github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-30 16:01:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

codespell: workflow, config + some (quite a few) typos fixed (#6785)

Browse Source 
Probably the most  boring PR to review ;)

Individual commits might be easier to digest

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
This commit is contained in:
Yaroslav Halchenko
2023-07-12 16:20:08 -04:00
committed by GitHub
parent 931e68692e
commit 0d92a7f357
100 changed files with 213 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/snippets/modules/memory/how_to/vectorstore_retriever_memory.mdx
View File

@@ -37,7 +37,7 @@ retriever = vectorstore.as_retriever(search_kwargs=dict(k=1))
memory = VectorStoreRetrieverMemory(retriever=retriever)
# When added to an agent, the memory object can save pertinent information from conversations or used tools
memory.save_context({"input": "My favorite food is pizza"}, {"output": "thats good to know"})
memory.save_context({"input": "My favorite food is pizza"}, {"output": "that's good to know"})
memory.save_context({"input": "My favorite sport is soccer"}, {"output": "..."})
memory.save_context({"input": "I don't the Celtics"}, {"output": "ok"}) #
```
@@ -98,7 +98,7 @@ conversation_with_summary.predict(input="Hi, my name is Perry, what's up?")
Relevant pieces of previous conversation:
input: My favorite food is pizza
output: thats good to know
output: that's good to know
(You do not need to use these pieces of information if not relevant)
@@ -155,7 +155,7 @@ conversation_with_summary.predict(input="what's my favorite sport?")
```python
# Even though the language model is stateless, since relavent memory is fetched, it can "reason" about the time.
# Even though the language model is stateless, since relevant memory is fetched, it can "reason" about the time.
# Timestamping memories and data is useful in general to let the agent determine temporal relevance
conversation_with_summary.predict(input="Whats my favorite food")
```
@@ -171,7 +171,7 @@ conversation_with_summary.predict(input="Whats my favorite food")
Relevant pieces of previous conversation:
input: My favorite food is pizza
output: thats good to know
output: that's good to know
(You do not need to use these pieces of information if not relevant)