dc9b080b9e
## Problem and Solution
This PR solves #1793, which is more of a convenience for users than
anything else. When using Chroma as a vectorstore, if you try to run
similarity search with a `k` value that is larger than the number of
documents stored in the vectorstore, Chroma will raise a
`chromadb.errors.NotEnoughElementsException`.
The workaround is to add a new parameter in all similarity search
methods under the `Chroma` class called `find_highest_possible_k`, an
optional boolean parameter that defaults to True (changes default
behavior). If this parameter is set to `False`, the methods will behave
exactly as they did before this PR.
If the parameter is `True`, however, the method will try running
similarity search with the given `k`, and if
`chromadb.errors.NotEnoughElementsException` is raised, iteratively
lower `k` (down to `k=1`) until the error is no longer raised.
The following is an example of how this is implemented in the
`Chroma.similarity_search` method.
e0846c2bca/langchain/vectorstores/chroma.py (L127-L159)
We add the `find_highest_possible_k` parameter as `Optional` and
defaulting to True. We explain it briefly in the docstring. We wrap the
previous similarity search logic inside a private local function that
takes `k`. If `find_highest_possible_k` is False, we return that private
function, retaining previous behavior. If it is True, which it is by
default, we iteratively lower `k` (until it is 1) until we can find `k`
documents from the Chroma vectorstore.
## Example
You create a `Chroma` object from 1 document. You then run
`.similarity_search()`, `.similarity_search_by_vector()`, or
`similarity_search_with_score()`. If you only pass a query, the default
`k` is `4`. All methods would previously raise a
`chromadb.errors.NotEnoughElementsException`.
Now, however, all methods will return one document, the document inside
the vectorstore (unless you're filtering, setting a maximum distance,
etc.).
## Note
I didn't find any places in the documentation to mention this change,
other than the example Jupyter notebook for the Chroma vectorstore. In
that notebook, there was never a cell running similarity search with
parameters. If it's important to include information on altering the
`find_highest_possible_k` parameter, I'll happily document it wherever.
🦜️🔗 LangChain
⚡ Building applications with LLMs through composability ⚡
Production Support: As you move your LangChains into production, we'd love to offer more comprehensive support. Please fill out this form and we'll set up a dedicated support Slack channel.
Quick Install
pip install langchain
or
conda install langchain -c conda-forge
🤔 What is this?
Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. But using these LLMs in isolation is often not enough to create a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
This library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:
❓ Question Answering over specific documents
- Documentation
- End-to-end Example: Question Answering over Notion Database
💬 Chatbots
- Documentation
- End-to-end Example: Chat-LangChain
🤖 Agents
- Documentation
- End-to-end Example: GPT+WolframAlpha
📖 Documentation
Please see here for full documentation on:
- Getting started (installation, setting up the environment, simple examples)
- How-To examples (demos, integrations, helper functions)
- Reference (full API docs)
- Resources (high-level explanation of core concepts)
🚀 What can this help with?
There are six main areas that LangChain is designed to help with. These are, in increasing order of complexity:
📃 LLMs and Prompts:
This includes prompt management, prompt optimization, generic interface for all LLMs, and common utilities for working with LLMs.
🔗 Chains:
Chains go beyond just a single LLM call, and are sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
📚 Data Augmented Generation:
Data Augmented Generation involves specific types of chains that first interact with an external datasource to fetch data to use in the generation step. Examples of this include summarization of long pieces of text and question/answering over specific data sources.
🤖 Agents:
Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end to end agents.
🧠 Memory:
Memory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.
🧐 Evaluation:
[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
For more information on these concepts, please see our full documentation.
💁 Contributing
As an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
For detailed information on how to contribute, see here.