RAGStack Graph Store
Hybrid Graph Store combining vector similarity and edges between chunks.
Usage
- Pre-process your documents to populate
metadatainformation. - Create a Hybrid
GraphStoreand add your LangChainDocuments. - Retrieve documents from the
GraphStore.
Populate Metadata
The Graph Store makes use of the following metadata fields on each Document:
content_id: If assigned, this specifies the unique ID of theDocument. If not assigned, one will be generated. This should be set if you may re-ingest the same document so that it is overwritten rather than being duplicated.links: A set ofLinks indicating how this node should be linked to other nodes.
Hyperlinks
To connect nodes based on hyperlinks, you can use the HtmlLinkExtractor as shown below:
from ragstack_knowledge_store.langchain.extractors import HtmlLinkExtractor
html_link_extractor = HtmlLinkExtractor()
for doc in documents:
doc.metadata["content_id"] = doc.metadata["source"]
# Add link tags from the page_content to the metadata.
# Should be passed the HTML content as a string or BeautifulSoup.
add_links(doc,
html_link_extractor.extract_one(HtmlInput(doc.page_content, doc.metadata["source_url"])))
Store
import cassio
from langchain_openai import OpenAIEmbeddings
from ragstack_knowledge_store import GraphStore
cassio.init(auto=True)
graph_store = GraphStore(embeddings=OpenAIEmbeddings())
# Store the documents
graph_store.add_documents(documents)
Retrieve
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-4o")
# Retrieve and generate using the relevant snippets of the blog.
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
# Depth 0 - don't traverse edges. equivalent to vector-only.
# Depth 1 - vector search plus 1 level of edges
retriever = graph_store.as_retriever(k=4, depth=1)
template = """You are a helpful technical support bot. You should provide complete answers explaining the options the user has available to address their problem. Answer the question based only on the following context:
{context}
Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)
def format_docs(docs):
formatted = "\n\n".join(f"From {doc.metadata['content_id']}: {doc.page_content}" for doc in docs)
return formatted
rag_chain = (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| prompt
| llm
| StrOutputParser()
)
Development
poetry install --with=dev
# Run Tests
poetry run pytest
Metadata
Release files for ragstack-ai-knowledge-store 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ragstack_ai_knowledge_store-0.2.1.tar.gz | 17.0 kB | Without provenance | Details for ragstack_ai_knowledge_store-0.2.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ragstack_ai_knowledge_store-0.2.1-py3-none-any.whl | Python 3 | none | any | Details for ragstack_ai_knowledge_store-0.2.1-py3-none-any.whl |
Total release size: 35.7 kB
Release files / ragstack_ai_knowledge_store-0.2.1.tar.gz
| Download URL | ragstack_ai_knowledge_store-0.2.1.tar.gz |
|---|---|
| Size | 17.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
20424d42978be228feb887a71d76228638765446d1a37a1f6faef109e448fe06
|
|
BLAKE2b-256 checksum How to use checksums |
3ee1da324f5b590aef5ae07b8e7e38ee249101b2bfae6882ba1152c06f8228b2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.4
|
Release files / ragstack_ai_knowledge_store-0.2.1-py3-none-any.whl
| Download URL | ragstack_ai_knowledge_store-0.2.1-py3-none-any.whl |
|---|---|
| Size | 18.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2749c6ab43768e14892dbc1190f2348e9006ad5eb77188e875d704ff811ccc6b
|
|
BLAKE2b-256 checksum How to use checksums |
3bab0afba28f5e9ff962130c8c08bea1ea609be98ec0be3175748911732bd2ca
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.12.4
|
Security for ragstack-ai-knowledge-store 0.2.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.