Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

docs[minor]: Add chat model tabs to docs pages (#19589)

Browse Source
pull/18603/head^2
Brace Sproul 3 months ago committed by GitHub
parent bd02b83acd
commit ce0a588ae6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
9 changed files with 1503 additions and 1568 deletions
Show Stats Download Patch File Download Diff File

44
docs/docs/expression_language/get_started.ipynb
Unescape Escape View File

@ -40,6 +40,33 @@
"%pip install --upgrade --quiet langchain-core langchain-community langchain-openai"
]
},
{
"cell_type": "markdown",
"id": "c3d54f72",
"metadata": {},
"source": [
"```{=mdx}\n",
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
"\n",
"<ChatModelTabs openaiParams={`model=\"gpt-4\"`} />\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f9eed8e8",
"metadata": {},
"outputs": [],
"source": [
"# | output: false\n",
"# | echo: false\n",
"\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"model = ChatOpenAI(model=\"gpt-4\")"
]
},
{
"cell_type": "code",
"execution_count": 1,
@ -60,10 +87,8 @@
"source": [
"from langchain_core.output_parsers import StrOutputParser\n",
"from langchain_core.prompts import ChatPromptTemplate\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"prompt = ChatPromptTemplate.from_template(\"tell me a short joke about {topic}\")\n",
"model = ChatOpenAI(model=\"gpt-4\")\n",
"output_parser = StrOutputParser()\n",
"\n",
"chain = prompt | model | output_parser\n",
@ -324,6 +349,16 @@
"For our next example, we want to run a retrieval-augmented generation chain to add some context when responding to questions."
]
},
{
"cell_type": "markdown",
"id": "b8fe8eb4",
"metadata": {},
"source": [
"```{=mdx}\n",
"<ChatModelTabs />\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
@ -338,7 +373,7 @@
"from langchain_core.output_parsers import StrOutputParser\n",
"from langchain_core.prompts import ChatPromptTemplate\n",
"from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
"from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
"from langchain_openai import OpenAIEmbeddings\n",
"\n",
"vectorstore = DocArrayInMemorySearch.from_texts(\n",
" [\"harrison worked at kensho\", \"bears like to eat honey\"],\n",
@ -352,7 +387,6 @@
"Question: {question}\n",
"\"\"\"\n",
"prompt = ChatPromptTemplate.from_template(template)\n",
"model = ChatOpenAI()\n",
"output_parser = StrOutputParser()\n",
"\n",
"setup_and_retrieval = RunnableParallel(\n",
@ -495,7 +529,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.11.0"
}
},
"nbformat": 4,

2349
docs/docs/expression_language/why.ipynb
View File

File diff suppressed because it is too large Load Diff

31
docs/docs/modules/model_io/chat/chat_model_caching.ipynb
Unescape Escape View File

@ -12,19 +12,44 @@
"It can speed up your application by reducing the number of API calls you make to the LLM provider.\n"
]
},
{
"cell_type": "markdown",
"id": "289b31de",
"metadata": {},
"source": [
"```{=mdx}\n",
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
"\n",
"<ChatModelTabs customVarName=\"llm\" />\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "5472a032",
"execution_count": null,
"id": "c6641f37",
"metadata": {},
"outputs": [],
"source": [
"from langchain.globals import set_llm_cache\n",
"# | output: false\n",
"# | echo: false\n",
"\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"llm = ChatOpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "5472a032",
"metadata": {},
"outputs": [],
"source": [
"# <!-- ruff: noqa: F821 -->\n",
"from langchain.globals import set_llm_cache"
]
},
{
"cell_type": "markdown",
"id": "357b89a8",

300
docs/docs/modules/model_io/chat/function_calling.mdx
Unescape Escape View File

@ -18,13 +18,13 @@ structured outputs from models more generally.
LangChain comes with a number of utilities to make function-calling
easy. Namely, it comes with:
- simple syntax for binding functions to models
- converters for formatting various types of objects to the expected
function schemas
- output parsers for extracting the function invocations from API
responses
- chains for getting structured outputs from a model, built on top of
function calling
- simple syntax for binding functions to models
- converters for formatting various types of objects to the expected
function schemas
- output parsers for extracting the function invocations from API
responses
- chains for getting structured outputs from a model, built on top of
function calling
We’ll focus here on the first two points. For a detailed guide on output
parsing check out the [OpenAI Tools output
@ -38,7 +38,6 @@ Before getting started make sure you have `langchain-core` installed.
%pip install -qU langchain-core langchain-openai
```
```python
import getpass
import os
@ -64,38 +63,26 @@ class Multiply(BaseModel):
b: int = Field(..., description="Second integer")
```
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
<Tabs>
<TabItem value="openai" label="OpenAI" default>
Set up dependencies and API keys:
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";
```python
%pip install -qU langchain-openai
```
import ChatModelTabs from "@theme/ChatModelTabs";
<ChatModelTabs
customVarName="llm"
fireworksParams={`model="accounts/fireworks/models/firefunction-v1", temperature=0`}
/>
```python
os.environ["OPENAI_API_KEY"] = getpass.getpass()
```
We can use the `ChatOpenAI.bind_tools()` method to handle converting
`Multiply` to an OpenAI function and binding it to the model (i.e.,
We can use the `bind_tools()` method to handle converting
`Multiply` to a "function" and binding it to the model (i.e.,
passing it in each time the model is invoked).
```python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
llm_with_tools = llm.bind_tools([Multiply])
llm_with_tools.invoke("what's 3 * 12")
```
``` text
```text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Q8ZQ97Qrj5zalugSkYMGV1Uo', 'function': {'arguments': '{"a":3,"b":12}', 'name': 'Multiply'}, 'type': 'function'}]})
```
@ -109,7 +96,7 @@ tool_chain = llm_with_tools | JsonOutputToolsParser()
tool_chain.invoke("what's 3 * 12")
```
``` text
```text
[{'type': 'Multiply', 'args': {'a': 3, 'b': 12}}]
```
@ -122,57 +109,10 @@ tool_chain = llm_with_tools | PydanticToolsParser(tools=[Multiply])
tool_chain.invoke("what's 3 * 12")
```
``` text
```text
[Multiply(a=3, b=12)]
```
If we wanted to force that a tool is used (and that it is used only
once), we can set the `tool_choice` argument:
```python
llm_with_multiply = llm.bind_tools([Multiply], tool_choice="Multiply")
llm_with_multiply.invoke(
"make up some numbers if you really want but I'm not forcing you"
)
```
``` text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_f3DApOzb60iYjTfOhVFhDRMI', 'function': {'arguments': '{"a":5,"b":10}', 'name': 'Multiply'}, 'type': 'function'}]})
```
For more see the [ChatOpenAI API
reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html#langchain_openai.chat_models.base.ChatOpenAI.bind_tools).
</TabItem>
<TabItem value="fireworks" label="Fireworks">
Install dependencies and set API keys:
```python
%pip install -qU langchain-fireworks
```
```python
os.environ["FIREWORKS_API_KEY"] = getpass.getpass()
```
We can use the `ChatFireworks.bind_tools()` method to handle converting
`Multiply` to a valid function schema and binding it to the model (i.e.,
passing it in each time the model is invoked).
```python
from langchain_fireworks import ChatFireworks
llm = ChatFireworks(model="accounts/fireworks/models/firefunction-v1", temperature=0)
llm_with_tools = llm.bind_tools([Multiply])
llm_with_tools.invoke("what's 3 * 12")
```
``` text
AIMessage(content='Three multiplied by twelve is 36.')
```
If our model isn’t using the tool, as is the case here, we can force
tool usage by specifying `tool_choice="any"` or by specifying the name
of the specific tool we want used:
@ -182,175 +122,12 @@ llm_with_tools = llm.bind_tools([Multiply], tool_choice="Multiply")
llm_with_tools.invoke("what's 3 * 12")
```
``` text
```text
AIMessage(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_qIP2bJugb67LGvc6Zhwkvfqc', 'type': 'function', 'function': {'name': 'Multiply', 'arguments': '{"a": 3, "b": 12}'}}]})
```
We can add a tool parser to extract the tool calls from the generated
message to JSON:
```python
from langchain_core.output_parsers.openai_tools import JsonOutputToolsParser
tool_chain = llm_with_tools | JsonOutputToolsParser()
tool_chain.invoke("what's 3 * 12")
```
``` text
[{'type': 'Multiply', 'args': {'a': 3, 'b': 12}}]
```
Or back to the original Pydantic class:
```python
from langchain_core.output_parsers.openai_tools import PydanticToolsParser
tool_chain = llm_with_tools | PydanticToolsParser(tools=[Multiply])
tool_chain.invoke("what's 3 * 12")
```
``` text
[Multiply(a=3, b=12)]
```
For more see the [ChatFireworks](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html#langchain_fireworks.chat_models.ChatFireworks.bind_tools) reference.
</TabItem>
<TabItem value="mistral" label="Mistral">
Install dependencies and set API keys:
```python
%pip install -qU langchain-mistralai
```
```python
os.environ["MISTRAL_API_KEY"] = getpass.getpass()
```
We can use the `ChatMistralAI.bind_tools()` method to handle converting
`Multiply` to a valid function schema and binding it to the model (i.e.,
passing it in each time the model is invoked).
```python
from langchain_mistralai import ChatMistralAI
llm = ChatMistralAI(model="mistral-large-latest", temperature=0)
llm_with_tools = llm.bind_tools([Multiply])
llm_with_tools.invoke("what's 3 * 12")
```
``` text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'null', 'type': <ToolType.function: 'function'>, 'function': {'name': 'Multiply', 'arguments': '{"a": 3, "b": 12}'}}]})
```
We can add a tool parser to extract the tool calls from the generated
message to JSON:
```python
from langchain_core.output_parsers.openai_tools import JsonOutputToolsParser
tool_chain = llm_with_tools | JsonOutputToolsParser()
tool_chain.invoke("what's 3 * 12")
```
``` text
[{'type': 'Multiply', 'args': {'a': 3, 'b': 12}}]
```
Or back to the original Pydantic class:
```python
from langchain_core.output_parsers.openai_tools import PydanticToolsParser
tool_chain = llm_with_tools | PydanticToolsParser(tools=[Multiply])
tool_chain.invoke("what's 3 * 12")
```
``` text
[Multiply(a=3, b=12)]
```
We can force tool usage by specifying `tool_choice="any"`:
```python
llm_with_tools = llm.bind_tools([Multiply], tool_choice="any")
llm_with_tools.invoke("I don't even want you to use the tool")
```
``` text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'null', 'type': <ToolType.function: 'function'>, 'function': {'name': 'Multiply', 'arguments': '{"a": 5, "b": 7}'}}]})
```
For more see the [ChatMistralAI API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html#langchain_mistralai.chat_models.ChatMistralAI).
</TabItem>
<TabItem value="together" label="Together">
Since TogetherAI is a drop-in replacement for OpenAI, we can just use
the OpenAI integration.
Install dependencies and set API keys:
```python
%pip install -qU langchain-openai
```
```python
os.environ["TOGETHER_API_KEY"] = getpass.getpass()
```
We can use the `ChatOpenAI.bind_tools()` method to handle converting
`Multiply` to a valid function schema and binding it to the model (i.e.,
passing it in each time the model is invoked).
```python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
base_url="https://api.together.xyz/v1",
api_key=os.environ["TOGETHER_API_KEY"],
model="mistralai/Mixtral-8x7B-Instruct-v0.1",
)
llm_with_tools = llm.bind_tools([Multiply])
llm_with_tools.invoke("what's 3 * 12")
```
``` text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_4tc61dp0478zafqe33hfriee', 'function': {'arguments': '{"a":3,"b":12}', 'name': 'Multiply'}, 'type': 'function'}]})
```
We can add a tool parser to extract the tool calls from the generated
message to JSON:
```python
from langchain_core.output_parsers.openai_tools import JsonOutputToolsParser
tool_chain = llm_with_tools | JsonOutputToolsParser()
tool_chain.invoke("what's 3 * 12")
```
``` text
[{'type': 'Multiply', 'args': {'a': 3, 'b': 12}}]
```
Or back to the original Pydantic class:
```python
from langchain_core.output_parsers.openai_tools import PydanticToolsParser
tool_chain = llm_with_tools | PydanticToolsParser(tools=[Multiply])
tool_chain.invoke("what's 3 * 12")
```
``` text
[Multiply(a=3, b=12)]
```
If we wanted to force that a tool is used (and that it is used only
once), we can set the `tool_choice` argument:
once), we can set the `tool_choice` argument to the name of the tool:
```python
llm_with_multiply = llm.bind_tools([Multiply], tool_choice="Multiply")
@ -359,16 +136,13 @@ llm_with_multiply.invoke(
)
```
``` text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6k6d0gr3jhqil2kqf7sgeusl', 'function': {'arguments': '{"a":5,"b":7}', 'name': 'Multiply'}, 'type': 'function'}]})
```text
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_f3DApOzb60iYjTfOhVFhDRMI', 'function': {'arguments': '{"a":5,"b":10}', 'name': 'Multiply'}, 'type': 'function'}]})
```
For more see the [ChatOpenAI API
reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html#langchain_openai.chat_models.base.ChatOpenAI.bind_tools).
</TabItem>
</Tabs>
## Defining functions schemas
In case you need to access function schemas directly, LangChain has a built-in converter that can turn
@ -395,7 +169,7 @@ def multiply(a: int, b: int) -> int:
print(json.dumps(convert_to_openai_tool(multiply), indent=2))
```
``` text
```text
{
"type": "function",
"function": {
@ -438,7 +212,7 @@ class multiply(BaseModel):
print(json.dumps(convert_to_openai_tool(multiply), indent=2))
```
``` text
```text
{
"type": "function",
"function": {
@ -493,7 +267,7 @@ class Multiply(BaseTool):
print(json.dumps(convert_to_openai_tool(Multiply()), indent=2))
```
``` text
```text
{
"type": "function",
"function": {
@ -522,14 +296,14 @@ print(json.dumps(convert_to_openai_tool(Multiply()), indent=2))
## Next steps
- **Output parsing**: See [OpenAI Tools output
parsers](../../../../docs/modules/model_io/output_parsers/types/openai_tools)
and [OpenAI Functions output
parsers](../../../../docs/modules/model_io/output_parsers/types/openai_functions)
to learn about extracting the function calling API responses into
various formats.
- **Structured output chains**: [Some models have constructors](../../../../docs/guides/structured_output) that
handle creating a structured output chain for you.
- **Tool use**: See how to construct chains and agents that actually
call the invoked tools in [these
guides](../../../../docs/use_cases/tool_use/).
- **Output parsing**: See [OpenAI Tools output
parsers](../../../../docs/modules/model_io/output_parsers/types/openai_tools)
and [OpenAI Functions output
parsers](../../../../docs/modules/model_io/output_parsers/types/openai_functions)
to learn about extracting the function calling API responses into
various formats.
- **Structured output chains**: [Some models have constructors](../../../../docs/guides/structured_output) that
handle creating a structured output chain for you.
- **Tool use**: See how to construct chains and agents that actually
call the invoked tools in [these
guides](../../../../docs/use_cases/tool_use/).

60
docs/docs/modules/model_io/chat/quick_start.ipynb
Unescape Escape View File

@ -22,32 +22,19 @@
"While chat models use language models under the hood, the interface they use is a bit different.\n",
"Rather than using a \"text in, text out\" API, they use an interface where \"chat messages\" are the inputs and outputs.\n",
"\n",
"## Setup\n",
"\n",
"For this example we'll need to install the OpenAI partner package:\n",
"\n",
"```bash\n",
"pip install langchain-openai\n",
"```\n",
"\n",
"Accessing the API requires an API key, which you can get by creating an account and heading [here](https://platform.openai.com/account/api-keys). Once we have a key we'll want to set it as an environment variable by running:\n",
"\n",
"```bash\n",
"export OPENAI_API_KEY=\"...\"\n",
"```\n",
"If you'd prefer not to set an environment variable you can pass the key in directly via the `openai_api_key` named parameter when initiating the OpenAI LLM class:\n"
"## Setup\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"cell_type": "markdown",
"id": "e230abb2-bc84-438b-b9ff-dd124acb1375",
"metadata": {},
"outputs": [],
"source": [
"from langchain_openai import ChatOpenAI\n",
"```{=mdx}\n",
"import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
"\n",
"chat = ChatOpenAI(openai_api_key=\"...\")"
"<ChatModelTabs customVarName=\"chat\" />\n",
"```"
]
},
{
@ -55,19 +42,25 @@
"id": "609bbd5c-e5a1-4166-89e1-d6c52054860d",
"metadata": {},
"source": [
"Otherwise you can initialize without any params:"
"If you'd prefer not to set an environment variable you can pass the key in directly via the api key arg named parameter when initiating the chat model class:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"cell_type": "markdown",
"id": "3d9dbf70-2397-4d6b-87ec-3e6d4699f3df",
"metadata": {},
"outputs": [],
"source": [
"from langchain_openai import ChatOpenAI\n",
"\n",
"chat = ChatOpenAI()"
"```{=mdx}\n",
"<ChatModelTabs\n",
" openaiParams={`model=\"gpt-3.5-turbo-0125\", openai_api_key=\"...\"`}\n",
" anthropicParams={`model=\"claude-3-sonnet-20240229\", anthropic_api_key=\"...\"`}\n",
" fireworksParams={`model=\"accounts/fireworks/models/mixtral-8x7b-instruct\", fireworks_api_key=\"...\"`}\n",
" mistralParams={`model=\"mistral-large-latest\", mistral_api_key=\"...\"`}\n",
" googleParams={`model=\"gemini-pro\", google_api_key=\"...\"`}\n",
" togetherParams={`, together_api_key=\"...\"`}\n",
" customVarName=\"chat\"\n",
"/>\n",
"```"
]
},
{
@ -108,6 +101,21 @@
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "570dae71",
"metadata": {},
"outputs": [],
"source": [
"# | output: false\n",
"# | echo: false\n",
"\n",
"from langchain_openai import ChatOpenAI\n",
"\n",
"chat = ChatOpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 11,

2
docs/docs/use_cases/question_answering/chat_history.ipynb
Unescape Escape View File

@ -516,7 +516,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
"version": "3.11.0"
}
},
"nbformat": 4,

192
docs/docs/use_cases/question_answering/quickstart.mdx
Unescape Escape View File

@ -24,7 +24,7 @@ introduction](../../../docs/use_cases/question_answering/), which has
two main components:
**Indexing**: a pipeline for ingesting data from a source and indexing
it. *This usually happens offline.*
it. _This usually happens offline._
**Retrieval and generation**: the actual RAG chain, which takes the user
query at run time and retrieves the relevant data from the index, then
@ -77,7 +77,7 @@ We’ll use the following packages:
%pip install --upgrade --quiet langchain langchain-community langchainhub langchain-openai chromadb bs4
```
We need to set environment variable `OPENAI_API_KEY`, which can be done
We need to set environment variable `OPENAI_API_KEY` for the embeddings model, which can be done
directly or loaded from a `.env` file like so:
```python
@ -125,10 +125,13 @@ from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import Chroma
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
```
import ChatModelTabs from "@theme/ChatModelTabs";
<ChatModelTabs customVarName="llm" />
```python
# Load, chunk and index the contents of the blog.
@ -149,8 +152,6 @@ vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings
# Retrieve and generate using the relevant snippets of the blog.
retriever = vectorstore.as_retriever()
prompt = hub.pull("rlm/rag-prompt")
llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
def format_docs(docs):
return "\n\n".join(doc.page_content for doc in docs)
@ -164,12 +165,11 @@ rag_chain = (
)
```
```python
rag_chain.invoke("What is Task Decomposition?")
```
``` text
```text
'Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. It can be done through prompting techniques like Chain of Thought or Tree of Thoughts, or by using task-specific instructions or human inputs. Task decomposition helps agents plan ahead and manage complicated tasks more effectively.'
```
@ -219,12 +219,11 @@ loader = WebBaseLoader(
docs = loader.load()
```
```python
len(docs[0].page_content)
```
``` text
```text
42824
```
@ -232,11 +231,11 @@ len(docs[0].page_content)
print(docs[0].page_content[:500])
```
``` text
```text
LLM Powered Autonomous Agents
Date: June 23, 2023 | Estimated Reading Time: 31 min | Author: Lilian Weng
@ -248,13 +247,14 @@ In
### Go deeper
`DocumentLoader`: Object that loads data from a source as list of
`Documents`.
`Documents`.
- [Docs](../../../docs/modules/data_connection/document_loaders/):
Detailed documentation on how to use `DocumentLoaders`.
Detailed documentation on how to use `DocumentLoaders`.
- [Integrations](../../../docs/integrations/document_loaders/): 160+
integrations to choose from.
integrations to choose from.
- [Interface](https://api.python.langchain.com/en/latest/document_loaders/langchain_core.document_loaders.base.BaseLoader.html):
API reference  for the base interface.
API reference  for the base interface.
## 2. Indexing: Split {#indexing-split}
@ -289,12 +289,11 @@ text_splitter = RecursiveCharacterTextSplitter(
all_splits = text_splitter.split_documents(docs)
```
```python
len(all_splits)
```
``` text
```text
66
```
@ -302,7 +301,7 @@ len(all_splits)
len(all_splits[0].page_content)
```
``` text
```text
969
```
@ -310,7 +309,7 @@ len(all_splits[0].page_content)
all_splits[10].metadata
```
``` text
```text
{'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/',
'start_index': 7056}
```
@ -318,18 +317,20 @@ all_splits[10].metadata
### Go deeper
`TextSplitter`: Object that splits a list of `Document`s into smaller
chunks. Subclass of `DocumentTransformer`s.
chunks. Subclass of `DocumentTransformer`s.
- Explore `Context-aware splitters`, which keep the location (“context”) of each
split in the original `Document`: - [Markdown
files](../../../docs/modules/data_connection/document_transformers/markdown_header_metadata)
- [Code (py or js)](../../../docs/integrations/document_loaders/source_code)
- [Scientific papers](../../../docs/integrations/document_loaders/grobid)
split in the original `Document`: - [Markdown
files](../../../docs/modules/data_connection/document_transformers/markdown_header_metadata)
- [Code (py or js)](../../../docs/integrations/document_loaders/source_code)
- [Scientific papers](../../../docs/integrations/document_loaders/grobid)
- [Interface](https://api.python.langchain.com/en/latest/base/langchain_text_splitters.base.TextSplitter.html): API reference for the base interface.
`DocumentTransformer`: Object that performs a transformation on a list
of `Document`s.
- [Docs](../../../docs/modules/data_connection/document_transformers/): Detailed documentation on how to use `DocumentTransformers`
- [Integrations](../../../docs/integrations/document_transformers/)
of `Document`s.
- [Docs](../../../docs/modules/data_connection/document_transformers/): Detailed documentation on how to use `DocumentTransformers`
- [Integrations](../../../docs/integrations/document_transformers/)
- [Interface](https://api.python.langchain.com/en/latest/documents/langchain_core.documents.transformers.BaseDocumentTransformer.html): API reference for the base interface.
## 3. Indexing: Store {#indexing-store}
@ -360,15 +361,17 @@ vectorstore = Chroma.from_documents(documents=all_splits, embedding=OpenAIEmbedd
### Go deeper
`Embeddings`: Wrapper around a text embedding model, used for converting
text to embeddings.
- [Docs](../../../docs/modules/data_connection/text_embedding): Detailed documentation on how to use embeddings.
- [Integrations](../../../docs/integrations/text_embedding/): 30+ integrations to choose from.
text to embeddings.
- [Docs](../../../docs/modules/data_connection/text_embedding): Detailed documentation on how to use embeddings.
- [Integrations](../../../docs/integrations/text_embedding/): 30+ integrations to choose from.
- [Interface](https://api.python.langchain.com/en/latest/embeddings/langchain_core.embeddings.Embeddings.html): API reference for the base interface.
`VectorStore`: Wrapper around a vector database, used for storing and
querying embeddings.
- [Docs](../../../docs/modules/data_connection/vectorstores/): Detailed documentation on how to use vector stores.
- [Integrations](../../../docs/integrations/vectorstores/): 40+ integrations to choose from.
querying embeddings.
- [Docs](../../../docs/modules/data_connection/vectorstores/): Detailed documentation on how to use vector stores.
- [Integrations](../../../docs/integrations/vectorstores/): 40+ integrations to choose from.
- [Interface](https://api.python.langchain.com/en/latest/vectorstores/langchain_core.vectorstores.VectorStore.html): API reference for the base interface.
This completes the **Indexing** portion of the pipeline. At this point
@ -399,17 +402,15 @@ facilitate retrieval. Any `VectorStore` can easily be turned into a
retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 6})
```
```python
retrieved_docs = retriever.invoke("What are the approaches to Task Decomposition?")
```
```python
len(retrieved_docs)
```
``` text
```text
6
```
@ -417,7 +418,7 @@ len(retrieved_docs)
print(retrieved_docs[0].page_content)
```
``` text
```text
Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.
Task decomposition can be done (1) by LLM with simple prompting like "Steps for XYZ.\n1.", "What are the subgoals for achieving XYZ?", (2) by using task-specific instructions; e.g. "Write a story outline." for writing a novel, or (3) with human inputs.
```
@ -429,27 +430,27 @@ to do retrieval, too.
`Retriever`: An object that returns `Document`s given a text query
- [Docs](../../../docs/modules/data_connection/retrievers/): Further
documentation on the interface and built-in retrieval techniques.
Some of which include:
- `MultiQueryRetriever` [generates variants of the input
question](../../../docs/modules/data_connection/retrievers/MultiQueryRetriever)
to improve retrieval hit rate.
- `MultiVectorRetriever` (diagram below) instead generates
[variants of the
embeddings](../../../docs/modules/data_connection/retrievers/multi_vector),
also in order to improve retrieval hit rate.
- `Max marginal relevance` selects for [relevance and
diversity](https://www.cs.cmu.edu/~jgc/publication/The_Use_MMR_Diversity_Based_LTMIR_1998.pdf)
among the retrieved documents to avoid passing in duplicate
context.
- Documents can be filtered during vector store retrieval using
metadata filters, such as with a [Self Query
Retriever](../../../docs/modules/data_connection/retrievers/self_query).
- [Integrations](../../../docs/integrations/retrievers/): Integrations
with retrieval services.
- [Interface](https://api.python.langchain.com/en/latest/retrievers/langchain_core.retrievers.BaseRetriever.html):
API reference for the base interface.
- [Docs](../../../docs/modules/data_connection/retrievers/): Further
documentation on the interface and built-in retrieval techniques.
Some of which include:
- `MultiQueryRetriever` [generates variants of the input
question](../../../docs/modules/data_connection/retrievers/MultiQueryRetriever)
to improve retrieval hit rate.
- `MultiVectorRetriever` (diagram below) instead generates
[variants of the
embeddings](../../../docs/modules/data_connection/retrievers/multi_vector),
also in order to improve retrieval hit rate.
- `Max marginal relevance` selects for [relevance and
diversity](https://www.cs.cmu.edu/~jgc/publication/The_Use_MMR_Diversity_Based_LTMIR_1998.pdf)
among the retrieved documents to avoid passing in duplicate
context.
- Documents can be filtered during vector store retrieval using
metadata filters, such as with a [Self Query
Retriever](../../../docs/modules/data_connection/retrievers/self_query).
- [Integrations](../../../docs/integrations/retrievers/): Integrations
with retrieval services.
- [Interface](https://api.python.langchain.com/en/latest/retrievers/langchain_core.retrievers.BaseRetriever.html):
API reference for the base interface.
## 5. Retrieval and Generation: Generate {#retrieval-and-generation-generate}
@ -460,34 +461,13 @@ parses the output.
We’ll use the gpt-3.5-turbo OpenAI chat model, but any LangChain `LLM`
or `ChatModel` could be substituted in.
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
<Tabs>
<TabItem value="openai" label="OpenAI" default>
```python
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model_name="gpt-3.5-turbo-0125", temperature=0)
```
</TabItem>
<TabItem value="local" label="Anthropic">
```python
%pip install -qU langchain-anthropic
```
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";
```python
from langchain_anthropic import ChatAnthropic
llm = ChatAnthropic(model="claude-3-sonnet-20240229", temperature=0.2, max_tokens=1024)
```
</TabItem>
</Tabs>
<ChatModelTabs
customVarName="llm"
anthropicParams={`"model="claude-3-sonnet-20240229", temperature=0.2, max_tokens=1024"`}
/>
We’ll use a prompt for RAG that is checked into the LangChain prompt hub
([here](https://smith.langchain.com/hub/rlm/rag-prompt)).
@ -498,7 +478,6 @@ from langchain import hub
prompt = hub.pull("rlm/rag-prompt")
```
```python
example_messages = prompt.invoke(
{"context": "filler context", "question": "filler question"}
@ -506,7 +485,7 @@ example_messages = prompt.invoke(
example_messages
```
``` text
```text
[HumanMessage(content="You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\nQuestion: filler question \nContext: filler context \nAnswer:")]
```
@ -514,10 +493,10 @@ example_messages
print(example_messages[0].content)
```
``` text
```text
You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.
Question: filler question
Context: filler context
Question: filler question
Context: filler context
Answer:
```
@ -543,13 +522,12 @@ rag_chain = (
)
```
```python
for chunk in rag_chain.stream("What is Task Decomposition?"):
print(chunk, end="", flush=True)
```
``` text
```text
Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. It involves transforming big tasks into multiple manageable tasks, allowing for easier interpretation and execution by autonomous agents or models. Task decomposition can be done through various methods, such as using prompting techniques, task-specific instructions, or human inputs.
```
@ -561,14 +539,16 @@ trace](https://smith.langchain.com/public/1799e8db-8a6d-4eb2-84d5-46e8d7d5a99b/r
#### Choosing a model
`ChatModel`: An LLM-backed chat model. Takes in a sequence of messages
and returns a message.
and returns a message.
- [Docs](../../../docs/modules/model_io/chat/)
- [Integrations](../../../docs/integrations/chat/): 25+ integrations to choose from.
- [Integrations](../../../docs/integrations/chat/): 25+ integrations to choose from.
- [Interface](https://api.python.langchain.com/en/latest/language_models/langchain_core.language_models.chat_models.BaseChatModel.html): API reference for the base interface.
`LLM`: A text-in-text-out LLM. Takes in a string and returns a string.
- [Docs](../../../docs/modules/model_io/llms)
- [Integrations](../../../docs/integrations/llms): 75+ integrations to choose from.
`LLM`: A text-in-text-out LLM. Takes in a string and returns a string.
- [Docs](../../../docs/modules/model_io/llms)
- [Integrations](../../../docs/integrations/llms): 75+ integrations to choose from.
- [Interface](https://api.python.langchain.com/en/latest/language_models/langchain_core.language_models.llms.BaseLLM.html): API reference for the base interface.
See a guide on RAG with locally-running models
@ -605,7 +585,7 @@ rag_chain = (
rag_chain.invoke("What is Task Decomposition?")
```
``` text
```text
'Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. It involves transforming big tasks into multiple manageable tasks, allowing for a more systematic and organized approach to problem-solving. Thanks for asking!'
```
@ -619,11 +599,11 @@ plenty of features, integrations, and extensions to explore in each of
the above sections. Along from the **Go deeper** sources mentioned
above, good next steps include:
- [Return
sources](../../../docs/use_cases/question_answering/sources): Learn
how to return source documents
- [Streaming](../../../docs/use_cases/question_answering/streaming):
Learn how to stream outputs and intermediate steps
- [Add chat
history](../../../docs/use_cases/question_answering/chat_history):
Learn how to add chat history to your app
- [Return
sources](../../../docs/use_cases/question_answering/sources): Learn
how to return source documents
- [Streaming](../../../docs/use_cases/question_answering/streaming):
Learn how to stream outputs and intermediate steps
- [Add chat
history](../../../docs/use_cases/question_answering/chat_history):
Learn how to add chat history to your app

87
docs/src/theme/ChatModelTabs.js
Unescape Escape View File

@ -1,4 +1,4 @@
/* eslint-disable react/jsx-props-no-spreading */
/* eslint-disable react/jsx-props-no-spreading, react/destructuring-assignment */
import React from "react";
import Tabs from "@theme/Tabs";
import TabItem from "@theme/TabItem";
@ -20,7 +20,24 @@ os.environ["${apiKeyName}"] = getpass.getpass()`;
}
/**
* @param {{ openaiParams?: string, anthropicParams?: string, fireworksParams?: string, mistralParams?: string, googleParams?: string, hideOpenai?: boolean, hideAnthropic?: boolean, hideFireworks?: boolean, hideMistral?: boolean, hideGoogle?: boolean }} props
* @typedef {Object} ChatModelTabsProps - Component props.
* @property {string} [openaiParams] - Parameters for OpenAI chat model. Defaults to `model="gpt-3.5-turbo-0125"`
* @property {string} [anthropicParams] - Parameters for Anthropic chat model. Defaults to `model="claude-3-sonnet-20240229"`
* @property {string} [fireworksParams] - Parameters for Fireworks chat model. Defaults to `model="accounts/fireworks/models/mixtral-8x7b-instruct"`
* @property {string} [mistralParams] - Parameters for Mistral chat model. Defaults to `model="mistral-large-latest"`
* @property {string} [googleParams] - Parameters for Google chat model. Defaults to `model="gemini-pro"`
* @property {string} [togetherParams] - Parameters for Google chat model. Defaults to `model="gemini-pro"`
* @property {boolean} [hideOpenai] - Whether or not to hide OpenAI chat model.
* @property {boolean} [hideAnthropic] - Whether or not to hide Anthropic chat model.
* @property {boolean} [hideFireworks] - Whether or not to hide Fireworks chat model.
* @property {boolean} [hideMistral] - Whether or not to hide Mistral chat model.
* @property {boolean} [hideGoogle] - Whether or not to hide Google chat model.
* @property {boolean} [hideTogether] - Whether or not to hide Together chat model.
* @property {string} [customVarName] - Custom variable name for the model. Defaults to `model`.
*/
/**
* @param {ChatModelTabsProps} props - Component props.
*/
export default function ChatModelTabs(props) {
const {
@ -29,24 +46,36 @@ export default function ChatModelTabs(props) {
fireworksParams,
mistralParams,
googleParams,
togetherParams,
hideOpenai,
hideAnthropic,
hideFireworks,
hideMistral,
hideGoogle,
hideTogether,
customVarName,
} = props;
const openAIParamsOrDefault = openaiParams ?? `model="gpt-3.5-turbo-0125"`
const anthropicParamsOrDefault = anthropicParams ?? `model="claude-3-sonnet-20240229"`
const fireworksParamsOrDefault = fireworksParams ?? `model="accounts/fireworks/models/mixtral-8x7b-instruct"`
const mistralParamsOrDefault = mistralParams ?? `model="mistral-large-latest"`
const googleParamsOrDefault = googleParams ?? `model="gemini-pro"`
const openAIParamsOrDefault = openaiParams ?? `model="gpt-3.5-turbo-0125"`;
const anthropicParamsOrDefault =
anthropicParams ?? `model="claude-3-sonnet-20240229"`;
const fireworksParamsOrDefault =
fireworksParams ??
`model="accounts/fireworks/models/mixtral-8x7b-instruct"`;
const mistralParamsOrDefault =
mistralParams ?? `model="mistral-large-latest"`;
const googleParamsOrDefault = googleParams ?? `model="gemini-pro"`;
const togetherParamsOrDefault =
togetherParams ??
`\n base_url="https://api.together.xyz/v1",\n api_key=os.environ["TOGETHER_API_KEY"],\n model="mistralai/Mixtral-8x7B-Instruct-v0.1",`;
const llmVarName = customVarName ?? "model";
const tabItems = [
{
value: "OpenAI",
label: "OpenAI",
text: `from langchain_openai import ChatOpenAI\n\nmodel = ChatOpenAI(${openAIParamsOrDefault})`,
text: `from langchain_openai import ChatOpenAI\n\n${llmVarName} = ChatOpenAI(${openAIParamsOrDefault})`,
apiKeyName: "OPENAI_API_KEY",
packageName: "langchain-openai",
default: true,
@ -55,7 +84,7 @@ export default function ChatModelTabs(props) {
{
value: "Anthropic",
label: "Anthropic",
text: `from langchain_anthropic import ChatAnthropic\n\nmodel = ChatAnthropic(${anthropicParamsOrDefault})`,
text: `from langchain_anthropic import ChatAnthropic\n\n${llmVarName} = ChatAnthropic(${anthropicParamsOrDefault})`,
apiKeyName: "ANTHROPIC_API_KEY",
packageName: "langchain-anthropic",
default: false,
@ -64,7 +93,7 @@ export default function ChatModelTabs(props) {
{
value: "FireworksAI",
label: "FireworksAI",
text: `from langchain_fireworks import ChatFireworks\n\nmodel = ChatFireworks(${fireworksParamsOrDefault})`,
text: `from langchain_fireworks import ChatFireworks\n\n${llmVarName} = ChatFireworks(${fireworksParamsOrDefault})`,
apiKeyName: "FIREWORKS_API_KEY",
packageName: "langchain-fireworks",
default: false,
@ -73,7 +102,7 @@ export default function ChatModelTabs(props) {
{
value: "MistralAI",
label: "MistralAI",
text: `from langchain_mistralai import ChatMistralAI\n\nmodel = ChatMistralAI(${mistralParamsOrDefault})`,
text: `from langchain_mistralai import ChatMistralAI\n\n${llmVarName} = ChatMistralAI(${mistralParamsOrDefault})`,
apiKeyName: "MISTRAL_API_KEY",
packageName: "langchain-mistralai",
default: false,
@ -82,22 +111,40 @@ export default function ChatModelTabs(props) {
{
value: "Google",
label: "Google",
text: `from langchain_google_genai import ChatGoogleGenerativeAI\n\nmodel = ChatGoogleGenerativeAI(${googleParamsOrDefault})`,
text: `from langchain_google_genai import ChatGoogleGenerativeAI\n\n${llmVarName} = ChatGoogleGenerativeAI(${googleParamsOrDefault})`,
apiKeyName: "GOOGLE_API_KEY",
packageName: "langchain-google-genai",
default: false,
shouldHide: hideGoogle,
}
]
},
{
value: "TogetherAI",
label: "TogetherAI",
text: `from langchain_openai import ChatOpenAI\n\n${llmVarName} = ChatOpenAI(${togetherParamsOrDefault})`,
apiKeyName: "TOGETHER_API_KEY",
packageName: "langchain-openai",
default: false,
shouldHide: hideTogether,
},
];
return (
<Tabs groupId="modelTabs">
{tabItems.filter((tabItem) => !tabItem.shouldHide).map((tabItem) => (
<TabItem value={tabItem.value} label={tabItem.label} default={tabItem.default}>
<Setup apiKeyName={tabItem.apiKeyName} packageName={tabItem.packageName} />
<CodeBlock language="python">{tabItem.text}</CodeBlock>
</TabItem>
))}
{tabItems
.filter((tabItem) => !tabItem.shouldHide)
.map((tabItem) => (
<TabItem
value={tabItem.value}
label={tabItem.label}
default={tabItem.default}
>
<Setup
apiKeyName={tabItem.apiKeyName}
packageName={tabItem.packageName}
/>
<CodeBlock language="python">{tabItem.text}</CodeBlock>
</TabItem>
))}
</Tabs>
);
}

6
docs/vercel_build.sh
Unescape Escape View File

@ -4,9 +4,9 @@ yum -y update
yum install gcc bzip2-devel libffi-devel zlib-devel wget tar gzip -y
# install quarto
wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.3.450/quarto-1.3.450-linux-amd64.tar.gz
tar -xzf quarto-1.3.450-linux-amd64.tar.gz
export PATH=$PATH:$(pwd)/quarto-1.3.450/bin/
wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.4.552/quarto-1.4.552-linux-amd64.tar.gz
tar -xzf quarto-1.4.552-linux-amd64.tar.gz
export PATH=$PATH:$(pwd)/quarto-1.4.552/bin/
# setup python env

Write Preview
Loading…
Cancel
Save