdea7a1e8641d"},
{file = "torch-2.2.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:9eeb42971619e24392c9088b5b6d387d896e267889d41d267b1fec334f5227c5"}, {file = "torch-2.1.2-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:e3225f47d50bb66f756fe9196a768055d1c26b02154eb1f770ce47a2578d3aa7"},
{file = "torch-2.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:c718b2ca69a6cac28baa36d86d8c0ec708b102cebd1ceb1b6488e404cd9be1d1"}, {file = "torch-2.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:33d59cd03cb60106857f6c26b36457793637512998666ee3ce17311f217afe2b"},
{file = "torch-2.2.0-cp312-none-macosx_10_9_x86_64.whl", hash = "sha256:f11d18fceb4f9ecb1ac680dde7c463c120ed29056225d75469c19637e9f98d12"}, {file = "torch-2.1.2-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:8e221deccd0def6c2badff6be403e0c53491805ed9915e2c029adbcdb87ab6b5"},
{file = "torch-2.2.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:ee1da852bfd4a7e674135a446d6074c2da7194c1b08549e31eae0b3138c6b4d2"}, {file = "torch-2.1.2-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:05b18594f60a911a0c4f023f38a8bda77131fba5fd741bda626e97dcf5a3dd0a"},
{file = "torch-2.2.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:0d819399819d0862268ac531cf12a501c253007df4f9e6709ede8a0148f1a7b8"}, {file = "torch-2.1.2-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:9ca96253b761e9aaf8e06fb30a66ee301aecbf15bb5a303097de1969077620b6"},
{file = "torch-2.2.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:08f53ccc38c49d839bc703ea1b20769cc8a429e0c4b20b56921a9f64949bf325"}, {file = "torch-2.1.2-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:d93ba70f67b08c2ae5598ee711cbc546a1bc8102cef938904b8c85c2089a51a0"},
{file = "torch-2.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:93bffe3779965a71dab25fc29787538c37c5d54298fd2f2369e372b6fb137d41"}, {file = "torch-2.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:255b50bc0608db177e6a3cc118961d77de7e5105f07816585fa6f191f33a9ff3"},
{file = "torch-2.2.0-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:c17ec323da778efe8dad49d8fb534381479ca37af1bfc58efdbb8607a9d263a3"}, {file = "torch-2.1.2-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:6984cd5057c0c977b3c9757254e989d3f1124f4ce9d07caa6cb637783c71d42a"},
{file = "torch-2.2.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:c02685118008834e878f676f81eab3a952b7936fa31f474ef8a5ff4b5c78b36d"}, {file = "torch-2.1.2-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:bc195d7927feabc0eb7c110e457c955ed2ab616f3c7c28439dd4188cf589699f"},
{file = "torch-2.2.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:d9f39d6f53cec240a0e3baa82cb697593340f9d4554cee6d3d6ca07925c2fac0"},
{file = "torch-2.2.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:51770c065206250dc1222ea7c0eff3f88ab317d3e931cca2aee461b85fbc2472"},
{file = "torch-2.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:008e4c6ad703de55af760c73bf937ecdd61a109f9b08f2bbb9c17e7c7017f194"},
{file = "torch-2.2.0-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:de8680472dd14e316f42ceef2a18a301461a9058cd6e99a1f1b20f78f11412f1"},
{file = "torch-2.2.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:99e1dcecb488e3fd25bcaac56e48cdb3539842904bdc8588b0b255fde03a254c"},
] ]
[package.dependencies] [package.dependencies]
@ -5472,15 +5467,15 @@ nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linu
nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
nvidia-nccl-cu12 = {version = "2.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-nccl-cu12 = {version = "2.18.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
sympy = "*" sympy = "*"
triton = {version = "2.2.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} triton = {version = "2.1.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
typing-extensions = ">=4.8.0" typing-extensions = "*"
[package.extras] [package.extras]
dynamo = ["jinja2"]
opt-einsum = ["opt-einsum (>=3.3)"] opt-einsum = ["opt-einsum (>=3.3)"]
optree = ["optree (>=0.9.1)"]
[[package]] [[package]]
name = "tqdm" name = "tqdm"
@ -5576,26 +5571,28 @@ vision = ["Pillow (>=10.0.1,<=15.0)"]
[[package]] [[package]]
name = "triton" name = "triton"
version = "2.2.0" version = "2.1.0"
description = "A language and compiler for custom Deep Learning operations" description = "A language and compiler for custom Deep Learning operations"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2294514340cfe4e8f4f9e5c66c702744c4a117d25e618bd08469d0bfed1e2e5"}, {file = "triton-2.1.0-0-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:66439923a30d5d48399b08a9eae10370f6c261a5ec864a64983bae63152d39d7"},
{file = "triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da58a152bddb62cafa9a857dd2bc1f886dbf9f9c90a2b5da82157cd2b34392b0"}, {file = "triton-2.1.0-0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:919b06453f0033ea52c13eaf7833de0e57db3178d23d4e04f9fc71c4f2c32bf8"},
{file = "triton-2.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0af58716e721460a61886668b205963dc4d1e4ac20508cc3f623aef0d70283d5"}, {file = "triton-2.1.0-0-cp37-cp37m-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ae4bb8a91de790e1866405211c4d618379781188f40d5c4c399766914e84cd94"},
{file = "triton-2.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8fe46d3ab94a8103e291bd44c741cc294b91d1d81c1a2888254cbf7ff846dab"}, {file = "triton-2.1.0-0-cp38-cp38-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:39f6fb6bdccb3e98f3152e3fbea724f1aeae7d749412bbb1fa9c441d474eba26"},
{file = "triton-2.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8ce26093e539d727e7cf6f6f0d932b1ab0574dc02567e684377630d86723ace"}, {file = "triton-2.1.0-0-cp39-cp39-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:21544e522c02005a626c8ad63d39bdff2f31d41069592919ef281e964ed26446"},
{file = "triton-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:227cc6f357c5efcb357f3867ac2a8e7ecea2298cd4606a8ba1e931d1d5a947df"}, {file = "triton-2.1.0-0-pp37-pypy37_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:143582ca31dd89cd982bd3bf53666bab1c7527d41e185f9e3d8a3051ce1b663b"},
{file = "triton-2.1.0-0-pp38-pypy38_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:82fc5aeeedf6e36be4e4530cbdcba81a09d65c18e02f52dc298696d45721f3bd"},
{file = "triton-2.1.0-0-pp39-pypy39_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:81a96d110a738ff63339fc892ded095b31bd0d205e3aace262af8400d40b6fa8"},
] ]
[package.dependencies] [package.dependencies]
filelock = "*" filelock = "*"
[package.extras] [package.extras]
build = ["cmake (>=3.20)", "lit"] build = ["cmake (>=3.18)", "lit"]
tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"] tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)"]
tutorials = ["matplotlib", "pandas", "tabulate", "torch"] tutorials = ["matplotlib", "pandas", "tabulate"]
[[package]] [[package]]
name = "typer" name = "typer"
@ -6389,4 +6386,4 @@ chroma = ["chromadb"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = ">=3.11,<3.12" python-versions = ">=3.11,<3.12"
content-hash = "acc455dd6fb59b86b5d3cc26a8d040074370f897f4694edbbe144ef4bc06e18c" content-hash = "bf8a849bc819f49c3dd293066387707e1c67d8b5cf63fcf21603cd8218858414"

2
private_gpt/components/ocr_components/TextExtraction.py
View File

@ -12,7 +12,7 @@ from transformers import TableTransformerForObjectDetection
from typing import Literal from typing import Literal
from TextExtraction import GetOCRText from private_gpt.components.ocr_components.table_ocr import GetOCRText
device = "cuda" if torch.cuda.is_available() else "cpu" device = "cuda" if torch.cuda.is_available() else "cpu"

0
private_gpt/components/ocr_components/__init__.py Normal file
View File

14
private_gpt/components/ocr_components/table_ocr_api.py
View File

@ -1,20 +1,20 @@
from fastapi import FastAPI, File, UploadFile, Response from fastapi import FastAPI, File, UploadFile, Response, APIRouter
from fastapi.responses import FileResponse from fastapi.responses import FileResponse
from pydantic import BaseModel from pydantic import BaseModel
from docx import Document from docx import Document
import os import os
import fitz import fitz
from table_ocr import ImageToTable from private_gpt.components.ocr_components.TextExtraction import ImageToTable
from TextExtraction import GetOCRText from private_gpt.components.ocr_components.table_ocr import GetOCRText
app = FastAPI() upload_dir = rf"F:\LLM\privateGPT\private_gpt\uploads"
pdf_router = APIRouter(prefix="/pdf", tags=["auth"])
@pdf_router.post("/pdf_ocr")
@app.post("/pdf_ocr")
async def get_pdf_ocr(file: UploadFile = File(...)): async def get_pdf_ocr(file: UploadFile = File(...)):
UPLOAD_DIR = os.getcwd() UPLOAD_DIR = upload_dir
try: try:
contents = await file.read() contents = await file.read()
except Exception: except Exception:

2
private_gpt/launcher.py
View File

@ -12,6 +12,7 @@ from private_gpt.server.embeddings.embeddings_router import embeddings_router
from private_gpt.server.health.health_router import health_router from private_gpt.server.health.health_router import health_router
from private_gpt.server.ingest.ingest_router import ingest_router from private_gpt.server.ingest.ingest_router import ingest_router
from private_gpt.users.api.v1.api import api_router from private_gpt.users.api.v1.api import api_router
from private_gpt.components.ocr_components.table_ocr_api import pdf_router
from private_gpt.settings.settings import Settings from private_gpt.settings.settings import Settings
from private_gpt.home import home_router from private_gpt.home import home_router
@ -34,6 +35,7 @@ def create_app(root_injector: Injector) -> FastAPI:
app.include_router(api_router) app.include_router(api_router)
app.include_router(home_router) app.include_router(home_router)
app.include_router(pdf_router)
settings = root_injector.get(Settings) settings = root_injector.get(Settings)
if settings.server.cors.enabled: if settings.server.cors.enabled:
logger.debug("Setting up CORS middleware") logger.debug("Setting up CORS middleware")

1
pyproject.toml
View File

@ -24,6 +24,7 @@ python-jose = "^3.3.0"
psycopg2-binary = "^2.9.9" psycopg2-binary = "^2.9.9"
passlib = "^1.7.4" passlib = "^1.7.4"
docx2txt = "^0.8" docx2txt = "^0.8"
torch = "2.1.2"
[tool.poetry.group.dev.dependencies] [tool.poetry.group.dev.dependencies]
black = "^22" black = "^22"