github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-26 16:43:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor edits to QA docs (#7507)

Browse Source 
Small clean-ups
This commit is contained in:
Lance Martin 2023-07-10 22:15:05 -07:00 committed by GitHub
parent 5171c3bcca
commit 4a94f56258
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docs/extras/use_cases/question_answering/index.mdx
View File

@ -65,7 +65,7 @@ index.query(question)
Of course, some users do not wnat this level of abstraction. Of course, some users do not want this level of abstraction.
Below, we will discuss each stage in more detail. Below, we will discuss each stage in more detail.
@ -113,13 +113,13 @@ Here are the three pieces together:
#### 1.2.1 Integrations #### 1.2.1 Integrations
`Data Loaders` `Document Loaders`
* Browse the > 120 data loader integrations [here](https://integrations.langchain.com/). * Browse the > 120 data loader integrations [here](https://integrations.langchain.com/).
* See further documentation on loaders [here](https://python.langchain.com/docs/modules/data_connection/document_loaders/). * See further documentation on loaders [here](https://python.langchain.com/docs/modules/data_connection/document_loaders/).
`Data Transformers` `Document Transformers`
* All can ingest loaded `Documents` and process them (e.g., split). * All can ingest loaded `Documents` and process them (e.g., split).
@ -133,7 +133,7 @@ Here are the three pieces together:
#### 1.2.2 Retaining metadata #### 1.2.2 Retaining metadata
`Context-aware splitters` keep the location or "context" of each split in the origional `Document`: `Context-aware splitters` keep the location ("context") of each split in the origional `Document`:
* [Markdown files](https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA) * [Markdown files](https://python.langchain.com/docs/use_cases/question_answering/document-context-aware-QA)
* [Code (py or js)](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/source_code) * [Code (py or js)](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/source_code)
@ -171,7 +171,7 @@ For example, SVMs (see thread [here](https://twitter.com/karpathy/status/1647025
LangChain [has many retrievers](https://python.langchain.com/docs/modules/data_connection/retrievers/) including, but not limited to, vectorstores. LangChain [has many retrievers](https://python.langchain.com/docs/modules/data_connection/retrievers/) including, but not limited to, vectorstores.
All retrievers implement some common, useful methods, such as `get_relevant_documents()`. All retrievers implement some common methods, such as `get_relevant_documents()`.
```python ```python
@ -222,7 +222,7 @@ len(unique_docs)
### 3.1 Getting started ### 3.1 Getting started
Distill the retried documents into an answer using an LLM (e.g., `gpt-3.5-turbo`) with `RetrievalQA` chain. Distill the retrieved documents into an answer using an LLM (e.g., `gpt-3.5-turbo`) with `RetrievalQA` chain.
```python ```python
@ -247,9 +247,9 @@ qa_chain({"query": question})
`LLMs` `LLMs`
* Browse the > 55 model integrations [here](https://integrations.langchain.com/). * Browse the > 55 LLM integrations [here](https://integrations.langchain.com/).
* See further documentation on vectorstores [here](https://python.langchain.com/docs/modules/model_io/models/). * See further documentation on LLMs [here](https://python.langchain.com/docs/modules/model_io/models/).
#### 3.2.2 Running LLMs locally #### 3.2.2 Running LLMs locally
@ -355,7 +355,7 @@ result
#### 3.2.5 Customizing how pass retrieved documents to the LLM #### 3.2.5 Customizing retrieved docs in the LLM prompt
Retrieved documents can be fed to an LLM for answer distillation in a few different ways. Retrieved documents can be fed to an LLM for answer distillation in a few different ways.