github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-01 10:54:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

cleanup getting started (#15450)

Browse Source
This commit is contained in:
Harrison Chase 2024-01-02 22:26:35 -08:00 committed by GitHub
parent 2bbee894bb
commit 51dcb89a72
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/docs/get_started/quickstart.mdx
View File

@ -143,6 +143,10 @@ chain = prompt | llm
We can now invoke it and ask the same question. It still won't know the answer, but it should respond in a more proper tone for a technical writer! We can now invoke it and ask the same question. It still won't know the answer, but it should respond in a more proper tone for a technical writer!
```python
chain.invoke({"input": "how can langsmith help with testing?"})
```
The output of a ChatModel (and therefore, of this chain) is a message. However, it's often much more convenient to work with strings. Let's add a simple output parser to convert the chat message to a string. The output of a ChatModel (and therefore, of this chain) is a message. However, it's often much more convenient to work with strings. Let's add a simple output parser to convert the chat message to a string.
```python ```python
@ -204,7 +208,7 @@ embeddings = OpenAIEmbeddings()
``` ```
</TabItem> </TabItem>
<TabItem value="local" label="Ollama"> <TabItem value="local" label="Local">
Make sure you have Ollama running (same set up as with the LLM). Make sure you have Ollama running (same set up as with the LLM).
@ -284,7 +288,7 @@ We can now invoke this chain. This returns a dictionary - the response from the
response = retrieval_chain.invoke({"input": "how can langsmith help with testing?"}) response = retrieval_chain.invoke({"input": "how can langsmith help with testing?"})
print(response["answer"]) print(response["answer"])
// LangSmith offers several features that can help with testing:... # LangSmith offers several features that can help with testing:...
``` ```
This answer should be much more accurate! This answer should be much more accurate!
@ -326,7 +330,7 @@ We can test this out by passing in an instance where the user is asking a follow
from langchain_core.messages import HumanMessage, AIMessage from langchain_core.messages import HumanMessage, AIMessage
chat_history = [HumanMessage(content="Can LangSmith help test my LLM applications?"), AIMessage(content="Yes!")] chat_history = [HumanMessage(content="Can LangSmith help test my LLM applications?"), AIMessage(content="Yes!")]
retrieval_chain.invoke({ retriever_chain.invoke({
"chat_history": chat_history, "chat_history": chat_history,
"input": "Tell me how" "input": "Tell me how"
}) })