Let's go through these categories and for each one identify key concepts (to clarify terminology) as well as the problems in this area LangChain helps solve.
- LLM: A large language model, in particular a text-to-text model.
- Prompt: The input to a language model. Typically this is not simply a hardcoded string but rather a combination of a template, some examples, and user input.
- Prompt Template: An object responsible for constructing the final prompt to pass to a LLM.
- Switching costs: by exposing a standard interface for all the top LLM providers, LangChain makes it easy to switch from one provider to another, whether it be for production use cases or just for testing stuff out.
- Prompt management: managing your prompts is easy when you only have one simple one, but can get tricky when you have a bunch or when they start to get more complex. LangChain provides a standard way for storing, constructing, and referencing prompts.
- Prompt optimization: despite the underlying models getting better and better, there is still currently a need for carefully constructing prompts.
Using an LLM in isolation is fine for some simple applications, but many more complex ones require chaining LLMs - either with eachother or with other experts.
LangChain provides several parts to help with that.
- Tools: APIs designed for assisting with a particular use case (search, databases, Python REPL, etc). Prompt templates, LLMs, and chains can also be considered tools.
- Chains: A combination of multiple tools in a deterministic manner.
Some applications will require not just a predetermined chain of calls to LLMs/other tools, but potentially an unknown chain that depends on the user input.
In these types of chains, there is a “agent” which has access to a suite of tools.
Depending on the user input, the agent can then decide which, if any, of these tools to call.
By default, Chains and Agents are stateless, meaning that they treat each incoming query independently.
In some applications (chatbots being a GREAT example) it is highly important to remember previous interactions,
both at a short term but also at a long term level. The concept of "Memory" exists to do exactly that.
**Key Concepts**
- Memory: A class that can be added to an Agent or Chain to (1) pull in memory variables before calling that chain/agent, and (2) create new memories after the chain/agent finishes.
- Memory Variables: Variables returned from a Memory class, to be passed into the chain/agent along with the user input.
**Problems Solved**
- Standard memory interfaces
- A collection of common memory implementations to choose from
- Common chains/agents that use memory (e.g. chatbots)
To begin developing on this project, first clone the repo locally.
### Quick Start
This project uses [Poetry](https://python-poetry.org/) as a dependency manager. Check out Poetry's own [documentation on how to install it](https://python-poetry.org/docs/#installation) on your system before proceeding.
To install requirements:
```bash
poetry install -E all
```
This will install all requirements for running the package, examples, linting, formatting, and tests. Note the `-E all` flag will install all optional dependencies necessary for integration testing.
Now, you should be able to run the common tasks in the following section.
Linting for this project is a combination of [Black](https://black.readthedocs.io/en/stable/), [isort](https://pycqa.github.io/isort/), [flake8](https://flake8.pycqa.org/en/latest/), and [mypy](http://mypy-lang.org/).
We recognize linting can be annoying - if you do not want to do it, please contact a project maintainer and they can help you with it. We do not want this to be a blocker for good code getting contributed.
If you are adding a Jupyter notebook example, you'll want to install the optional `dev` dependencies.
To install dev dependencies:
```bash
poetry install --with dev
```
Launch a notebook:
```bash
poetry run jupyter notebook
```
When you run `poetry install`, the `langchain` package is installed as editable in the virtualenv, so your new logic can be imported into the notebook.
Similar to linting, we recognize documentation can be annoying - if you do not want to do it, please contact a project maintainer and they can help you with it. We do not want this to be a blocker for good code getting contributed.
