diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index ceabd9053dd899de3d7ede9cb3c41f361c984670..8dbca4ad914f2498e3938038fac6b33f8a615fe4 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -18,7 +18,7 @@ Also, join our Discord for ideas and discussions: <https://discord.gg/dGcwcsnxhU ### 1. 🆕 Extend Core Modules -The most impactful way to contribute to LlamaIndex is extending our core modules: +The most impactful way to contribute to LlamaIndex is by extending our core modules:  We welcome contributions in _all_ modules shown above. @@ -52,7 +52,7 @@ A data loader ingests data of any format from anywhere into `Document` objects, - [Github Repository Loader](https://github.com/emptycrown/llama-hub/tree/main/llama_hub/github_repo) Contributing a data loader is easy and super impactful for the community. -The preferred way to contribute is making a PR at [LlamaHub Github](https://github.com/emptycrown/llama-hub). +The preferred way to contribute is by making a PR at [LlamaHub Github](https://github.com/emptycrown/llama-hub). **Ideas** @@ -62,8 +62,8 @@ The preferred way to contribute is making a PR at [LlamaHub Github](https://gith #### Node Parser -A node parser parses `Document` objects into `Node` objects (atomic unit of data that LlamaIndex operates over, e.g., chunk of text, image, or table). -It is responsible for splitting text (via text splitters) and explicitly modelling the relationship between units of data (e.g. A is the source of B, C is a chunk after D). +A node parser parses `Document` objects into `Node` objects (atomic units of data that LlamaIndex operates over, e.g., chunk of text, image, or table). +It is responsible for splitting text (via text splitters) and explicitly modeling the relationship between units of data (e.g. A is the source of B, C is a chunk after D). **Interface**: `get_nodes_from_documents` takes a sequence of `Document` objects as input, and outputs a sequence of `Node` objects. @@ -75,7 +75,7 @@ See [the API reference](https://docs.llamaindex.ai/en/latest/api_reference/index **Ideas**: -- Add new `Node` relationships to model to model hierarchical documents (e.g. play-act-scene, chapter-section-heading). +- Add new `Node` relationships to model hierarchical documents (e.g. play-act-scene, chapter-section-heading). --- @@ -122,7 +122,7 @@ These serve as the main data store and retrieval engine for our vector index. **Interface**: -- `add` takes in a sequence of `NodeWithEmbeddings` and insert the embeddings (and possibly the node contents & metadata) into the vector store. +- `add` takes in a sequence of `NodeWithEmbeddings` and inserts the embeddings (and possibly the node contents & metadata) into the vector store. - `delete` removes entries given document IDs. - `query` retrieves top-k most similar entries given a query embedding. @@ -145,7 +145,7 @@ See [reference](https://docs.llamaindex.ai/en/stable/api_reference/indices/vecto Our retriever classes are lightweight classes that implement a `retrieve` method. They may take in an index class as input - by default, each of our indices -(list, vector, keyword) have an associated retriever. The output is a set of +(list, vector, keyword) has an associated retriever. The output is a set of `NodeWithScore` objects (a `Node` object with an extra `score` field). You may also choose to implement your own retriever classes on top of your own @@ -174,7 +174,7 @@ Our query engine classes are lightweight classes that implement a `query` method For instance, they may take in a retriever class as input; our `RetrieverQueryEngine` takes in a `retriever` as input as well as a `BaseSynthesizer` class for response synthesis, and the `query` method performs retrieval and synthesis before returning the final result. -They may take in other query engine classes in as input too. +They may take in other query engine classes as input too. **Interface**: @@ -217,7 +217,7 @@ A token usage optimizer refines the retrieved `Nodes` to reduce token usage duri #### Node Postprocessors -A node postprocessor refines a list of retrieve nodes given configuration and context. +A node postprocessor refines a list of retrieved nodes given configuration and context. **Interface**: `postprocess_nodes` takes a list of `Nodes` and extra metadata (e.g. similarity and query), and outputs a refined list of `Nodes`. @@ -231,7 +231,7 @@ A node postprocessor refines a list of retrieve nodes given configuration and co #### Output Parsers -A output parser enables us to extract structured output from the plain text output generated by the LLM. +An output parser enables us to extract structured output from the plain text output generated by the LLM. **Interface**: diff --git a/docs/DOCS_README.md b/docs/DOCS_README.md index 3e9faa1e102968ff4be9a6ccbd0307165ffad31a..749229369ff8cd5a58b9149befa57d4cf0ddb632 100644 --- a/docs/DOCS_README.md +++ b/docs/DOCS_README.md @@ -6,7 +6,7 @@ The `docs` directory contains the sphinx source text for LlamaIndex docs, visit https://docs.llamaindex.ai/en/stable/ to read the full documentation. This guide is made for anyone who's interested in running LlamaIndex documentation locally, -making changes to it and make contributions. LlamaIndex is made by the thriving community +making changes to it and making contributions. LlamaIndex is made by the thriving community behind it, and you're always welcome to make contributions to the project and the documentation. diff --git a/docs/community/llama_packs/root.md b/docs/community/llama_packs/root.md index 8c7ad1e1c4e51de0f218c78e9c9a0dac0ce8c9b5..fa59d116b2a2438711bd7c5dffd1cef317ee0a8f 100644 --- a/docs/community/llama_packs/root.md +++ b/docs/community/llama_packs/root.md @@ -8,8 +8,8 @@ This directly tackles a big pain point in building LLM apps; every use case requ They can be used in two ways: -- On one hand, they are **prepackaged modules** that can be initialized with parameters and run out of the box to achieve a given use case (whether that’s a full RAG pipeline, application template, and more). You can also import submodules (e.g. LLMs, query engines) to use directly. -- On another hand, LlamaPacks are **templates** that you can inspect, modify, and use. +- On one hand, they are **prepackaged modules** that can be initialized with parameters and run out of the box to achieve a given use case (whether that’s a full RAG pipeline, application template, or more). You can also import submodules (e.g. LLMs, query engines) to use directly. +- On the other hand, LlamaPacks are **templates** that you can inspect, modify, and use. **All packs are found on [LlamaHub](https://llamahub.ai/).** Go to the dropdown menu and select "LlamaPacks" to filter by packs. diff --git a/docs/understanding/storing/storing.md b/docs/understanding/storing/storing.md index e344c7929b5fc7a97887ae0782abaf24942033f1..862ee180b242537afac462dcbb5bf1b97f98c8ec 100644 --- a/docs/understanding/storing/storing.md +++ b/docs/understanding/storing/storing.md @@ -10,7 +10,7 @@ The simplest way to store your indexed data is to use the built-in `.persist()` index.storage_context.persist(persist_dir="<persist_dir>") ``` -Here is an example for Composable Graph: +Here is an example of a Composable Graph: ```python graph.root_index.storage_context.persist(persist_dir="<persist_dir>") diff --git a/docs/use_cases/q_and_a.md b/docs/use_cases/q_and_a.md index c2fa223d60497b12828d5faf198f4421fddc56ac..b5a69e3b43511ce06b232a9cdcd0b3da4b524a5c 100644 --- a/docs/use_cases/q_and_a.md +++ b/docs/use_cases/q_and_a.md @@ -33,4 +33,4 @@ Q&A has all sorts of sub-types, such as: ## Further examples -For further examples of Q&A use cases, see our [Q&A section in Putting it All Together](/understanding/putting_it_all_together/q_and_a.html). +For further examples of Q&A use cases, see our [Q&A section in Putting it All Together](/understanding/putting_it_all_together/q_and_a.md). diff --git a/experimental/classifier/utils.py b/experimental/classifier/utils.py index 877dfd7adb34c37871cfc33857d190c29e5ca9cb..abf808c8201cd6305195ffbfaf1a2ed42a6aec37 100644 --- a/experimental/classifier/utils.py +++ b/experimental/classifier/utils.py @@ -68,7 +68,7 @@ def extract_float_given_response(response: str, n: int = 1) -> Optional[float]: if new_numbers is None: return None else: - return float(numbers[0]) + return float(new_numbers[0]) else: return float(numbers[0])