New commit

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -0,0 +1,339 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 2, June 1991
+
+ Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
+ 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The licenses for most software are designed to take away your
+freedom to share and change it.  By contrast, the GNU General Public
+License is intended to guarantee your freedom to share and change free
+software--to make sure the software is free for all its users.  This
+General Public License applies to most of the Free Software
+Foundation's software and to any other program whose authors commit to
+using it.  (Some other Free Software Foundation software is covered by
+the GNU Lesser General Public License instead.)  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+this service if you wish), that you receive source code or can get it
+if you want it, that you can change the software or use pieces of it
+in new free programs; and that you know you can do these things.
+
+  To protect your rights, we need to make restrictions that forbid
+anyone to deny you these rights or to ask you to surrender the rights.
+These restrictions translate to certain responsibilities for you if you
+distribute copies of the software, or if you modify it.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must give the recipients all the rights that
+you have.  You must make sure that they, too, receive or can get the
+source code.  And you must show them these terms so they know their
+rights.
+
+  We protect your rights with two steps: (1) copyright the software, and
+(2) offer you this license which gives you legal permission to copy,
+distribute and/or modify the software.
+
+  Also, for each author's protection and ours, we want to make certain
+that everyone understands that there is no warranty for this free
+software.  If the software is modified by someone else and passed on, we
+want its recipients to know that what they have is not the original, so
+that any problems introduced by others will not reflect on the original
+authors' reputations.
+
+  Finally, any free program is threatened constantly by software
+patents.  We wish to avoid the danger that redistributors of a free
+program will individually obtain patent licenses, in effect making the
+program proprietary.  To prevent this, we have made it clear that any
+patent must be licensed for everyone's free use or not licensed at all.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                    GNU GENERAL PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. This License applies to any program or other work which contains
+a notice placed by the copyright holder saying it may be distributed
+under the terms of this General Public License.  The "Program", below,
+refers to any such program or work, and a "work based on the Program"
+means either the Program or any derivative work under copyright law:
+that is to say, a work containing the Program or a portion of it,
+either verbatim or with modifications and/or translated into another
+language.  (Hereinafter, translation is included without limitation in
+the term "modification".)  Each licensee is addressed as "you".
+
+Activities other than copying, distribution and modification are not
+covered by this License; they are outside its scope.  The act of
+running the Program is not restricted, and the output from the Program
+is covered only if its contents constitute a work based on the
+Program (independent of having been made by running the Program).
+Whether that is true depends on what the Program does.
+
+  1. You may copy and distribute verbatim copies of the Program's
+source code as you receive it, in any medium, provided that you
+conspicuously and appropriately publish on each copy an appropriate
+copyright notice and disclaimer of warranty; keep intact all the
+notices that refer to this License and to the absence of any warranty;
+and give any other recipients of the Program a copy of this License
+along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and
+you may at your option offer warranty protection in exchange for a fee.
+
+  2. You may modify your copy or copies of the Program or any portion
+of it, thus forming a work based on the Program, and copy and
+distribute such modifications or work under the terms of Section 1
+above, provided that you also meet all of these conditions:
+
+    a) You must cause the modified files to carry prominent notices
+    stating that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in
+    whole or in part contains or is derived from the Program or any
+    part thereof, to be licensed as a whole at no charge to all third
+    parties under the terms of this License.
+
+    c) If the modified program normally reads commands interactively
+    when run, you must cause it, when started running for such
+    interactive use in the most ordinary way, to print or display an
+    announcement including an appropriate copyright notice and a
+    notice that there is no warranty (or else, saying that you provide
+    a warranty) and that users may redistribute the program under
+    these conditions, and telling the user how to view a copy of this
+    License.  (Exception: if the Program itself is interactive but
+    does not normally print such an announcement, your work based on
+    the Program is not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If
+identifiable sections of that work are not derived from the Program,
+and can be reasonably considered independent and separate works in
+themselves, then this License, and its terms, do not apply to those
+sections when you distribute them as separate works.  But when you
+distribute the same sections as part of a whole which is a work based
+on the Program, the distribution of the whole must be on the terms of
+this License, whose permissions for other licensees extend to the
+entire whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest
+your rights to work written entirely by you; rather, the intent is to
+exercise the right to control the distribution of derivative or
+collective works based on the Program.
+
+In addition, mere aggregation of another work not based on the Program
+with the Program (or with a work based on the Program) on a volume of
+a storage or distribution medium does not bring the other work under
+the scope of this License.
+
+  3. You may copy and distribute the Program (or a work based on it,
+under Section 2) in object code or executable form under the terms of
+Sections 1 and 2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable
+    source code, which must be distributed under the terms of Sections
+    1 and 2 above on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three
+    years, to give any third party, for a charge no more than your
+    cost of physically performing source distribution, a complete
+    machine-readable copy of the corresponding source code, to be
+    distributed under the terms of Sections 1 and 2 above on a medium
+    customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer
+    to distribute corresponding source code.  (This alternative is
+    allowed only for noncommercial distribution and only if you
+    received the program in object code or executable form with such
+    an offer, in accord with Subsection b above.)
+
+The source code for a work means the preferred form of the work for
+making modifications to it.  For an executable work, complete source
+code means all the source code for all modules it contains, plus any
+associated interface definition files, plus the scripts used to
+control compilation and installation of the executable.  However, as a
+special exception, the source code distributed need not include
+anything that is normally distributed (in either source or binary
+form) with the major components (compiler, kernel, and so on) of the
+operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering
+access to copy from a designated place, then offering equivalent
+access to copy the source code from the same place counts as
+distribution of the source code, even though third parties are not
+compelled to copy the source along with the object code.
+
+  4. You may not copy, modify, sublicense, or distribute the Program
+except as expressly provided under this License.  Any attempt
+otherwise to copy, modify, sublicense or distribute the Program is
+void, and will automatically terminate your rights under this License.
+However, parties who have received copies, or rights, from you under
+this License will not have their licenses terminated so long as such
+parties remain in full compliance.
+
+  5. You are not required to accept this License, since you have not
+signed it.  However, nothing else grants you permission to modify or
+distribute the Program or its derivative works.  These actions are
+prohibited by law if you do not accept this License.  Therefore, by
+modifying or distributing the Program (or any work based on the
+Program), you indicate your acceptance of this License to do so, and
+all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+  6. Each time you redistribute the Program (or any work based on the
+Program), the recipient automatically receives a license from the
+original licensor to copy, distribute or modify the Program subject to
+these terms and conditions.  You may not impose any further
+restrictions on the recipients' exercise of the rights granted herein.
+You are not responsible for enforcing compliance by third parties to
+this License.
+
+  7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues),
+conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot
+distribute so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you
+may not distribute the Program at all.  For example, if a patent
+license would not permit royalty-free redistribution of the Program by
+all those who receive copies directly or indirectly through you, then
+the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under
+any particular circumstance, the balance of the section is intended to
+apply and the section as a whole is intended to apply in other
+circumstances.
+
+It is not the purpose of this section to induce you to infringe any
+patents or other property right claims or to contest validity of any
+such claims; this section has the sole purpose of protecting the
+integrity of the free software distribution system, which is
+implemented by public license practices.  Many people have made
+generous contributions to the wide range of software distributed
+through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing
+to distribute software through any other system and a licensee cannot
+impose that choice.
+
+This section is intended to make thoroughly clear what is believed to
+be a consequence of the rest of this License.
+
+  8. If the distribution and/or use of the Program is restricted in
+certain countries either by patents or by copyrighted interfaces, the
+original copyright holder who places the Program under this License
+may add an explicit geographical distribution limitation excluding
+those countries, so that distribution is permitted only in or among
+countries not thus excluded.  In such case, this License incorporates
+the limitation as if written in the body of this License.
+
+  9. The Free Software Foundation may publish revised and/or new versions
+of the General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any
+later version", you have the option of following the terms and conditions
+either of that version or of any later version published by the Free
+Software Foundation.  If the Program does not specify a version number of
+this License, you may choose any version ever published by the Free Software
+Foundation.
+
+  10. If you wish to incorporate parts of the Program into other free
+programs whose distribution conditions are different, write to the author
+to ask for permission.  For software which is copyrighted by the Free
+Software Foundation, write to the Free Software Foundation; we sometimes
+make exceptions for this.  Our decision will be guided by the two goals
+of preserving the free status of all derivatives of our free software and
+of promoting the sharing and reuse of software generally.
+
+                            NO WARRANTY
+
+  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
+FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
+OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
+PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
+OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
+TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
+PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
+REPAIR OR CORRECTION.
+
+  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
+REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
+INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
+OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
+TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
+YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
+PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGES.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+convey the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this
+when it starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author
+    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may
+be called something other than `show w' and `show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your
+school, if any, to sign a "copyright disclaimer" for the program, if
+necessary.  Here is a sample; alter the names:
+
+  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+  `Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+  <signature of Ty Coon>, 1 April 1989
+  Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.

LLMdocumentchatbot_Colab.ipynb

@@ -0,0 +1,109 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "colab_type": "text",
+        "id": "view-in-github"
+      },
+      "source": [
+        "<a href=\"https://colab.research.google.com/github/R3gm/ConversaDocs/blob/main/ConversaDocs_Colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EnzlcRZycXnr"
+      },
+      "source": [
+        "# LLmDocumentChatBot\n",
+        "\n",
+        "`Chat with your documents using Llama 2, Falcon or OpenAI`\n",
+        "\n",
+        "- You can upload multiple documents at once to a single database.\n",
+        "- Every time a new database is created, the previous one is deleted.\n",
+        "- For maximum privacy, you can click \"Load LLAMA GGML Model\" to use a Llama 2 model. By default, the model llama-2_7B-Chat is loaded.\n",
+        "\n",
+        "Program that enables seamless interaction with your documents through an advanced vector database and the power of Large Language Model (LLM) technology.\n",
+        "\n",
+        "| Description | Link |\n",
+        "| ----------- | ---- |\n",
+        "| 📙 Colab Notebook | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ndn1954/llmdocumentchatbot/blob/main/LLMdocumentchatbot_Colab.ipynb) |\n",
+        "| 🎉 Repository | [![GitHub Repository](https://img.shields.io/badge/GitHub-Repository-black?style=flat-square&logo=github)](https://github.com/ndn1954/llmdocumentchatbot/) |\n",
+        "| 🚀 Online Demo | [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/ndn1954/llmdocumentchatbot) |\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "S5awiNy-A50W"
+      },
+      "outputs": [],
+      "source": [
+        "!git clone https://github.com/ndn1954/llmdocumentchatbot.git\n",
+        "%cd llmdocumentchatbot\n",
+        "!pip install -r requirements.txt\n",
+        "\n",
+        "import torch\n",
+        "import os\n",
+        "print(\"Wait until the cell finishes executing\")\n",
+        "if torch.cuda.is_available():\n",
+        "    print(\"CUDA is available on this system.\")\n",
+        "    os.system('CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir --verbose')\n",
+        "else:\n",
+        "    print(\"CUDA is not available on this system.\")\n",
+        "    os.system('pip install llama-cpp-python')"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "jLfxiOyMEcGF"
+      },
+      "source": [
+        "`RESTART THE RUNTIME` before executing the next cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2F2VGAJtEbb3"
+      },
+      "outputs": [],
+      "source": [
+        "%cd /content/llmdocumentchatbot\n",
+        "!python app.py"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3aEEcmchZIlf"
+      },
+      "source": [
+        "Open the `public URL` when it appears"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "authorship_tag": "ABX9TyMoq/QuUmy+xrGmEAesfDhp",
+      "gpuType": "T4",
+      "include_colab_link": true,
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

README.md

@@ -1,13 +1,24 @@
----
-title: Llmdocumentchatbot
-emoji: 🐢
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 3.40.1
-app_file: app.py
-pinned: false
-license: other
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# ConversaDocs
+
+## 🦙 Chat with your documents using Llama 2, Falcon 🦅 or OpenAI 🤖
+
+- 🔒 By default, the model llama2_7B-Chat is loaded for maximum privacy.
+- 📚 You can upload multiple documents at once to a single database.
+- ♻️ Every time a new database is created, the previous one is deleted.
+- This project is been created from https://github.com/R3gm/ConversaDocs/
+
+Program that enables seamless interaction with your documents through an advanced vector database and the power of Large Language Model (LLM) technology.
+
+| Description | Link |
+| ----------- | ---- |
+| 📙 Colab Notebook | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ndn1954/llmdocumentchatbot/blob/main/LLMdocumentchatbot_Colab.ipynb) |
+| 🎉 Repository | [![GitHub Repository](https://img.shields.io/badge/GitHub-Repository-black?style=flat-square&logo=github)](https://github.com/ndn1954/llmdocumentchatbot/) |
+| 🚀 Online inference HF | [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://github.com/ndn1954/llmdocumentchatbot/) |
+
+<!--### Chat with different formats of documents.
+![image](https://github.com/R3gm/ConversaDocs/assets/114810545/1c6c426f-c144-442e-b71a-07867bdf68d3)
+
+### Summarize.
+
+![image](https://github.com/R3gm/ConversaDocs/assets/114810545/2ded3f4e-a9d6-44db-b73b-b81c0abeeebb)-->
+

app.py

@@ -0,0 +1,178 @@
+import torch
+import os
+try:
+  from llama_cpp import Llama
+except:
+  if torch.cuda.is_available():
+      print("CUDA is available on this system.")
+      os.system('CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir --verbose')
+  else:
+      print("CUDA is not available on this system.")
+      os.system('pip install llama-cpp-python')
+
+import gradio as gr
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
+from langchain.vectorstores import DocArrayInMemorySearch
+from langchain.chains import RetrievalQA,  ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain import HuggingFaceHub
+from langchain.llms import LlamaCpp
+from huggingface_hub import hf_hub_download
+from langchain.document_loaders import (
+    EverNoteLoader,
+    TextLoader,
+    UnstructuredEPubLoader,
+    UnstructuredHTMLLoader,
+    UnstructuredMarkdownLoader,
+    UnstructuredODTLoader,
+    UnstructuredPowerPointLoader,
+    UnstructuredWordDocumentLoader,
+    PyPDFLoader,
+)
+import param
+from bones import DocChat
+
+dc = DocChat()
+
+##### GRADIO CONFIG ####
+
+css="""
+#col-container {max-width: 1500px; margin-left: auto; margin-right: auto;}
+"""
+
+title = """
+<div style="text-align: center;max-width: 1500px;">
+    <h2>Chat with Documents 📚 - Falcon, Llama-2 and OpenAI</h2>
+    <p style="text-align: center;">Upload txt, pdf, doc, docx, enex, epub, html, md, odt, ptt and pttx.
+    Wait for the Status to show Loaded documents, start typing your questions. Oficial Repository <a href="https://github.com/ndn1954/llmdocumentchatbot">llmdocumentchatbot</a>.<br /></p>
+</div>
+"""
+
+description = """
+# Application Information
+
+- Notebook for run llmdocumentchatbot in Colab [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github.com/ndn1954/llmdocumentchatbot/LLMdocumentchatbot_Colab.ipynb)
+
+- Oficial Repository [![a](https://img.shields.io/badge/GitHub-Repository-black?style=flat-square&logo=github)](https://github.com/ndn1954/llmdocumentchatbot/)
+
+- You can upload multiple documents at once to a single database.
+
+- Every time a new database is created, the previous one is deleted.
+
+- For maximum privacy, you can click "Load LLAMA GGML Model" to use a Llama 2 model. By default, the model llama-2_7B-Chat is loaded.
+
+- This application works on both CPU and GPU. For fast inference with GGML models, use the GPU.
+
+- For more information about what GGML models are, you can visit this notebook [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github.com/ndn1954/llmdocumentchatbot/LLMdocumentchatbot_Colab.ipynb)
+
+"""
+
+theme='aliabid94/new-theme'
+
+def flag():
+  return "PROCESSING..."
+
+def upload_file(files, max_docs):
+    file_paths = [file.name for file in files]
+    return dc.call_load_db(file_paths, max_docs)
+
+def predict(message, chat_history, max_k, check_memory):
+        print(message)
+        bot_message = dc.convchain(message, max_k, check_memory)
+        print(bot_message)
+        return "", dc.get_chats()
+
+def convert():
+  docs = dc.get_sources()
+  data_docs = ""
+  for i in range(0,len(docs),2):
+    txt = docs[i][1].replace("\n","<br>")
+    sc = "Archive: " + docs[i+1][1]["source"]
+    try:
+      pg = "Page: " + str(docs[i+1][1]["page"])
+    except:
+      pg = "Document Data"
+    data_docs += f"<hr><h3 style='color:red;'>{pg}</h2><p>{txt}</p><p>{sc}</p>"
+  return data_docs
+
+def clear_api_key(api_key):
+  return 'api_key...', dc.openai_model(api_key)
+
+# Max values in generation
+DOC_DB_LIMIT = 5
+MAX_NEW_TOKENS = 2048
+
+# Limit in HF, no need to set it
+if "SET_LIMIT" == os.getenv("DEMO"):
+    DOC_DB_LIMIT = 4
+    MAX_NEW_TOKENS = 32
+
+with gr.Blocks(theme=theme, css=css) as demo:
+  with gr.Tab("Chat"):
+
+    with gr.Column():
+        gr.HTML(title)
+        upload_button = gr.UploadButton("Click to Upload Files", file_count="multiple")
+        file_output = gr.HTML()
+
+        chatbot = gr.Chatbot([], elem_id="chatbot") #.style(height=300)
+        msg = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
+        with gr.Row():
+            check_memory = gr.inputs.Checkbox(label="Remember previous messages")
+            clear_button = gr.Button("CLEAR CHAT HISTORY", )
+            max_docs = gr.inputs.Slider(1, DOC_DB_LIMIT, default=3, label="Maximum querys to the DB.", step=1)
+
+    with gr.Column():
+        link_output = gr.HTML("")
+        sou = gr.HTML("")
+
+    clear_button.click(flag,[],[link_output]).then(dc.clr_history,[], [link_output]).then(lambda: None, None, chatbot, queue=False)
+    upload_button.upload(flag,[],[file_output]).then(upload_file, [upload_button, max_docs], file_output).then(dc.clr_history,[], [link_output])
+
+  with gr.Tab("Experimental Summarization"):
+    default_model = gr.HTML("<hr>From DB<br>It may take approximately 5 minutes to complete 15 pages in GPU. Please use files with fewer pages if you want to use summarization.<br></h2>")
+    summarize_button = gr.Button("Start summarization")
+
+    summarize_verify = gr.HTML(" ")
+    summarize_button.click(dc.summarize, [], [summarize_verify])
+  
+  with gr.Tab("Config llama-2 model"):
+    gr.HTML("<h3>Only models from the GGML library are accepted. To apply the new configurations, please reload the model.</h3>")
+    repo_ = gr.Textbox(label="Repository" ,value="TheBloke/Llama-2-7B-Chat-GGML")
+    file_ = gr.Textbox(label="File name" ,value="llama-2-7b-chat.ggmlv3.q5_1.bin")
+    max_tokens = gr.inputs.Slider(1, 2048, default=256, label="Max new tokens", step=1)
+    temperature = gr.inputs.Slider(0.1, 1., default=0.2, label="Temperature", step=0.1)
+    top_k = gr.inputs.Slider(0.01, 1., default=0.95, label="Top K", step=0.01)
+    top_p = gr.inputs.Slider(0, 100, default=50, label="Top P", step=1)
+    repeat_penalty = gr.inputs.Slider(0.1, 100., default=1.2, label="Repeat penalty", step=0.1)
+    change_model_button = gr.Button("Load Llama GGML Model")
+
+    model_verify_ggml = gr.HTML("Loaded model Llama-2")
+
+  with gr.Tab("API Models"):
+
+    default_model = gr.HTML("<hr>Falcon Model</h2>")
+    hf_key = gr.Textbox(label="HF TOKEN", value="token...")
+    falcon_button = gr.Button("Load FALCON 7B-Instruct")
+
+    openai_gpt_model = gr.HTML("<hr>OpenAI Model gpt-3.5-turbo</h2>")
+    api_key = gr.Textbox(label="API KEY", value="api_key...")
+    openai_button = gr.Button("Load gpt-3.5-turbo")
+
+    line_ = gr.HTML("<hr> </h2>")
+    model_verify = gr.HTML(" ")
+
+  with gr.Tab("Help"):
+    description_md = gr.Markdown(description)
+
+  msg.submit(predict,[msg, chatbot, max_docs, check_memory],[msg, chatbot]).then(convert,[],[sou])
+
+  change_model_button.click(dc.change_llm,[repo_, file_, max_tokens, temperature, top_p, top_k, repeat_penalty, max_docs],[model_verify_ggml])
+
+  falcon_button.click(dc.default_falcon_model, [hf_key], [model_verify])
+  openai_button.click(clear_api_key, [api_key], [api_key, model_verify])
+
+demo.launch(debug=True, share=True,  enable_queue=True)

bones.py

@@ -0,0 +1,277 @@
+import gradio as gr
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
+from langchain.vectorstores import DocArrayInMemorySearch
+from langchain.chains import RetrievalQA,  ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain import HuggingFaceHub
+from conversadocs.llamacppmodels import LlamaCpp #from langchain.llms import LlamaCpp
+from huggingface_hub import hf_hub_download
+import param
+import os
+import torch
+from langchain.document_loaders import (
+    EverNoteLoader,
+    TextLoader,
+    UnstructuredEPubLoader,
+    UnstructuredHTMLLoader,
+    UnstructuredMarkdownLoader,
+    UnstructuredODTLoader,
+    UnstructuredPowerPointLoader,
+    UnstructuredWordDocumentLoader,
+    PyPDFLoader,
+)
+import gc
+gc.collect()
+torch.cuda.empty_cache()
+
+#YOUR_HF_TOKEN = os.getenv("My_hf_token")
+
+EXTENSIONS = {
+    ".txt": (TextLoader, {"encoding": "utf8"}),
+    ".pdf": (PyPDFLoader, {}),
+    ".doc": (UnstructuredWordDocumentLoader, {}),
+    ".docx": (UnstructuredWordDocumentLoader, {}),
+    ".enex": (EverNoteLoader, {}),
+    ".epub": (UnstructuredEPubLoader, {}),
+    ".html": (UnstructuredHTMLLoader, {}),
+    ".md": (UnstructuredMarkdownLoader, {}),
+    ".odt": (UnstructuredODTLoader, {}),
+    ".ppt": (UnstructuredPowerPointLoader, {}),
+    ".pptx": (UnstructuredPowerPointLoader, {}),
+}
+
+#alter
+def load_db(files):
+
+    # select extensions loader
+    documents = []
+    for file in files:
+      ext = "." + file.rsplit(".", 1)[-1]
+      if ext in EXTENSIONS:
+          loader_class, loader_args = EXTENSIONS[ext]
+          loader = loader_class(file, **loader_args)
+          documents.extend(loader.load())
+      else:
+        pass
+
+    # load documents
+    if documents == []:
+        loader_class, loader_args = EXTENSIONS['.txt']
+        loader = loader_class('demo_docs/demo.txt', **loader_args)
+        documents = loader.load()
+
+    # split documents
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
+    docs = text_splitter.split_documents(documents)
+
+    # define embedding
+    embeddings = HuggingFaceEmbeddings(model_name='all-MiniLM-L6-v2') # all-mpnet-base-v2 #embeddings = OpenAIEmbeddings()
+
+    # create vector database from data
+    db = DocArrayInMemorySearch.from_documents(docs, embeddings)
+    return db
+
+def q_a(db, chain_type="stuff", k=3, llm=None):
+    retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": k})
+    # create a chatbot chain. Memory is managed externally.
+    qa = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        chain_type=chain_type,
+        retriever=retriever,
+        return_source_documents=True,
+        return_generated_question=True,
+    )
+    return qa
+
+
+
+class DocChat(param.Parameterized):
+    chat_history = param.List([])
+    answer = param.String("")
+    db_query  = param.String("")
+    db_response = param.List([])
+    k_value = param.Integer(3)
+    llm = None
+
+    def __init__(self,  **params):
+        super(DocChat, self).__init__( **params)
+        self.loaded_file = ["demo_docs/demo.txt"]
+        self.db = load_db(self.loaded_file)
+        self.change_llm("TheBloke/Llama-2-7B-Chat-GGML", "llama-2-7b-chat.ggmlv3.q5_1.bin", max_tokens=256, temperature=0.2, top_p=0.95, top_k=50, repeat_penalty=1.2, k=3)
+        self.qa = q_a(self.db, "stuff", self.k_value, self.llm)
+        
+
+    def call_load_db(self, path_file, k):
+        if not os.path.exists(path_file[0]):  # init or no file specified
+            return "No file loaded"
+        else:
+          try:
+            self.db = load_db(path_file)
+            self.loaded_file = path_file
+            self.qa = q_a(self.db, "stuff", k, self.llm)
+            self.k_value = k
+            #self.clr_history()
+            return f"New DB created and history cleared | Loaded File: {self.loaded_file}"
+          except:
+            return f'No valid file'
+
+
+    # chat
+    def convchain(self, query, k_max, recall_previous_messages):
+        if k_max != self.k_value:
+          print("Maximum querys changed")
+          self.qa = q_a(self.db, "stuff", k_max, self.llm)
+          self.k_value = k_max
+
+        if not recall_previous_messages:
+          self.clr_history()
+
+        try:
+          result = self.qa({"question": query, "chat_history": self.chat_history})
+        except:
+          print("Error not get response from model, reloaded default llama-2 7B config")
+          self.change_llm("TheBloke/Llama-2-7B-Chat-GGML", "llama-2-7b-chat.ggmlv3.q5_1.bin", max_tokens=256, temperature=0.2, top_p=0.95, top_k=50, repeat_penalty=1.2, k=3)
+          self.qa = q_a(self.db, "stuff", k_max, self.llm)
+          result = self.qa({"question": query, "chat_history": self.chat_history})
+        
+        self.chat_history.extend([(query, result["answer"])])
+        self.db_query = result["generated_question"]
+        self.db_response = result["source_documents"]
+        self.answer = result['answer']
+        return self.answer
+
+    def summarize(self, chunk_size=2000, chunk_overlap=100):
+        # load docs
+        documents = []
+        for file in self.loaded_file:
+          ext = "." + file.rsplit(".", 1)[-1]
+          if ext in EXTENSIONS:
+              loader_class, loader_args = EXTENSIONS[ext]
+              loader = loader_class(file, **loader_args)
+              documents.extend(loader.load_and_split())
+
+        if documents == []:
+            return "Error in summarization"
+
+        # split documents
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=chunk_size, 
+            chunk_overlap=chunk_overlap,
+            separators=["\n\n", "\n", "(?<=\. )", " ", ""]
+            )
+        docs = text_splitter.split_documents(documents)
+        # summarize
+        from langchain.chains.summarize import load_summarize_chain
+        chain = load_summarize_chain(self.llm, chain_type='map_reduce', verbose=True)
+        return chain.run(docs)
+
+    def change_llm(self, repo_, file_, max_tokens=256, temperature=0.2, top_p=0.95, top_k=50, repeat_penalty=1.2, k=3):
+
+        if torch.cuda.is_available():
+            try:
+              model_path = hf_hub_download(repo_id=repo_, filename=file_)
+              
+              self.qa = None
+              self.llm = None
+              gc.collect()
+              torch.cuda.empty_cache()
+              gpu_llm_layers = 35 if not '70B' in repo_.upper() else 25 # fix for 70B
+
+              self.llm = LlamaCpp(
+                  model_path=model_path,
+                  n_ctx=4096,
+                  n_batch=512,
+                  n_gpu_layers=gpu_llm_layers, 
+                  max_tokens=max_tokens,
+                  verbose=False,
+                  temperature=temperature,
+                  top_p=top_p,
+                  top_k=top_k,
+                  repeat_penalty=repeat_penalty,
+                  )
+              self.qa = q_a(self.db, "stuff", k, self.llm)
+              self.k_value = k
+              return f"Loaded {file_} [GPU INFERENCE]"
+            except:
+              self.change_llm("TheBloke/Llama-2-7B-Chat-GGML", "llama-2-7b-chat.ggmlv3.q5_1.bin", max_tokens=256, temperature=0.2, top_p=0.95, top_k=50, repeat_penalty=1.2, k=3)
+              return "No valid model | Reloaded Reloaded default llama-2 7B config"
+        else:
+            try:
+              model_path = hf_hub_download(repo_id=repo_, filename=file_)
+              
+              self.qa = None
+              self.llm = None
+              gc.collect()
+              torch.cuda.empty_cache()
+
+              self.llm = LlamaCpp(
+                  model_path=model_path,
+                  n_ctx=2048,
+                  n_batch=8,
+                  max_tokens=max_tokens,
+                  verbose=False,
+                  temperature=temperature,
+                  top_p=top_p,
+                  top_k=top_k,
+                  repeat_penalty=repeat_penalty,
+                  )
+              self.qa = q_a(self.db, "stuff", k, self.llm)
+              self.k_value = k
+              return f"Loaded {file_} [CPU INFERENCE SLOW]"
+            except:
+              self.change_llm("TheBloke/Llama-2-7B-Chat-GGML", "llama-2-7b-chat.ggmlv3.q5_1.bin", max_tokens=256, temperature=0.2, top_p=0.95, top_k=50, repeat_penalty=1.2, k=3)
+              return "No valid model | Reloaded default llama-2 7B config"
+
+    def default_falcon_model(self, HF_TOKEN):
+      self.llm = llm_api=HuggingFaceHub(
+          huggingfacehub_api_token=HF_TOKEN,
+          repo_id="tiiuae/falcon-7b-instruct",
+          model_kwargs={
+              "temperature":0.2,
+              "max_new_tokens":500,
+              "top_k":50,
+              "top_p":0.95,
+              "repetition_penalty":1.2,
+              },)
+      self.qa = q_a(self.db, "stuff", self.k_value, self.llm)
+      return "Loaded model Falcon 7B-instruct [API FAST INFERENCE]"
+
+    def openai_model(self, API_KEY):
+        self.llm = ChatOpenAI(temperature=0, openai_api_key=API_KEY, model_name='gpt-3.5-turbo')
+        self.qa = q_a(self.db, "stuff", self.k_value, self.llm)
+        API_KEY = ""
+        return "Loaded model OpenAI gpt-3.5-turbo [API FAST INFERENCE]"
+
+    @param.depends('db_query ', )
+    def get_lquest(self):
+        if not self.db_query :
+            return print("Last question to DB: no DB accesses so far")
+        return self.db_query
+
+    @param.depends('db_response', )
+    def get_sources(self):
+        if not self.db_response:
+            return
+        #rlist=[f"Result of DB lookup:"]
+        rlist=[]
+        for doc in self.db_response:
+          for element in doc:
+            rlist.append(element)
+        return rlist
+
+    @param.depends('convchain', 'clr_history')
+    def get_chats(self):
+        if not self.chat_history:
+            return "No History Yet"
+        #rlist=[f"Current Chat History variable"]
+        rlist=[]
+        for exchange in self.chat_history:
+            rlist.append(exchange)
+        return rlist
+
+    def clr_history(self,count=0):
+        self.chat_history = []
+        return "HISTORY CLEARED"

llamacppmodels.py

@@ -0,0 +1,309 @@
+import logging
+from typing import Any, Dict, Iterator, List, Optional
+
+from pydantic import Field, root_validator
+
+from langchain.callbacks.manager import CallbackManagerForLLMRun
+from langchain.llms.base import LLM
+from langchain.schema.output import GenerationChunk
+
+logger = logging.getLogger(__name__)
+
+
+class LlamaCpp(LLM):
+    """llama.cpp model.
+
+    To use, you should have the llama-cpp-python library installed, and provide the
+    path to the Llama model as a named parameter to the constructor.
+    Check out: https://github.com/abetlen/llama-cpp-python
+
+    Example:
+        .. code-block:: python
+
+            from langchain.llms import LlamaCpp
+            llm = LlamaCpp(model_path="/path/to/llama/model")
+    """
+
+    client: Any  #: :meta private:
+    model_path: str
+    """The path to the Llama model file."""
+
+    lora_base: Optional[str] = None
+    """The path to the Llama LoRA base model."""
+
+    lora_path: Optional[str] = None
+    """The path to the Llama LoRA. If None, no LoRa is loaded."""
+
+    n_ctx: int = Field(512, alias="n_ctx")
+    """Token context window."""
+
+    n_parts: int = Field(-1, alias="n_parts")
+    """Number of parts to split the model into.
+    If -1, the number of parts is automatically determined."""
+
+    seed: int = Field(-1, alias="seed")
+    """Seed. If -1, a random seed is used."""
+
+    f16_kv: bool = Field(True, alias="f16_kv")
+    """Use half-precision for key/value cache."""
+
+    logits_all: bool = Field(False, alias="logits_all")
+    """Return logits for all tokens, not just the last token."""
+
+    vocab_only: bool = Field(False, alias="vocab_only")
+    """Only load the vocabulary, no weights."""
+
+    use_mlock: bool = Field(False, alias="use_mlock")
+    """Force system to keep model in RAM."""
+
+    n_threads: Optional[int] = Field(None, alias="n_threads")
+    """Number of threads to use.
+    If None, the number of threads is automatically determined."""
+
+    n_batch: Optional[int] = Field(8, alias="n_batch")
+    """Number of tokens to process in parallel.
+    Should be a number between 1 and n_ctx."""
+
+    n_gpu_layers: Optional[int] = Field(None, alias="n_gpu_layers")
+    """Number of layers to be loaded into gpu memory. Default None."""
+
+    suffix: Optional[str] = Field(None)
+    """A suffix to append to the generated text. If None, no suffix is appended."""
+
+    max_tokens: Optional[int] = 256
+    """The maximum number of tokens to generate."""
+
+    temperature: Optional[float] = 0.8
+    """The temperature to use for sampling."""
+
+    top_p: Optional[float] = 0.95
+    """The top-p value to use for sampling."""
+
+    logprobs: Optional[int] = Field(None)
+    """The number of logprobs to return. If None, no logprobs are returned."""
+
+    echo: Optional[bool] = False
+    """Whether to echo the prompt."""
+
+    stop: Optional[List[str]] = []
+    """A list of strings to stop generation when encountered."""
+
+    repeat_penalty: Optional[float] = 1.1
+    """The penalty to apply to repeated tokens."""
+
+    top_k: Optional[int] = 40
+    """The top-k value to use for sampling."""
+
+    last_n_tokens_size: Optional[int] = 64
+    """The number of tokens to look back when applying the repeat_penalty."""
+
+    use_mmap: Optional[bool] = True
+    """Whether to keep the model loaded in RAM"""
+
+    rope_freq_scale: float = 1.0
+    """Scale factor for rope sampling."""
+
+    rope_freq_base: float = 10000.0
+    """Base frequency for rope sampling."""
+
+    streaming: bool = True
+    """Whether to stream the results, token by token."""
+
+    verbose: bool = True
+    """Print verbose output to stderr."""
+
+    n_gqa: Optional[int] = None
+
+    @root_validator()
+    def validate_environment(cls, values: Dict) -> Dict:
+        """Validate that llama-cpp-python library is installed."""
+
+        
+        model_path = values["model_path"]
+        model_param_names = [
+            "n_gqa",
+            "rope_freq_scale",
+            "rope_freq_base",
+            "lora_path",
+            "lora_base",
+            "n_ctx",
+            "n_parts",
+            "seed",
+            "f16_kv",
+            "logits_all",
+            "vocab_only",
+            "use_mlock",
+            "n_threads",
+            "n_batch",
+            "use_mmap",
+            "last_n_tokens_size",
+            "verbose",
+        ]
+        model_params = {k: values[k] for k in model_param_names}
+
+        model_params['n_gqa'] = 8 if '70B' in model_path.upper() else None # (TEMPORARY) must be 8 for llama2 70b
+        # For backwards compatibility, only include if non-null.
+        if values["n_gpu_layers"] is not None:
+            model_params["n_gpu_layers"] = values["n_gpu_layers"]
+
+        try:
+            from llama_cpp import Llama
+
+            values["client"] = Llama(model_path, **model_params)
+        except ImportError:
+            raise ImportError(
+                "Could not import llama-cpp-python library. "
+                "Please install the llama-cpp-python library to "
+                "use this embedding model: pip install llama-cpp-python"
+            )
+        except Exception as e:
+            raise ValueError(
+                f"Could not load Llama model from path: {model_path}. "
+                f"Received error {e}"
+            )
+
+        return values
+
+    @property
+    def _default_params(self) -> Dict[str, Any]:
+        """Get the default parameters for calling llama_cpp."""
+        return {
+            "suffix": self.suffix,
+            "max_tokens": self.max_tokens,
+            "temperature": self.temperature,
+            "top_p": self.top_p,
+            "logprobs": self.logprobs,
+            "echo": self.echo,
+            "stop_sequences": self.stop,  # key here is convention among LLM classes
+            "repeat_penalty": self.repeat_penalty,
+            "top_k": self.top_k,
+        }
+
+    @property
+    def _identifying_params(self) -> Dict[str, Any]:
+        """Get the identifying parameters."""
+        return {**{"model_path": self.model_path}, **self._default_params}
+
+    @property
+    def _llm_type(self) -> str:
+        """Return type of llm."""
+        return "llamacpp"
+
+    def _get_parameters(self, stop: Optional[List[str]] = None) -> Dict[str, Any]:
+        """
+        Performs sanity check, preparing parameters in format needed by llama_cpp.
+
+        Args:
+            stop (Optional[List[str]]): List of stop sequences for llama_cpp.
+
+        Returns:
+            Dictionary containing the combined parameters.
+        """
+
+        # Raise error if stop sequences are in both input and default params
+        if self.stop and stop is not None:
+            raise ValueError("`stop` found in both the input and default params.")
+
+        params = self._default_params
+
+        # llama_cpp expects the "stop" key not this, so we remove it:
+        params.pop("stop_sequences")
+
+        # then sets it as configured, or default to an empty list:
+        params["stop"] = self.stop or stop or []
+
+        return params
+
+    def _call(
+        self,
+        prompt: str,
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> str:
+        """Call the Llama model and return the output.
+
+        Args:
+            prompt: The prompt to use for generation.
+            stop: A list of strings to stop generation when encountered.
+
+        Returns:
+            The generated text.
+
+        Example:
+            .. code-block:: python
+
+                from langchain.llms import LlamaCpp
+                llm = LlamaCpp(model_path="/path/to/local/llama/model.bin")
+                llm("This is a prompt.")
+        """
+        if self.streaming:
+            # If streaming is enabled, we use the stream
+            # method that yields as they are generated
+            # and return the combined strings from the first choices's text:
+            combined_text_output = ""
+            for chunk in self._stream(
+                prompt=prompt, stop=stop, run_manager=run_manager, **kwargs
+            ):
+                combined_text_output += chunk.text
+            return combined_text_output
+        else:
+            params = self._get_parameters(stop)
+            params = {**params, **kwargs}
+            result = self.client(prompt=prompt, **params)
+            return result["choices"][0]["text"]
+
+    def _stream(
+        self,
+        prompt: str,
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> Iterator[GenerationChunk]:
+        """Yields results objects as they are generated in real time.
+
+        It also calls the callback manager's on_llm_new_token event with
+        similar parameters to the OpenAI LLM class method of the same name.
+
+        Args:
+            prompt: The prompts to pass into the model.
+            stop: Optional list of stop words to use when generating.
+
+        Returns:
+            A generator representing the stream of tokens being generated.
+
+        Yields:
+            A dictionary like objects containing a string token and metadata.
+            See llama-cpp-python docs and below for more.
+
+        Example:
+            .. code-block:: python
+
+                from langchain.llms import LlamaCpp
+                llm = LlamaCpp(
+                    model_path="/path/to/local/model.bin",
+                    temperature = 0.5
+                )
+                for chunk in llm.stream("Ask 'Hi, how are you?' like a pirate:'",
+                        stop=["'","\n"]):
+                    result = chunk["choices"][0]
+                    print(result["text"], end='', flush=True)
+
+        """
+        params = {**self._get_parameters(stop), **kwargs}
+        result = self.client(prompt=prompt, stream=True, **params)
+        for part in result:
+            logprobs = part["choices"][0].get("logprobs", None)
+            chunk = GenerationChunk(
+                text=part["choices"][0]["text"],
+                generation_info={"logprobs": logprobs},
+            )
+            yield chunk
+            if run_manager:
+                run_manager.on_llm_new_token(
+                    token=chunk.text, verbose=self.verbose, log_probs=logprobs
+                )
+
+    def get_num_tokens(self, text: str) -> int:
+        tokenized_text = self.client.tokenize(text.encode("utf-8"))
+        return len(tokenized_text)

requirements.txt

@@ -0,0 +1,14 @@
+transformers
+torch
+pypdf
+langchain==0.0.247
+langchain[docarray]
+tiktoken
+sentence_transformers
+chromadb
+huggingface_hub
+unstructured[local-inference]
+gradio==3.35.2
+param==1.13.0
+openai
+python-chess==1.999