baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

add privategpt example

Browse source
This commit is contained in:
Jeffrey Morgan 2023-08-11 00:18:13 -07:00
parent efae43f932
commit b1c88eb978
9 changed files with 5778 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

170
examples/privategpt/.gitignore vendored Normal file
View file

@ -0,0 +1,170 @@
# OSX
.DS_STORE
# Models
models/
# Local Chroma db
.chroma/
db/
# 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/

201
examples/privategpt/LICENSE Normal file
View file

@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

66
examples/privategpt/README.md Normal file
View file

@ -0,0 +1,66 @@
# privateGPT with Llama 2 Uncensored
> Note: this example is a simplified version of [PrivateGPT](https://github.com/imartinez/privateGPT) that works with Llama 2 Uncensored.
### Setup
```shell
pip install -r requirements.txt
```
### Getting WeWork's latest quarterly report
```
curl https://d18rn0p25nwr6d.cloudfront.net/CIK-0001813756/975b3e9b-268e-4798-a9e4-2a9a7c92dc10.pdf -o source_documents/wework.pdf
```
### Ingesting data
```shell
python ingest.py
```
Output should look like this:
```shell
Creating new vectorstore
Loading documents from source_documents
Loading new documents: 100%|██████████████████████| 1/1 [00:01<00:00, 1.73s/it]
Loaded 1 new documents from source_documents
Split into 90 chunks of text (max. 500 tokens each)
Creating embeddings. May take some minutes...
Using embedded DuckDB with persistence: data will be stored in: db
Ingestion complete! You can now run privateGPT.py to query your documents
```
### Ask Questions!
```shell
python privateGPT.py
Enter a query: How many locations does WeWork have?
> Answer (took 17.7 s.):
As of June 2023, WeWork has 777 locations worldwide, including 610 Consolidated Locations (as defined in the section entitled Key Performance Indicators).
```
## Adding your own data
Put any and all your files into the `source_documents` directory
The supported extensions are:
- `.csv`: CSV,
- `.docx`: Word Document,
- `.doc`: Word Document,
- `.enex`: EverNote,
- `.eml`: Email,
- `.epub`: EPub,
- `.html`: HTML File,
- `.md`: Markdown,
- `.msg`: Outlook Message,
- `.odt`: Open Document Text,
- `.pdf`: Portable Document Format (PDF),
- `.pptx` : PowerPoint Document,
- `.ppt` : PowerPoint Document,
- `.txt`: Text file (UTF-8),

15
examples/privategpt/constants.py Normal file
View file

@ -0,0 +1,15 @@
import os
from dotenv import load_dotenv
from chromadb.config import Settings
load_dotenv()
# Define the folder for storing database
PERSIST_DIRECTORY = os.environ.get('PERSIST_DIRECTORY', 'db')
# Define the Chroma settings
CHROMA_SETTINGS = Settings(
chroma_db_impl='duckdb+parquet',
persist_directory=PERSIST_DIRECTORY,
anonymized_telemetry=False
)

166
examples/privategpt/ingest.py Executable file
View file

@ -0,0 +1,166 @@
#!/usr/bin/env python3
import os
import glob
from typing import List
from dotenv import load_dotenv
from multiprocessing import Pool
from tqdm import tqdm
from langchain.document_loaders import (
CSVLoader,
EverNoteLoader,
PyMuPDFLoader,
TextLoader,
UnstructuredEmailLoader,
UnstructuredEPubLoader,
UnstructuredHTMLLoader,
UnstructuredMarkdownLoader,
UnstructuredODTLoader,
UnstructuredPowerPointLoader,
UnstructuredWordDocumentLoader,
)
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.docstore.document import Document
from constants import CHROMA_SETTINGS
load_dotenv()
# Load environment variables
persist_directory = os.environ.get('PERSIST_DIRECTORY', 'db')
source_directory = os.environ.get('SOURCE_DIRECTORY', 'source_documents')
embeddings_model_name = os.environ.get('EMBEDDINGS_MODEL_NAME', 'all-MiniLM-L6-v2')
chunk_size = 500
chunk_overlap = 50
# Custom document loaders
class MyElmLoader(UnstructuredEmailLoader):
"""Wrapper to fallback to text/plain when default does not work"""
def load(self) -> List[Document]:
"""Wrapper adding fallback for elm without html"""
try:
try:
doc = UnstructuredEmailLoader.load(self)
except ValueError as e:
if 'text/html content not found in email' in str(e):
# Try plain text
self.unstructured_kwargs["content_source"]="text/plain"
doc = UnstructuredEmailLoader.load(self)
else:
raise
except Exception as e:
# Add file_path to exception message
raise type(e)(f"{self.file_path}: {e}") from e
return doc
# Map file extensions to document loaders and their arguments
LOADER_MAPPING = {
".csv": (CSVLoader, {}),
# ".docx": (Docx2txtLoader, {}),
".doc": (UnstructuredWordDocumentLoader, {}),
".docx": (UnstructuredWordDocumentLoader, {}),
".enex": (EverNoteLoader, {}),
".eml": (MyElmLoader, {}),
".epub": (UnstructuredEPubLoader, {}),
".html": (UnstructuredHTMLLoader, {}),
".md": (UnstructuredMarkdownLoader, {}),
".odt": (UnstructuredODTLoader, {}),
".pdf": (PyMuPDFLoader, {}),
".ppt": (UnstructuredPowerPointLoader, {}),
".pptx": (UnstructuredPowerPointLoader, {}),
".txt": (TextLoader, {"encoding": "utf8"}),
# Add more mappings for other file extensions and loaders as needed
}
def load_single_document(file_path: str) -> List[Document]:
ext = "." + file_path.rsplit(".", 1)[-1]
if ext in LOADER_MAPPING:
loader_class, loader_args = LOADER_MAPPING[ext]
loader = loader_class(file_path, **loader_args)
return loader.load()
raise ValueError(f"Unsupported file extension '{ext}'")
def load_documents(source_dir: str, ignored_files: List[str] = []) -> List[Document]:
"""
Loads all documents from the source documents directory, ignoring specified files
"""
all_files = []
for ext in LOADER_MAPPING:
all_files.extend(
glob.glob(os.path.join(source_dir, f"**/*{ext}"), recursive=True)
)
filtered_files = [file_path for file_path in all_files if file_path not in ignored_files]
with Pool(processes=os.cpu_count()) as pool:
results = []
with tqdm(total=len(filtered_files), desc='Loading new documents', ncols=80) as pbar:
for i, docs in enumerate(pool.imap_unordered(load_single_document, filtered_files)):
results.extend(docs)
pbar.update()
return results
def process_documents(ignored_files: List[str] = []) -> List[Document]:
"""
Load documents and split in chunks
"""
print(f"Loading documents from {source_directory}")
documents = load_documents(source_directory, ignored_files)
if not documents:
print("No new documents to load")
exit(0)
print(f"Loaded {len(documents)} new documents from {source_directory}")
text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
texts = text_splitter.split_documents(documents)
print(f"Split into {len(texts)} chunks of text (max. {chunk_size} tokens each)")
return texts
def does_vectorstore_exist(persist_directory: str) -> bool:
"""
Checks if vectorstore exists
"""
if os.path.exists(os.path.join(persist_directory, 'index')):
if os.path.exists(os.path.join(persist_directory, 'chroma-collections.parquet')) and os.path.exists(os.path.join(persist_directory, 'chroma-embeddings.parquet')):
list_index_files = glob.glob(os.path.join(persist_directory, 'index/*.bin'))
list_index_files += glob.glob(os.path.join(persist_directory, 'index/*.pkl'))
# At least 3 documents are needed in a working vectorstore
if len(list_index_files) > 3:
return True
return False
def main():
# Create embeddings
embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
if does_vectorstore_exist(persist_directory):
# Update and store locally vectorstore
print(f"Appending to existing vectorstore at {persist_directory}")
db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
collection = db.get()
texts = process_documents([metadata['source'] for metadata in collection['metadatas']])
print(f"Creating embeddings. May take some minutes...")
db.add_documents(texts)
else:
# Create and store locally vectorstore
print("Creating new vectorstore")
texts = process_documents()
print(f"Creating embeddings. May take some minutes...")
db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
db.persist()
db = None
print(f"Ingestion complete! You can now run privateGPT.py to query your documents")
if __name__ == "__main__":
main()

3310
examples/privategpt/poetry.lock generated Normal file
View file

File diff suppressed because it is too large Load diff

72
examples/privategpt/privateGPT.py Executable file
View file

@ -0,0 +1,72 @@
#!/usr/bin/env python3
from dotenv import load_dotenv
from langchain.chains import RetrievalQA
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.vectorstores import Chroma
from langchain.llms import GPT4All, Ollama
import os
import argparse
import time
load_dotenv()
model = os.environ.get("MODEL", "llama2-uncensored")
embeddings_model_name = os.environ.get("EMBEDDINGS_MODEL_NAME", "all-MiniLM-L6-v2")
persist_directory = os.environ.get("PERSIST_DIRECTORY", "db")
target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
from constants import CHROMA_SETTINGS
def main():
# Parse the command line arguments
args = parse_arguments()
embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
retriever = db.as_retriever(search_kwargs={"k": target_source_chunks})
# activate/deactivate the streaming StdOut callback for LLMs
callbacks = [] if args.mute_stream else [StreamingStdOutCallbackHandler()]
llm = Ollama(model=model, callbacks=callbacks)
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents= not args.hide_source)
# Interactive questions and answers
while True:
query = input("\nEnter a query: ")
if query == "exit":
break
if query.strip() == "":
continue
# Get the answer from the chain
start = time.time()
res = qa(query)
answer, docs = res['result'], [] if args.hide_source else res['source_documents']
end = time.time()
# Print the result
print("\n\n> Question:")
print(query)
print(f"\n> Answer (took {round(end - start, 2)} s.):")
print(answer)
# Print the relevant sources used for the answer
for document in docs:
print("\n> " + document.metadata["source"] + ":")
print(document.page_content)
def parse_arguments():
parser = argparse.ArgumentParser(description='privateGPT: Ask questions to your documents without an internet connection, '
'using the power of LLMs.')
parser.add_argument("--hide-source", "-S", action='store_true',
help='Use this flag to disable printing of source documents used for answers.')
parser.add_argument("--mute-stream", "-M",
action='store_true',
help='Use this flag to disable the streaming StdOut callback for LLMs.')
return parser.parse_args()
if __name__ == "__main__":
main()

25
examples/privategpt/pyproject.toml Normal file
View file

@ -0,0 +1,25 @@
[tool.poetry]
name = "privategpt"
version = "0.1.0"
description = ""
authors = ["Ivan Martinez <ivanmartit@gmail.com>"]
license = "Apache Version 2.0"
readme = "README.md"
[tool.poetry.dependencies]
python = "^3.10"
langchain = "0.0.261"
gpt4all = "^1.0.3"
chromadb = "^0.3.26"
PyMuPDF = "^1.22.5"
python-dotenv = "^1.0.0"
unstructured = "^0.8.0"
extract-msg = "^0.41.5"
tabulate = "^0.9.0"
pandoc = "^2.3"
pypandoc = "^1.11"
tqdm = "^4.65.0"
[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"

1753
examples/privategpt/requirements.txt Normal file
View file

File diff suppressed because it is too large Load diff