Langchain: Fix quickstart doc code not working (#15352)

The quickstart doc is missing a few but very simple things that without
them, the code does not work. This PR fixes that by
- Adding commands to install `tiktoken` and `langchainhub`
- Adds a comma between 2 parameters for one of the methods
pull/14852/head
Ahmed Hathout 8 months ago committed by GitHub
parent a7f0b65d26
commit d0a1c71eda
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -223,6 +223,7 @@ First we need to install the required packages for that:
```shell
pip install docarray
pip install tiktoken
```
Then we can build our index:
@ -313,7 +314,7 @@ from langchain_core.prompts import MessagesPlaceholder
prompt = ChatPromptTemplate.from_messages([
MessagesPlaceholder(variable_name="chat_history"),
("user", "{input}")
("user", "{input}"),
("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
])
retriever_chain = create_history_aware_retriever(llm, retriever, prompt)
@ -403,6 +404,13 @@ tools = [retriever_tool, search]
Now that we have the tools, we can create an agent to use them. We will go over this pretty quickly - for a deeper dive into what exactly is going on, check out the [Agent's Getting Started documentation](/docs/modules/agents)
Install langchain hub first
```bash
pip install langchainhub
```
Now we can use it to get a predefined prompt
```python
from langchain.chat_models import ChatOpenAI
from langchain import hub

Loading…
Cancel
Save