zed/crates/semantic_index/Cargo.toml

63 lines
1.6 KiB
TOML
Raw Normal View History

Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
[package]
name = "semantic_index"
description = "Process, chunk, and embed text as vectors for semantic search."
version = "0.1.0"
edition = "2021"
publish = false
license = "GPL-3.0-or-later"
[lints]
workspace = true
Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
[lib]
path = "src/semantic_index.rs"
[[example]]
name = "index"
path = "examples/index.rs"
crate-type = ["bin"]
Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
[dependencies]
anyhow.workspace = true
client.workspace = true
clock.workspace = true
collections.workspace = true
fs.workspace = true
futures.workspace = true
futures-batch.workspace = true
gpui.workspace = true
language.workspace = true
log.workspace = true
heed.workspace = true
http.workspace = true
Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
open_ai.workspace = true
parking_lot.workspace = true
Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
project.workspace = true
settings.workspace = true
serde.workspace = true
serde_json.workspace = true
sha2.workspace = true
smol.workspace = true
theme.workspace = true
tree-sitter.workspace = true
ui. workspace = true
Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
util. workspace = true
unindent.workspace = true
workspace.workspace = true
Semantic Index (#10329) This introduces semantic indexing in Zed based on chunking text from files in the developer's workspace and creating vector embeddings using an embedding model. As part of this, we've created an embeddings provider trait that allows us to work with OpenAI, a local Ollama model, or a Zed hosted embedding. The semantic index is built by breaking down text for known (programming) languages into manageable chunks that are smaller than the max token size. Each chunk is then fed to a language model to create a high dimensional vector which is then normalized to a unit vector to allow fast comparison with other vectors with a simple dot product. Alongside the vector, we store the path of the file and the range within the document where the vector was sourced from. Zed will soon grok contextual similarity across different text snippets, allowing for natural language search beyond keyword matching. This is being put together both for human-based search as well as providing results to Large Language Models to allow them to refine how they help developers. Remaining todo: * [x] Change `provider` to `model` within the zed hosted embeddings database (as its currently a combo of the provider and the model in one name) Release Notes: - N/A --------- Co-authored-by: Nathan Sobo <nathan@zed.dev> Co-authored-by: Antonio Scandurra <me@as-cii.com> Co-authored-by: Conrad Irwin <conrad@zed.dev> Co-authored-by: Marshall Bowers <elliott.codes@gmail.com> Co-authored-by: Antonio <antonio@zed.dev>
2024-04-12 20:40:59 +03:00
worktree.workspace = true
[dev-dependencies]
env_logger.workspace = true
client = { workspace = true, features = ["test-support"] }
fs = { workspace = true, features = ["test-support"] }
futures.workspace = true
gpui = { workspace = true, features = ["test-support"] }
language = { workspace = true, features = ["test-support"] }
languages.workspace = true
project = { workspace = true, features = ["test-support"] }
tempfile.workspace = true
util = { workspace = true, features = ["test-support"] }
worktree = { workspace = true, features = ["test-support"] }
workspace = { workspace = true, features = ["test-support"] }
http = { workspace = true, features = ["test-support"] }