github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-07 05:52:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/as retriever docstring (#8840)

Browse Source 
Co-authored-by: Bytestorm <31070777+Bytestorm5@users.noreply.github.com>
This commit is contained in:
Harrison Chase
2023-08-06 17:00:57 -07:00
committed by GitHub
parent bd4865b6fe
commit 0adc282d70
3 changed files with 90 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/snippets/modules/chains/popular/vector_db_qa.mdx
View File

@@ -117,3 +117,38 @@ qa.run(query)
```
</CodeOutputBlock>
## Vectorstore Retriever Options
You can adjust how documents are retrieved from your vectorstore depending on the specific task.
There are two main ways to retrieve documents relevant to a query- Similarity Search and Max Marginal Relevance Search (MMR Search). Similarity Search is the default, but you can use MMR by adding the `search_type` parameter:
```python
docsearch.as_retriever(search_type="mmr")
```
You can also modify the search by passing specific search arguments through the retriever to the search function, using the `search_kwargs` keyword argument.
- `k` defines how many documents are returned; defaults to 4.
- `score_threshold` allows you to set a minimum relevance for documents returned by the retriever, if you are using the "similarity_score_threshold" search type.
- `fetch_k` determines the amount of documents to pass to the MMR algorithm; defaults to 20.
- `lambda_mult` controls the diversity of results returned by the MMR algorithm, with 1 being minimum diversity and 0 being maximum. Defaults to 0.5.
- `filter` allows you to define a filter on what documents should be retrieved, based on the documents' metadata. This has no effect if the Vectorstore doesn't store any metadata.
Some examples for how these parameters can be used:
```python
# Retrieve more documents with higher diversity- useful if your dataset has many similar documents
docsearch.as_retriever(search_type="mmr", search_kwargs={'k': 6, 'lambda_mult': 0.25})
# Fetch more documents for the MMR algorithm to consider, but only return the top 5
docsearch.as_retriever(search_type="mmr", search_kwargs={'k': 5, 'fetch_k': 50})
# Only retrieve documents that have a relevance score above a certain threshold
docsearch.as_retriever(search_type="similarity_score_threshold", search_kwargs={'score_threshold': 0.8})
# Only get the single most similar document from the dataset
docsearch.as_retriever(search_kwargs={'k': 1})
# Use a filter to only retrieve documents from a specific paper
docsearch.as_retriever(search_kwargs={'filter': {'paper_title':'GPT-4 Technical Report'}})
```

2
docs/snippets/modules/chains/popular/vector_db_qa_with_sources.mdx
View File

@@ -3,7 +3,7 @@ Additionally, we can return the source documents used to answer the question by
```python
qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever(), return_source_documents=True)
qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever(search_type="mmr", search_kwargs={'fetch_k': 30}), return_source_documents=True)
```