First commit

.gitignore

@@ -0,0 +1,197 @@
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,python
+
+### Python ###
+# 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+downloaded_docs/*
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,python

README.md

@@ -0,0 +1 @@
+# Search all the docs demo

main.py

@@ -0,0 +1,133 @@
+from typing import List, Tuple
+from pathlib import Path
+import subprocess
+import os
+
+from dotenv import load_dotenv
+from haystack.preview import Pipeline
+from haystack.preview.components.retrievers import MemoryBM25Retriever
+from haystack.preview.components.generators.openai.gpt import GPTGenerator
+from haystack.preview.components.builders.prompt_builder import PromptBuilder
+from haystack.preview.components.preprocessors import (
+    DocumentCleaner,
+    TextDocumentSplitter,
+)
+from haystack.preview.components.writers import DocumentWriter
+from haystack.preview.components.file_converters import TextFileToDocument
+from haystack.preview.document_stores.memory import MemoryDocumentStore
+import streamlit as st
+
+# Load the environment variables, we're going to need it for OpenAI
+load_dotenv()
+
+# This is the list of documentation that we're going to fetch
+DOCUMENTATIONS = [
+    ("docarray", "https://github.com/docarray/docarray.git", "./docs/**/*.md"),
+    ("streamlit", "https://github.com/streamlit/docs.git", "./content/**/*.md"),
+    ("jinja", "https://github.com/pallets/jinja.git", "./docs/**/*.rst"),
+    ("pandas", "https://github.com/pandas-dev/pandas.git", "./docs/source/**/*.rst"),
+    (
+        "elasticsearch",
+        "https://github.com/elastic/elasticsearch.git",
+        "./docs/**/*.asciidoc",
+    ),
+]
+
+
+@st.cache_data(show_spinner=False)
+def fetch(documentations: List[Tuple[str, str, str]]):
+    paths = []
+    for name, url, pattern in documentations:
+        st.write(f"Fetching {name} repository")
+        repo = Path(__file__).parent / "downloaded_docs" / name
+        if not repo.exists():
+            subprocess.run(["git", "clone", "--depth", "1", url, str(repo)], check=True)
+        paths.extend(repo.glob(pattern))
+
+    return paths
+
+
+@st.cache_resource
+def document_store():
+    # We're going to store the processed documents in here
+    return MemoryDocumentStore()
+
+
+@st.cache_resource
+def index_files(files):
+    # We create some components
+    text_converter = TextFileToDocument(progress_bar=False)
+    document_cleaner = DocumentCleaner()
+    document_splitter = TextDocumentSplitter()
+    document_writer = DocumentWriter(
+        document_store=document_store(), policy="overwrite"
+    )
+
+    # And our pipeline
+    indexing_pipeline = Pipeline()
+    indexing_pipeline.add_component("converter", text_converter)
+    indexing_pipeline.add_component("cleaner", document_cleaner)
+    indexing_pipeline.add_component("splitter", document_splitter)
+    indexing_pipeline.add_component("writer", document_writer)
+    indexing_pipeline.connect("converter", "cleaner")
+    indexing_pipeline.connect("cleaner", "splitter")
+    indexing_pipeline.connect("splitter", "writer")
+
+    # And now we clone and save the documentation in our MemoryDocumentStore
+    indexing_pipeline.run({"converter": {"paths": files}})
+
+
+def search(question: str) -> str:
+    retriever = MemoryBM25Retriever(document_store=document_store(), top_k=10)
+
+    template = """Take a deep breath and think then answer given the context
+    Context: {{ documents|map(attribute='text')|join('\n') }}
+    Question: {{ question }}
+    Answer:
+    """
+    prompt_builder = PromptBuilder(template)
+
+    OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "")
+    generator = GPTGenerator(api_key=OPENAI_API_KEY)
+
+    pipe = Pipeline()
+
+    pipe.add_component("docs_retriever", retriever)
+    pipe.add_component("builder", prompt_builder)
+    pipe.add_component("gpt35", generator)
+
+    pipe.connect("docs_retriever.documents", "builder.documents")
+    pipe.connect("builder.prompt", "gpt35.prompt")
+    res = pipe.run(
+        {
+            "docs_retriever": {"query": question},
+            "builder": {"question": question},
+        }
+    )
+    return res["gpt35"]["replies"][0]
+
+
+with st.status(
+    "Downloading documentation files...",
+    expanded=st.session_state.get("expanded", True),
+) as status:
+    files = fetch(DOCUMENTATIONS)
+    status.update(label="Indexing documentation...")
+    index_files(files)
+    status.update(
+        label="Download and indexing complete!", state="complete", expanded=False
+    )
+    st.session_state["expanded"] = False
+
+
+st.header("Documentation finder", divider="rainbow")
+
+
+if question := st.text_input(
+    label="What do you need to know?", placeholder="What is a DataFrame?"
+):
+    with st.spinner("Waiting"):
+        answer = search(question)
+
+    st.balloons()
+    st.markdown(answer)

requirements.txt

@@ -0,0 +1,7 @@
+haystack-ai==0.79.0
+ipython
+more_itertools
+langdetect
+streamlit
+python-dotenv
+watchdog