@ -153,6 +153,8 @@ Generally, such models are better at tool calling than non-fine-tuned models, an
Please see the [tool calling section](/docs/concepts/#functiontool-calling) for more information.
:::
For specifics on how to use chat models, see the [relevant how-to guides here](/docs/how_to/#chat-models).
### LLMs
<span data-heading-keywords="llm,llms"></span>
@ -165,6 +167,8 @@ When messages are passed in as input, they will be formatted into a string under
LangChain does not provide any LLMs, rather we rely on third party integrations.
For specifics on how to use LLMs, see the [relevant how-to guides here](/docs/how_to/#llms).
### Messages
Some language models take a list of messages as input and return a message.
@ -228,7 +232,7 @@ Prompt Templates take as input a dictionary, where each key represents a variabl
Prompt Templates output a PromptValue. This PromptValue can be passed to an LLM or a ChatModel, and can also be cast to a string or a list of messages.
The reason this PromptValue exists is to make it easy to switch between strings and messages.
There are a few different types of prompt templates
There are a few different types of prompt templates:
@ -348,6 +355,8 @@ LangChain has lots of different types of output parsers. This is a list of outpu
| [Datetime](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.datetime.DatetimeOutputParser.html#langchain.output_parsers.datetime.DatetimeOutputParser) | | ✅ | | `str` \| `Message` | `datetime.datetime` | Parses response into a datetime string. |
| [Structured](https://api.python.langchain.com/en/latest/output_parsers/langchain.output_parsers.structured.StructuredOutputParser.html#langchain.output_parsers.structured.StructuredOutputParser) | | ✅ | | `str` \| `Message` | `Dict[str, str]` | An output parser that returns structured information. It is less powerful than other output parsers since it only allows for fields to be strings. This can be useful when you are working with smaller LLMs. |
For specifics on how to use output parsers, see the [relevant how-to guides here](/docs/how_to/#output-parsers).
### Chat history
Most LLM applications have a conversational interface.
An essential component of a conversation is being able to refer to information introduced earlier in the conversation.
@ -382,6 +391,8 @@ loader = CSVLoader(
data = loader.load()
```
For specifics on how to use document loaders, see the [relevant how-to guides here](/docs/how_to/#document-loaders).
### Text splitters
Once you've loaded documents, you'll often want to transform them to better suit your application. The simplest example is you may want to split a long document into smaller chunks that can fit into your model's context window. LangChain has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.
@ -399,6 +410,8 @@ That means there are two different axes along which you can customize your text
1. How the text is split
2. How the chunk size is measured
For specifics on how to use text splitters, see the [relevant how-to guides here](/docs/how_to/#text-splitters).
@ -408,6 +421,8 @@ Embeddings create a vector representation of a piece of text. This is useful bec
The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former takes as input multiple texts, while the latter takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself).
For specifics on how to use embedding models, see the [relevant how-to guides here](/docs/how_to/#embedding-models).
@ -432,6 +449,8 @@ Retrievers can be created from vectorstores, but are also broad enough to includ
Retrievers accept a string query as input and return a list of Document's as output.
For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
### Tools
<span data-heading-keywords="tool,tools"></span>
@ -459,6 +478,8 @@ Generally, when designing tools to be used by a chat model or LLM, it is importa
- Models will perform better if the tools have well-chosen names, descriptions, and JSON schemas.
- Simpler tools are generally easier for models to use than more complex tools.
For specifics on how to use tools, see the [relevant how-to guides here](/docs/how_to/#tools).
### Toolkits
Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
@ -491,7 +512,7 @@ In order to solve that we built LangGraph to be this flexible, highly-controllab
If you are still using AgentExecutor, do not fear: we still have a guide on [how to use AgentExecutor](/docs/how_to/agent_executor).
It is recommended, however, that you start to transition to LangGraph.
In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent)
In order to assist in this we have put together a [transition guide on how to do so](/docs/how_to/migrate_agent).
### Multimodal
@ -499,6 +520,8 @@ Some models are multimodal, accepting images, audio and even video as inputs. Th
In LangChain, most chat models that support multimodal inputs also accept those values in OpenAI's content blocks format. So far this is restricted to image inputs. For models like Gemini which support video and other bytes input, the APIs also support the native, model-specific representations.
For specifics on how to use multimodal models, see the [relevant how-to guides here](/docs/how_to/#multimodal).
### Callbacks
LangChain provides a callbacks system that allows you to hook into the various stages of your LLM application. This is useful for logging, monitoring, streaming, and other tasks.
@ -569,6 +592,8 @@ This is a common reason why you may fail to see events being emitted from custom
runnables or tools.
:::
For specifics on how to use callbacks, see the [relevant how-to guides here](/docs/how_to/#callbacks).
## Techniques
### Function/tool calling
@ -640,6 +665,7 @@ LangChain provides several advanced retrieval types. A full list is below, along
| [Multi-Query Retriever](/docs/how_to/MultiQueryRetriever/) | Any | Yes | If users are asking questions that are complex and require multiple pieces of distinct information to respond | This uses an LLM to generate multiple queries from the original one. This is useful when the original query needs pieces of information about multiple topics to be properly answered. By generating multiple queries, we can then fetch documents for each of them. |
| [Ensemble](/docs/how_to/ensemble_retriever/) | Any | No | If you have multiple retrieval methods and want to try combining them. | This fetches documents from multiple retrievers and then combines them. |
For a high-level guide on retrieval, see this [tutorial on RAG](/docs/tutorials/rag/).
@ -49,7 +49,7 @@ These are the core building blocks you can use when building applications.
### Prompt templates
Prompt Templates are responsible for formatting user input into a format that can be passed to a language model.
[Prompt Templates](/docs/concepts/#prompt-templates) are responsible for formatting user input into a format that can be passed to a language model.
- [How to: use few shot examples](/docs/how_to/few_shot_examples)
- [How to: use few shot examples in chat models](/docs/how_to/few_shot_examples_chat/)
@ -58,7 +58,7 @@ Prompt Templates are responsible for formatting user input into a format that ca
### Example selectors
Example Selectors are responsible for selecting the correct few shot examples to pass to the prompt.
[Example Selectors](/docs/concepts/#example-selectors) are responsible for selecting the correct few shot examples to pass to the prompt.
- [How to: use example selectors](/docs/how_to/example_selectors)
- [How to: select examples by length](/docs/how_to/example_selectors_length_based)
@ -68,7 +68,7 @@ Example Selectors are responsible for selecting the correct few shot examples to
### Chat models
Chat Models are newer forms of language models that take messages in and output a message.
[Chat Models](/docs/concepts/#chat-models) are newer forms of language models that take messages in and output a message.
- [How to: do function/tool calling](/docs/how_to/tool_calling)
- [How to: get models to return structured output](/docs/how_to/structured_output)
@ -82,7 +82,7 @@ Chat Models are newer forms of language models that take messages in and output
### LLMs
What LangChain calls LLMs are older forms of language models that take a string in and output a string.
What LangChain calls [LLMs](/docs/concepts/#llms) are older forms of language models that take a string in and output a string.
- [How to: cache model responses](/docs/how_to/llm_caching)
- [How to: create a custom LLM class](/docs/how_to/custom_llm)
@ -92,7 +92,7 @@ What LangChain calls LLMs are older forms of language models that take a string
### Output parsers
Output Parsers are responsible for taking the output of an LLM and parsing into more structured format.
[Output Parsers](/docs/concepts/#output-parsers) are responsible for taking the output of an LLM and parsing into more structured format.
- [How to: use output parsers to parse an LLM response into structured format](/docs/how_to/output_parser_structured)
- [How to: parse JSON output](/docs/how_to/output_parser_json)
@ -104,7 +104,7 @@ Output Parsers are responsible for taking the output of an LLM and parsing into
### Document loaders
Document Loaders are responsible for loading documents from a variety of sources.
[Document Loaders](/docs/concepts/#document-loaders) are responsible for loading documents from a variety of sources.
- [How to: load CSV data](/docs/how_to/document_loader_csv)
- [How to: load data from a directory](/docs/how_to/document_loader_directory)
@ -117,7 +117,7 @@ Document Loaders are responsible for loading documents from a variety of sources
### Text splitters
Text Splitters take a document and split into chunks that can be used for retrieval.
[Text Splitters](/docs/concepts/#text-splitters) take a document and split into chunks that can be used for retrieval.
- [How to: recursively split text](/docs/how_to/recursive_text_splitter)
- [How to: split by HTML headers](/docs/how_to/HTML_header_metadata_splitter)
@ -131,20 +131,20 @@ Text Splitters take a document and split into chunks that can be used for retrie
### Embedding models
Embedding Models take a piece of text and create a numerical representation of it.
[Embedding Models](/docs/concepts/#embedding-models) take a piece of text and create a numerical representation of it.
- [How to: embed text data](/docs/how_to/embed_text)
- [How to: cache embedding results](/docs/how_to/caching_embeddings)
### Vector stores
Vector stores are databases that can efficiently store and retrieve embeddings.
[Vector stores](/docs/concepts/#vector-stores) are databases that can efficiently store and retrieve embeddings.
- [How to: use a vector store to retrieve data](/docs/how_to/vectorstores)
### Retrievers
Retrievers are responsible for taking a query and returning relevant documents.
[Retrievers](/docs/concepts/#retrievers) are responsible for taking a query and returning relevant documents.
- [How to: use a vector store to retrieve data](/docs/how_to/vectorstore_retriever)
- [How to: generate multiple queries to retrieve data for](/docs/how_to/MultiQueryRetriever)
@ -167,7 +167,7 @@ Indexing is the process of keeping your vectorstore in-sync with the underlying
### Tools
LangChain Tools contain a description of the tool (to pass to the language model) as well as the implementation of the function to call).
LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to pass to the language model) as well as the implementation of the function to call).
- [How to: create custom tools](/docs/how_to/custom_tools)
- [How to: use built-in tools and built-in toolkits](/docs/how_to/tools_builtin)
@ -196,6 +196,8 @@ For in depth how-to guides for agents, please check out [LangGraph](https://gith
### Callbacks
[Callbacks](/docs/concepts/#callbacks) allow you to hook into the various stages of your LLM application's execution.
- [How to: pass in callbacks at runtime](/docs/how_to/callbacks_runtime)
- [How to: attach callbacks to a module](/docs/how_to/callbacks_attach)
- [How to: pass callbacks into a module constructor](/docs/how_to/callbacks_constructor)
@ -222,6 +224,7 @@ These guides cover use-case specific details.
### Q&A with RAG
Retrieval Augmented Generation (RAG) is a way to connect LLMs to external sources of data.
For a high-level tutorial on RAG, check out [this guide](/docs/tutorials/rag/).
- [How to: add chat history](/docs/how_to/qa_chat_history_how_to/)
- [How to: stream](/docs/how_to/qa_streaming/)
@ -233,6 +236,7 @@ Retrieval Augmented Generation (RAG) is a way to connect LLMs to external source
### Extraction
Extraction is when you use LLMs to extract structured information from unstructured text.
For a high level tutorial on extraction, check out [this guide](/docs/tutorials/extraction/).
- [How to: use reference examples](/docs/how_to/extraction_examples/)
- [How to: handle long text](/docs/how_to/extraction_long_text/)
@ -241,6 +245,7 @@ Extraction is when you use LLMs to extract structured information from unstructu
### Chatbots
Chatbots involve using an LLM to have a conversation.
For a high-level tutorial on building chatbots, check out [this guide](/docs/tutorials/chatbot/).
- [How to: manage memory](/docs/how_to/chatbots_memory)
- [How to: do retrieval](/docs/how_to/chatbots_retrieval)
@ -249,6 +254,7 @@ Chatbots involve using an LLM to have a conversation.
### Query analysis
Query Analysis is the task of using an LLM to generate a query to send to a retriever.
For a high-level tutorial on query analysis, check out [this guide](/docs/tutorials/query_analysis/).
- [How to: add examples to the prompt](/docs/how_to/query_few_shot)
- [How to: handle cases where no queries are generated](/docs/how_to/query_no_queries)
@ -260,6 +266,7 @@ Query Analysis is the task of using an LLM to generate a query to send to a retr
### Q&A over SQL + CSV
You can use LLMs to do question answering over tabular data.
For a high-level tutorial, check out [this guide](/docs/tutorials/sql_qa/).
- [How to: use prompting to improve results](/docs/how_to/sql_prompting)
- [How to: do query validation](/docs/how_to/sql_query_checking)
@ -269,8 +276,25 @@ You can use LLMs to do question answering over tabular data.
### Q&A over graph databases
You can use an LLM to do question answering over graph databases.
For a high-level tutorial, check out [this guide](/docs/tutorials/graph/).
- [How to: map values to a database](/docs/how_to/graph_mapping)
- [How to: add a semantic layer over the database](/docs/how_to/graph_semantic)
- [How to: improve results with prompting](/docs/how_to/graph_prompting)
- [How to: construct knowledge graphs](/docs/how_to/graph_constructing)
Jacob Lee
4 months ago
committed by
GitHub