save change

packages/rag-redis/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 LangChain, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

packages/rag-redis/README.md

@@ -0,0 +1,94 @@
+
+# rag-redis
+
+This template performs RAG using Redis (vector database) and OpenAI (LLM) on financial 10k filings docs for Nike.
+
+It relies on the sentence transformer `all-MiniLM-L6-v2` for embedding chunks of the pdf and user questions.
+
+## Environment Setup
+
+Set the `OPENAI_API_KEY` environment variable to access the [OpenAI](https://platform.openai.com) models:
+
+```bash
+export OPENAI_API_KEY= <YOUR OPENAI API KEY>
+```
+
+Set the following [Redis](https://redis.com/try-free) environment variables:
+
+```bash
+export REDIS_HOST = <YOUR REDIS HOST>
+export REDIS_PORT = <YOUR REDIS PORT>
+export REDIS_USER = <YOUR REDIS USER NAME>
+export REDIS_PASSWORD = <YOUR REDIS PASSWORD>
+```
+
+## Supported Settings
+We use a variety of environment variables to configure this application
+
+| Environment Variable | Description                       | Default Value |
+|----------------------|-----------------------------------|---------------|
+| `DEBUG`            | Enable or disable Langchain debugging logs       | True         |
+| `REDIS_HOST`           | Hostname for the Redis server     | "localhost"   |
+| `REDIS_PORT`           | Port for the Redis server         | 6379          |
+| `REDIS_USER`           | User for the Redis server         | "" |
+| `REDIS_PASSWORD`       | Password for the Redis server     | "" |
+| `REDIS_URL`            | Full URL for connecting to Redis  | `None`, Constructed from user, password, host, and port if not provided |
+| `INDEX_NAME`           | Name of the vector index          | "rag-redis"   |
+
+## Usage
+
+To use this package, you should first have the LangChain CLI and Pydantic installed in a Python virtual environment:
+
+```shell
+pip install -U langchain-cli pydantic==1.10.13
+```
+
+To create a new LangChain project and install this as the only package, you can do:
+
+```shell
+langchain app new my-app --package rag-redis
+```
+
+If you want to add this to an existing project, you can just run:
+```shell
+langchain app add rag-redis
+```
+
+And add the following code snippet to your `app/server.py` file:
+```python
+from rag_redis.chain import chain as rag_redis_chain
+
+add_routes(app, rag_redis_chain, path="/rag-redis")
+```
+
+(Optional) Let's now configure LangSmith.
+LangSmith will help us trace, monitor and debug LangChain applications.
+LangSmith is currently in private beta, you can sign up [here](https://smith.langchain.com/).
+If you don't have access, you can skip this section
+
+
+```shell
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=<your-api-key>
+export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"
+```
+
+If you are inside this directory, then you can spin up a LangServe instance directly by:
+
+```shell
+langchain serve
+```
+
+This will start the FastAPI app with a server is running locally at
+[http://localhost:8000](http://localhost:8000)
+
+We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
+We can access the playground at [http://127.0.0.1:8000/rag-redis/playground](http://127.0.0.1:8000/rag-redis/playground)
+
+We can access the template from code with:
+
+```python
+from langserve.client import RemoteRunnable
+
+runnable = RemoteRunnable("http://localhost:8000/rag-redis")
+```

packages/rag-redis/ingest.py

@@ -0,0 +1,43 @@
+import os
+
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Redis
+from rag_redis.config import INDEX_NAME, INDEX_SCHEMA, REDIS_URL
+from langchain.embeddings import OpenAIEmbeddings
+
+
+def ingest_documents():
+    """
+    Ingest PDF to Redis from the data/ directory that
+    """
+    # Load list of pdfs
+    data_path = "data/"
+    docs = [os.path.join(data_path, file) for file in os.listdir(data_path)]
+
+    print("Parsing docs", docs)
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1500, chunk_overlap=100, add_start_index=True
+    )
+    chunks = []
+    for doc in docs:
+        loader = UnstructuredFileLoader(doc, mode="single", strategy="fast")
+        chunks.extend(loader.load_and_split(text_splitter))
+
+    print("Chunk 0:", chunks[0])
+
+    print("Done preprocessing. Created", len(chunks), "chunks of the original pdf")
+
+    rds = Redis.from_texts(
+        texts=[chunk.page_content for chunk in chunks],
+        metadatas=[chunk.metadata for chunk in chunks],
+        embedding=OpenAIEmbeddings(),
+        index_name=INDEX_NAME,
+        redis_url=REDIS_URL,
+    )
+    rds.write_schema(INDEX_SCHEMA)
+
+
+if __name__ == "__main__":
+    ingest_documents()

packages/rag-redis/pyproject.toml

@@ -0,0 +1,53 @@
+[tool.poetry]
+name = "rag-redis"
+version = "0.0.1"
+description = "Run a RAG app backed by OpenAI, HuggingFace, and Redis as a vector database"
+authors = [
+    "Tyler Hutcherson <tyler.hutcherson@redis.com>",
+    "Sam Partee <sam.partee@redis.com>",
+]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.9,<3.13"
+langchain = ">=0.0.325"
+fastapi = "^0.104.0"
+sse-starlette = "^1.6.5"
+openai = "<2"
+sentence-transformers = "2.2.2"
+redis = "5.0.1"
+tiktoken = "0.5.1"
+pdf2image = "1.16.3"
+
+[tool.poetry.dependencies.unstructured]
+version = "^0.10.27"
+extras = [
+    "pdf",
+]
+
+[tool.poetry.group.dev.dependencies]
+poethepoet = "^0.24.1"
+langchain-cli = ">=0.0.15"
+
+[tool.langserve]
+export_module = "rag_redis.chain"
+export_attr = "chain"
+
+[tool.templates-hub]
+use-case = "rag"
+author = "Redis"
+integrations = ["OpenAI", "Redis", "HuggingFace"]
+tags = ["vectordbs"]
+
+[tool.poe.tasks.start]
+cmd = "uvicorn langchain_cli.dev_scripts:create_demo_server --reload --port $port --host $host"
+args = [
+    { name = "port", help = "port to run on", default = "8000" },
+    { name = "host", help = "host to run on", default = "127.0.0.1" },
+]
+
+[build-system]
+requires = [
+    "poetry-core",
+]
+build-backend = "poetry.core.masonry.api"

packages/rag-redis/rag_redis.ipynb

@@ -0,0 +1,88 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "681a5d1e",
+   "metadata": {},
+   "source": [
+    "## Connect to RAG App\n",
+    "\n",
+    "Assuming you are already running this server:\n",
+    "```bash\n",
+    "langserve start\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "d774be2a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nike's revenue in 2023 was $51.2 billion. \n",
+      "\n",
+      "Source: 'data/nke-10k-2023.pdf', Start Index: '146100'\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langserve.client import RemoteRunnable\n",
+    "\n",
+    "rag_redis = RemoteRunnable(\"http://localhost:8000/rag-redis\")\n",
+    "\n",
+    "print(rag_redis.invoke(\"What was Nike's revenue in 2023?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "07ae0005",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "As of May 31, 2023, Nike had approximately 83,700 employees worldwide. This information can be found in the first piece of context provided. (source: data/nke-10k-2023.pdf, start_index: 32532)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(rag_redis.invoke(\"How many employees work at Nike?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4a6b9f00",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

packages/rag-redis/rag_redis/__init__.py

@@ -0,0 +1,3 @@
+from dotenv import load_dotenv
+
+load_dotenv()

packages/rag-redis/rag_redis/chain.py

@@ -0,0 +1,65 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.prompts import ChatPromptTemplate
+from langchain.pydantic_v1 import BaseModel
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+from langchain.vectorstores import Redis
+
+from rag_redis.config import (
+    INDEX_NAME,
+    INDEX_SCHEMA,
+    REDIS_URL,
+)
+
+
+# Make this look better in the docs.
+class Question(BaseModel):
+    __root__: str
+
+
+# Init Embeddings
+embedder = OpenAIEmbeddings()
+
+# Connect to pre-loaded vectorstore
+# run the ingest.py script to populate this
+vectorstore = Redis.from_existing_index(
+    embedding=embedder, index_name=INDEX_NAME, schema=INDEX_SCHEMA, redis_url=REDIS_URL
+)
+retriever = vectorstore.as_retriever(search_type="mmr")
+
+
+# Define our prompt
+template = """
+Use the following pieces of context from ApartmentManagementDocument and
+ProjectManagementDocument to answer the question. Do not make up an answer 
+if there is no context provided to help answer it. Answer the question in
+the same language as the question is asked.
+
+Context:
+---------
+{context}
+
+---------
+Question: {question}
+---------
+
+Answer:
+"""
+
+
+prompt = ChatPromptTemplate.from_template(template)
+
+# Cache
+from langchain.cache import InMemoryCache
+from langchain.globals import set_llm_cache
+set_llm_cache(InMemoryCache())
+
+# RAG Chain
+model = ChatOpenAI(model_name="gpt-3.5-turbo")
+chain = (
+    RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
+    | prompt
+    | model
+    | StrOutputParser()
+).with_types(input_type=Question)

packages/rag-redis/rag_redis/config.py

@@ -0,0 +1,76 @@
+import os
+
+
+def get_boolean_env_var(var_name, default_value=False):
+    """Retrieve the boolean value of an environment variable.
+
+    Args:
+    var_name (str): The name of the environment variable to retrieve.
+    default_value (bool): The default value to return if the variable
+    is not found.
+
+    Returns:
+    bool: The value of the environment variable, interpreted as a boolean.
+    """
+    true_values = {"true", "1", "t", "y", "yes"}
+    false_values = {"false", "0", "f", "n", "no"}
+
+    # Retrieve the environment variable's value
+    value = os.getenv(var_name, "").lower()
+
+    # Decide the boolean value based on the content of the string
+    if value in true_values:
+        return True
+    elif value in false_values:
+        return False
+    else:
+        return default_value
+
+
+# Check for openai API key
+if "OPENAI_API_KEY" not in os.environ:
+    raise Exception("Must provide an OPENAI_API_KEY as an env var.")
+
+
+# Whether or not to enable langchain debugging
+DEBUG = get_boolean_env_var("DEBUG", False)
+# Set DEBUG env var to "true" if you wish to enable LC debugging module
+if DEBUG:
+    import langchain
+
+    langchain.debug = True
+
+
+# Redis Connection Information
+REDIS_HOST = os.getenv("REDIS_HOST", "localhost")
+REDIS_PORT = int(os.getenv("REDIS_PORT", 6379))
+
+
+def format_redis_conn_from_env():
+    redis_url = os.getenv("REDIS_URL", None)
+    if redis_url:
+        return redis_url
+    else:
+        using_ssl = get_boolean_env_var("REDIS_SSL", False)
+        start = "rediss://" if using_ssl else "redis://"
+
+        # if using RBAC
+        password = os.getenv("REDIS_PASSWORD", None)
+        username = os.getenv("REDIS_USERNAME", "default")
+        if password is not None:
+            start += f"{username}:{password}@"
+
+        return start + f"{REDIS_HOST}:{REDIS_PORT}"
+
+
+REDIS_URL = format_redis_conn_from_env()
+
+# Vector Index Configuration
+INDEX_NAME = os.getenv("INDEX_NAME", "rag-redis")
+
+# Embedding model
+
+current_file_path = os.path.abspath(__file__)
+parent_dir = os.path.dirname(current_file_path)
+schema_path = os.path.join(parent_dir, "schema.yml")
+INDEX_SCHEMA = schema_path

packages/rag-redis/rag_redis/schema.yml

@@ -0,0 +1,23 @@
+numeric:
+- name: start_index
+  no_index: false
+  sortable: false
+text:
+- name: source
+  no_index: false
+  no_stem: false
+  sortable: false
+  weight: 1
+  withsuffixtrie: false
+- name: content
+  no_index: false
+  no_stem: false
+  sortable: false
+  weight: 1
+  withsuffixtrie: false
+vector:
+- algorithm: FLAT
+  datatype: FLOAT32
+  dims: 1536
+  distance_metric: COSINE
+  name: content_vector