zylon-ai · zhygallo · Aug 7, 2024 · Aug 10, 2024 · Aug 12, 2024 · Sep 5, 2024
diff --git a/.docker/router.yml b/.docker/router.yml
@@ -13,4 +13,4 @@ http:
   routers:
     ollama-router:
       rule: "PathPrefix(`/`)"
-      service: ollama
+      service: ollama
diff --git a/.dockerignore b/.dockerignore
@@ -9,4 +9,4 @@ local_data
 terraform
 tests
 Dockerfile
-Dockerfile.*
+Dockerfile.*
diff --git a/.github/pull_request_template.md b/.github/pull_request_template.md
@@ -34,4 +34,4 @@ Please describe the tests that you ran to verify your changes. Provide instructi
 - [ ] I have added tests that prove my fix is effective or that my feature works
 - [ ] New and existing unit tests pass locally with my changes
 - [ ] Any dependent changes have been merged and published in downstream modules
-- [ ] I ran `make check; make test` to ensure mypy and tests pass
+- [ ] I ran `make check; make test` to ensure mypy and tests pass
diff --git a/.github/workflows/actions/install_dependencies/action.yml b/.github/workflows/actions/install_dependencies/action.yml
@@ -27,4 +27,3 @@ runs:
     - name: Install Dependencies
       run: poetry install --extras "ui vector-stores-qdrant" --no-root
       shell: bash
-
diff --git a/.github/workflows/fern-check.yml b/.github/workflows/fern-check.yml
@@ -6,7 +6,7 @@ on:
       - main
     paths:
       - "fern/**"
-      
+
 jobs:
   fern-check:
     runs-on: ubuntu-latest
@@ -18,4 +18,4 @@ jobs:
         run:  npm install -g fern-api
 
       - name: Check Fern API is valid
-        run: fern check
+        run: fern check
diff --git a/.github/workflows/generate-release.yml b/.github/workflows/generate-release.yml
@@ -80,4 +80,4 @@ jobs:
 
       - name: Version output
         id: version
-        run: echo "version=${{ steps.meta.outputs.version }}" >> "$GITHUB_OUTPUT"
+        run: echo "version=${{ steps.meta.outputs.version }}" >> "$GITHUB_OUTPUT"
diff --git a/.github/workflows/publish-docs.yml b/.github/workflows/publish-docs.yml
@@ -1,8 +1,8 @@
 name: publish docs
 
-on: 
-  push: 
-    branches: 
+on:
+  push:
+    branches:
       - main
     paths:
       - "fern/**"

diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
@@ -16,4 +16,4 @@ jobs:
       - uses: google-github-actions/release-please-action@v3
         with:
           release-type: simple
-          version-file: version.txt
+          version-file: version.txt
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -40,4 +40,4 @@ repos:
     pass_filenames: false
     language: system
     types: [python]
-    stages: [push]
+    stages: [push]
diff --git a/Dockerfile.llamacpp-cpu b/Dockerfile.llamacpp-cpu
@@ -59,4 +59,4 @@ COPY --chown=worker *.yaml ./
 COPY --chown=worker scripts/ scripts
 
 USER worker
-ENTRYPOINT python -m private_gpt
+ENTRYPOINT python -m private_gpt
diff --git a/Makefile b/Makefile
@@ -39,7 +39,7 @@ dev-windows:
 	(set PGPT_PROFILES=local & poetry run python -m uvicorn private_gpt.main:app --reload --port 8001)
 
 dev:
-	PYTHONUNBUFFERED=1 PGPT_PROFILES=local poetry run python -m uvicorn private_gpt.main:app --reload --port 8001
+	PYTHONUNBUFFERED=1 PGPT_PROFILES=huglama poetry run python -m uvicorn private_gpt.main:app --reload --port 8001
 
 ########################################################################################################################
 # Misc

diff --git a/README.md b/README.md
@@ -110,10 +110,10 @@ typing checks, just run `make check` before committing to make sure your code is
 Remember to test your code! You'll find a tests folder with helpers, and you can run
 tests using `make test` command.
 
-Don't know what to contribute? Here is the public 
-[Project Board](https://github.com/users/imartinez/projects/3) with several ideas. 
+Don't know what to contribute? Here is the public
+[Project Board](https://github.com/users/imartinez/projects/3) with several ideas.
 
-Head over to Discord 
+Head over to Discord
 #contributors channel and ask for write permissions on that GitHub project.
 
 ## 💬 Community
@@ -122,7 +122,7 @@ Join the conversation around PrivateGPT on our:
 - [Discord](https://discord.gg/bK6mRVpErU)
 
 ## 📖 Citation
-If you use PrivateGPT in a paper, check out the [Citation file](CITATION.cff) for the correct citation.  
+If you use PrivateGPT in a paper, check out the [Citation file](CITATION.cff) for the correct citation.
 You can also use the "Cite this repository" button in this repo to get the citation in different formats.
 
 Here are a couple of examples:
@@ -150,7 +150,7 @@ PrivateGPT is actively supported by the teams behind:
 * [Fern](https://buildwithfern.com/), providing Documentation and SDKs
 * [LlamaIndex](https://www.llamaindex.ai/), providing the base RAG framework and abstractions
 
-This project has been strongly influenced and supported by other amazing projects like 
+This project has been strongly influenced and supported by other amazing projects like
 [LangChain](https://github.com/hwchase17/langchain),
 [GPT4All](https://github.com/nomic-ai/gpt4all),
 [LlamaCpp](https://github.com/ggerganov/llama.cpp),

diff --git a/docker-compose.yaml b/docker-compose.yaml
@@ -99,4 +99,4 @@ services:
               count: 1
               capabilities: [gpu]
     profiles:
-      - ollama-cuda
+      - ollama-cuda
diff --git a/experiments/llama_index.ipynb b/experiments/llama_index.ipynb
@@ -0,0 +1,268 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2024-09-05T14:03:18.404518Z",
+     "start_time": "2024-09-05T14:03:18.401535Z"
+    }
+   },
+   "source": "# Read PDF",
+   "outputs": [],
+   "execution_count": 33
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-05T14:39:16.282184Z",
+     "start_time": "2024-09-05T14:39:16.279186Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "import pdf2image\n",
+    "import pytesseract\n",
+    "from pytesseract import Output, TesseractError"
+   ],
+   "id": "ad1ffea2dcb7dcaf",
+   "outputs": [],
+   "execution_count": 74
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-05T14:39:16.648563Z",
+     "start_time": "2024-09-05T14:39:16.646494Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "file = \"../local_data/input_raw/test/26223.pdf\"",
+   "id": "f38556f4ef09d669",
+   "outputs": [],
+   "execution_count": 75
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-05T14:39:23.492339Z",
+     "start_time": "2024-09-05T14:39:18.280277Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "images = pdf2image.convert_from_path(file)",
+   "id": "67286a6f741debb0",
+   "outputs": [],
+   "execution_count": 76
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-05T14:39:38.005863Z",
+     "start_time": "2024-09-05T14:39:36.119195Z"
+    }
+   },
+   "cell_type": "code",
+   "source": [
+    "pil_im = images[5] # assuming that we're interested in the first page only\n",
+    "\n",
+    "ocr_dict = pytesseract.image_to_string(pil_im, lang=\"rus\")"
+   ],
+   "id": "ec339f7da13fc37f",
+   "outputs": [],
+   "execution_count": 79
+  },
+  {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-09-05T14:39:49.348914Z",
+     "start_time": "2024-09-05T14:39:49.344588Z"
+    }
+   },
+   "cell_type": "code",
+   "source": "print(ocr_dict)",
+   "id": "df86f1ed6f5f1b6e",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "096 отдельный батальон материального обеспечения\n",
+      "\n",
+      "1099 мотострелковый полк\n",
+      "\n",
+      "| береговая ракетно-артиллерийская бригада\n",
+      "\n",
+      "военная автомобильная инспекция\n",
+      "\n",
+      "гвардейская отдельная десантно-штурмовая бригада\n",
+      "гвардейская отдельная инженерная бригада\n",
+      "отдельная вертолетная эскадрилья\n",
+      "отдельная танковая бригада\n",
+      "отдельный медицинский батальон\n",
+      "отдельный танковый полк\n",
+      "\n",
+      "полк радиационной, химической и биологической защиты\n",
+      "\n",
+      "смешанный авиационный полк\n",
+      "средняя общеобразовательная школа\n",
+      "\n",
+      "центральный узел контроля безопасности связи\n",
+      "\n",
+      "11 экипаж большой подводной лодки\n",
+      "\n",
+      "110 военная автомобильная инспекция\n",
+      "\n",
+      "110 военное представительство Министерства обороны Российской Федерации\n",
+      "\n",
+      "110 отдельная мотострелковая бригада\n",
+      "110 отдельный стрелковый полк\n",
+      "\n",
+      "1101 отдел государственного технического надзора\n",
+      "\n",
+      "1102 мотострелковый полк\n",
+      "1104 мотострелковый полк\n",
+      "\n",
+      "144\n",
+      "\n",
+      "1105 мотострелковый полк\n",
+      "\n",
+      "109 отдельный оптико-электронный узел\n",
+      "\n",
+      "11 военная автомобильная инспекция\n",
+      "\n",
+      "П главный государственный центр судеоно-медицинских и криминалистических экспертиз Министерства\n",
+      "\n",
+      "|| отдельный стрелковый полк\n",
+      "\n",
+      "11 центральная база резерва танков\n",
+      "\n",
+      "110 объединенное управление эксплуатации специальных объектов\n",
+      "\n",
+      "117 зенитный ракетный полк\n",
+      "\n",
+      "152|1118 военное представительство Министерства обороны Российской Федерации\n",
+      "153|1118 отдельный радиолокационный узел\n",
+      "\n",
+      "154|112 авиационный полигон\n",
+      "\n",
+      "155112 гвардейская ракетная бригада\n",
+      "\n",
+      "156| 112 отдельный вертолетный полк\n",
+      "\n",
+      "157|112 отдельный стрелковый полк\n",
+      "\n",
+      "158|1122 отдельный батальон материального обеспечения\n",
+      "159|1124 отдельный батальон материального обеспечения\n",
+      "160|1127 ремонтный завод ракетно-артиллерийского вооружения\n",
+      "161|113 военная автомобильная инспекция\n",
+      "\n",
+      "162|1139 отдельный батальон материального обеспечения\n",
+      "163|1139 отдельный измерительный пункт\n",
+      "\n",
+      "164| 114 бригада\n",
+      "\n",
+      "165| 114 военная автомобильная инспекция\n",
+      "\n",
+      "166|114 гвардейская отдельная мотострелковая бригада\n",
+      "\n",
+      "114 гвардейский мотострелковый полк\n",
+      "\n",
+      "168\n",
+      "\n",
+      "114 отделение территориальное\n",
+      "\n",
+      "169\n",
+      "\n",
+      "40 гвардейский артиллерийский полк\n",
+      "\n",
+      "170\n",
+      "\n",
+      "41 гвардейский артиллерийский полк\n",
+      "\n",
+      "171\n",
+      "\n",
+      "1142 военное представительство Министерства обороны Российской Федерации\n",
+      "\n",
+      "172\n",
+      "\n",
+      "1143 отдельный зенитный ракетный дивизион\n",
+      "\n",
+      "173\n",
+      "\n",
+      "115 военная автомобильная инспекция\n",
+      "\n",
+      "174\n",
+      "\n",
+      "5 государственный специальный химический арсенал\n",
+      "\n",
+      "175\n",
+      "\n",
+      "150 радиоэлектронный центр\n",
+      "\n",
+      "176\n",
+      "\n",
+      "177\n",
+      "178\n",
+      "\n",
+      "1152 мотострелковый полк\n",
+      "1153 мотострелковый полк\n",
+      "54 мотострелковый полк\n",
+      "\n",
+      "179\n",
+      "\n",
+      "1155 центр\n",
+      "\n",
+      "180\n",
+      "\n",
+      "157 пожарная команда\n",
+      "\n",
+      "ТТТ.\n",
+      "\n",
+      "181\n",
+      "\n",
+      "1158 пожарная команда.\n",
+      "\n",
+      "182\n",
+      "\n",
+      "1159 военное представительство Министерства обороны Российской Федерации\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
+   "execution_count": 81
+  },
+  {
+   "metadata": {},
+   "cell_type": "code",
+   "outputs": [],
+   "execution_count": null,
+   "source": "",
+   "id": "7e909e7dc99c7f4a"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
Original file line number	Diff line number	Diff line change
Expand Up		@@ -27,4 +27,3 @@ runs:
		- name: Install Dependencies
		run: poetry install --extras "ui vector-stores-qdrant" --no-root
		shell: bash