From d896b3a30e4e1aff7a574bbb2379c7b3d7e6c229 Mon Sep 17 00:00:00 2001
From: Shorthills AI <141953346+ShorthillsAI@users.noreply.github.com>
Date: Wed, 20 Dec 2023 20:08:49 +0530
Subject: [PATCH] FIx Doc links and other documentation issue (#9632)
* Update CHANGELOG.md
* Update agents.md
* Updated understanding.md (#51)
* Grammatical_error in docs/api_reference/query.rst
* Grammatical error in docs/end_to_end_tutorials/dev_practices/e2e_evaluation.md
* Changed word from unstructed to unstructured
* Corrected the spelling of performing
* Update evaluating.md
Corrected the spelling of "guidelines"
* Update evaluation.md
Changed " things are working will together" to " things are working well together"
* Update usage_pattern.md (#2)
* Update usage_pattern.md
Corrected the spellings of measure.
* Update basic_strategies.md
* Update (#8)
* Introduce Google Generative Language Semantic Retriever (#9440)
* Add a Gemini models for text and multi-modal. (#9452)
* Add a Gemini models for text and multi-modal.
Includes each of {text, mm} x {completion, chat} x {stream, one-shot}
x {sync, async} for Gemini's Developer API.
And two notebooks - regular text & multi-modal.
* add gemini into doc and rename MM example file
* Add version constraints to pip install
And remove noisy output.
* Enrich Gemini Example
* cr
* Use gemini-pro instead of ultra
* cr
* cr
* cr
---------
Co-authored-by: Haotian Zhang <socool.king@gmail.com>
* [version] bump to v0.9.15 (#9485)
* use persist dir in faiss (#9486)
* Gemini Embedding (#9476)
* Gemini Embedding
* cr
* Merge Gemini Same Role Chat Message (#9498)
* Fix Gemini Same Role Chat Msg
* cr
* cr
* cr
* cr
* Teeny stray link causing weirdness (#9501)
* Fixing CHANGELOG for wrong PR ID (#9505)
* Overhauling indexing to emphasize VectorStoreIndex and SEO
* Expanding use-cases docs: Q&A and chatbots
* Fix small bug in string method of NodeWithScore (#9494)
Update schema.py
Avoid exception in __str__ method of NodeWithScore when the optional member variable self.score is None.
* Added missing `default=None` to `LLM.system_prompt` (#9504)
* Adding default=None to system_prompt to fix type errors
* Added CHANGELOG entry
* Update PDFReader (#9508)
Add to PDFReader so that a user can specify if they want the PDF read in as one whole Document, or each page as a Document.
* Updating Spelling Mistakes (#9513)
* Grammatical_error in docs/api_reference/query.rst
* Grammatical error in docs/end_to_end_tutorials/dev_practices/e2e_evaluation.md
* Changed word from unstructed to unstructured
* Corrected the spelling of performing
---------
Co-authored-by: KamalSharmaShorthillsAI <kamal@shorthills.ai>
Co-authored-by: Haotian Zhang <socool.king@gmail.com>
Co-authored-by: UpneetShorthillsAI <144228282+UpneetShorthillsAI@users.noreply.github.com>
* FIxing Grammatical issues in docs (#9514)
* Fixing Docs (#9515)
* Allowing `LOCALAI_DEFAULTS` to work with `__ror__` (#9502)
---------
Co-authored-by: Lawrence Tsang <pikalaw@gmail.com>
Co-authored-by: Mark McDonald <macd@google.com>
Co-authored-by: Haotian Zhang <socool.king@gmail.com>
Co-authored-by: Logan <logan.markewich@live.com>
Co-authored-by: Laurie Voss <github@seldo.com>
Co-authored-by: James Braza <jamesbraza@gmail.com>
Co-authored-by: Max <150716622+maximannrcp@users.noreply.github.com>
Co-authored-by: Alex McGraw <60911060+JAlexMcGraw@users.noreply.github.com>
Co-authored-by: KamalSharmaShorthillsAI <kamal@shorthills.ai>
Co-authored-by: UpneetShorthillsAI <144228282+UpneetShorthillsAI@users.noreply.github.com>
* Update train_questions.txt (#5)
removed a from a developing
* updated basic_strategies.md and building_rag_from_scratch.md files (#6)
* Update basic_strategies.md
* Update building_rag_from_scratch.md
* Update deprecated_terms.md , changed "THe" to "The"
* Update graph_stores.md
* Update guidance.md
* Update vector_stores.md
* This PR addresses grammatical and clarity enhancements. (#7)
* Update structured_outputs.md
Grammatical Improvements
* Update query_transformations.md
Changed followup to follow-up.
* Update structured_outputs.md
---------
Co-authored-by: Shorthills AI <141953346+ShorthillsAI@users.noreply.github.com>
* made a grammatical correction (#10)
* Update train_questions.txt
removed a from a developing
* Update agents.md
removed a from a more information
* Update gatsby_license.txt (#11)
* Update gatsby_license.txt
grammar and tense correction: "read, understand, agree to and accept all the terms" to "read, understood, and agreed to accept all the terms", "do not agree" to "disagree", "agreement for keeping" to "agreement to keep", "unlink or detach or remove" to "unlink, detach or remove", "statements concerning tax" to "statements concerning the tax"
* Update concepts.md
grammar and tense correction: "or retrieved data" to "or retrieve data", "data which is" to "data that is", "class, are responsible" to "class, is responsible"," that allow you to ask question" to "that allows you to ask questions".
* Update discover_llamaindex.md (#15)
* Update llms.md (#9)
Corrected spellings of 'results'.
* Update llms.md (#13)
Corrected spelling of results.
* Update CHANGELOG.md (#14)
fixed the spelling mistake of the evaluation
* Update deprecated_terms.md
Links Urls in Deprecated_terms is not working.
1. Configuring settings in the Service Context Link updated.
2. Parsing Documents into Nodes Link updated.
3. LLMs in LlamaIndex Link updated.
4. Setting LLMs in the ServiceContext updated
* Update deprecated_terms.md
Links Updated in Deprecated_terms mentioned below:
1. Index Usage Pattern link updated.
2. Vector Store Guide link updated
3. Vector Store Integrations link updated.
4. Index Usage Pattern link updated.
5. Vector Store Guide link updated.
6. Vector Store Integrations link updated.
* Update deprecated_terms.md
GPTVectorStoreIndex "Index Usage Pattern" Link updated.
* Update chatbots.md
Improve clarity and consistency in the Chatbots section of the documentation:
1. Corrected the term 'LLM's' to 'LLMs' for consistency.
2. Modified 'Here's some relevant resources' to 'Here are some relevant resources' for grammatical correctness.
* Update chatbots.md with spelling : chatbots
Previous : chat bots
Corrected : chatbots
* Update multimodal.md
removed an extra word : "out" for consistency and clarity
* Update chatbots.md
* Update agents.md
* Update embeddings.md
* Update understanding.md
* Update extraction.md
---------
Co-authored-by: KamalSharmaShorthillsAI <kamal@shorthills.ai>
Co-authored-by: Shorthills AI <141953346+ShorthillsAI@users.noreply.github.com>
Co-authored-by: Haotian Zhang <socool.king@gmail.com>
Co-authored-by: UpneetShorthillsAI <144228282+UpneetShorthillsAI@users.noreply.github.com>
Co-authored-by: ManpreetShorthillsAI <142380984+ManpreetShorthillsAI@users.noreply.github.com>
Co-authored-by: SakshiShorthillsAI <144228183+SakshiShorthillsAI@users.noreply.github.com>
Co-authored-by: Lawrence Tsang <pikalaw@gmail.com>
Co-authored-by: Mark McDonald <macd@google.com>
Co-authored-by: Logan <logan.markewich@live.com>
Co-authored-by: Laurie Voss <github@seldo.com>
Co-authored-by: James Braza <jamesbraza@gmail.com>
Co-authored-by: Max <150716622+maximannrcp@users.noreply.github.com>
Co-authored-by: Alex McGraw <60911060+JAlexMcGraw@users.noreply.github.com>
Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com>
Co-authored-by: Saransh Sharma <142397365+SaranshSharmaShorthillsAI@users.noreply.github.com>
Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com>
Co-authored-by: Sanskar Tanwar <142409040+SanskarTanwarShorthillsAI@users.noreply.github.com>
Co-authored-by: ShreeramKumawatShorthillsAI <142401684+ShreeramKumawatShorthillsAI@users.noreply.github.com>
Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AashutoshPathakShorthillsAI <142410372+AashutoshPathakShorthillsAI@users.noreply.github.com>
Co-authored-by: Rajneesh Singh <68937839+rajneeshRepo@users.noreply.github.com>
Co-authored-by: VagishaMisraShorthillsAI <143705558+VagishaMisraShorthillsAI@users.noreply.github.com>
Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: Puneet Dhiman <142409038+PuneetDhimanShorthillsAI@users.noreply.github.com>
Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com>
* Update embeddings.md
* Update embeddings.md
* Update embeddings.md
* Update embeddings.md
---------
Co-authored-by: ChetnaGuptaShorthillsAI <142381084+ChetnaGuptaShorthillsAI@users.noreply.github.com>
Co-authored-by: Puneet Dhiman <142409038+PuneetDhimanShorthillsAI@users.noreply.github.com>
Co-authored-by: AdityaKalraShorthillsAI <143726711+AdityaKalraShorthillsAI@users.noreply.github.com>
Co-authored-by: KamalSharmaShorthillsAI <kamal@shorthills.ai>
Co-authored-by: Haotian Zhang <socool.king@gmail.com>
Co-authored-by: UpneetShorthillsAI <144228282+UpneetShorthillsAI@users.noreply.github.com>
Co-authored-by: ManpreetShorthillsAI <142380984+ManpreetShorthillsAI@users.noreply.github.com>
Co-authored-by: SakshiShorthillsAI <144228183+SakshiShorthillsAI@users.noreply.github.com>
Co-authored-by: Lawrence Tsang <pikalaw@gmail.com>
Co-authored-by: Mark McDonald <macd@google.com>
Co-authored-by: Logan <logan.markewich@live.com>
Co-authored-by: Laurie Voss <github@seldo.com>
Co-authored-by: James Braza <jamesbraza@gmail.com>
Co-authored-by: Max <150716622+maximannrcp@users.noreply.github.com>
Co-authored-by: Alex McGraw <60911060+JAlexMcGraw@users.noreply.github.com>
Co-authored-by: Aayush <142384656+AayushShorthillsAI@users.noreply.github.com>
Co-authored-by: Saransh Sharma <142397365+SaranshSharmaShorthillsAI@users.noreply.github.com>
Co-authored-by: AbhishekYadavShorthillsAI <142393903+AbhishekYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AryamanJaiswalShorthillsAI <142397527+AryamanJaiswalShorthillsAI@users.noreply.github.com>
Co-authored-by: Sanskar Tanwar <142409040+SanskarTanwarShorthillsAI@users.noreply.github.com>
Co-authored-by: ShreeramKumawatShorthillsAI <142401684+ShreeramKumawatShorthillsAI@users.noreply.github.com>
Co-authored-by: Vishal <141389263+VishalYadavShorthillsAI@users.noreply.github.com>
Co-authored-by: AashutoshPathakShorthillsAI <142410372+AashutoshPathakShorthillsAI@users.noreply.github.com>
Co-authored-by: Rajneesh Singh <68937839+rajneeshRepo@users.noreply.github.com>
Co-authored-by: VagishaMisraShorthillsAI <143705558+VagishaMisraShorthillsAI@users.noreply.github.com>
Co-authored-by: PankajKumarShorthillsAI <142473460+PankajKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: Adarsh Shrivastav <142413097+AdarshKumarShorthillsAI@users.noreply.github.com>
Co-authored-by: AmitSinghShorthillsAI <142410046+AmitSinghShorthillsAI@users.noreply.github.com>
---
CHANGELOG.md | 4 ++--
docs/module_guides/models/embeddings.md | 4 ++--
docs/understanding/understanding.md | 4 ++--
docs/use_cases/agents.md | 2 +-
docs/use_cases/chatbots.md | 8 ++++----
docs/use_cases/extraction.md | 4 ++--
docs/use_cases/multimodal.md | 2 +-
7 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2dc4e36bab..6093029b43 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -34,7 +34,7 @@
- Gemini Model Checks (#9563)
- Update OpenAI fine-tuning with latest changes (#9564)
- fix/Reintroduce `WHERE` filter to the Sparse Query for PgVectorStore (#9529)
-- Update Ollama API for ollama v0.1.16 (#9558)
+- Update Ollama API to ollama v0.1.16 (#9558)
- ollama: strip invalid `formatted` option (#9555)
- add a device in optimum push #9541 (#9554)
- Title vs content difference for Gemini Embedding (#9547)
@@ -206,7 +206,7 @@
### Bug Fixes / Nits
- Fixed bug in formatting chat prompt templates when estimating chunk sizes (#9025)
-- Sandboxed Pandas execution, remidiate CVE-2023-39662 (#8890)
+- Sandboxed Pandas execution, remediate CVE-2023-39662 (#8890)
- Restored `mypy` for Python 3.8 (#9031)
- Loosened `dataclasses-json` version range,
and removes unnecessary `jinja2` extra from `pandas` (#9042)
diff --git a/docs/module_guides/models/embeddings.md b/docs/module_guides/models/embeddings.md
index d1ef3fb938..4706e077d8 100644
--- a/docs/module_guides/models/embeddings.md
+++ b/docs/module_guides/models/embeddings.md
@@ -36,7 +36,7 @@ You can find more usage details and available customization options below.
## Getting Started
-The most common usage for an embedding model will be setting it in the service context object, and then using it to construct an index and query. The input documents will be broken into nodes, and the emedding model will generate an embedding for each node.
+The most common usage for an embedding model will be setting it in the service context object, and then using it to construct an index and query. The input documents will be broken into nodes, and the embedding model will generate an embedding for each node.
By default, LlamaIndex will use `text-embedding-ada-002`, which is what the example below manually sets up for you.
@@ -47,7 +47,7 @@ from llama_index.embeddings import OpenAIEmbedding
embed_model = OpenAIEmbedding()
service_context = ServiceContext.from_defaults(embed_model=embed_model)
-# optionally set a global service context to avoid passing it into other objects every time
+# Optionally set a global service context to avoid passing it into other objects every time
from llama_index import set_global_service_context
set_global_service_context(service_context)
diff --git a/docs/understanding/understanding.md b/docs/understanding/understanding.md
index 2fd1afcb16..0f7126741f 100644
--- a/docs/understanding/understanding.md
+++ b/docs/understanding/understanding.md
@@ -1,6 +1,6 @@
# Building an LLM application
-Welcome to the start of Understanding LlamaIndex. This is a series of short, bite-sized tutorials on every stage of building an LLM application to get you acquainted with how to use LlamaIndex before diving into more advanced and subtle strategies. If you're an experienced programmer new to LlamaIndex, this is the place to start.
+Welcome to the beginning of Understanding LlamaIndex. This is a series of short, bite-sized tutorials on every stage of building an LLM application to get you acquainted with how to use LlamaIndex before diving into more advanced and subtle strategies. If you're an experienced programmer new to LlamaIndex, this is the place to start.
## Key steps in building an LLM application
@@ -24,7 +24,7 @@ There are a series of key steps involved in building any LLM-powered application
- **[Tracing and debugging](/understanding/tracing_and_debugging/tracing_and_debugging.md)**: also called **observability**, it's especially important with LLM applications to be able to look into the inner workings of what's going on to help you debug problems and spot places to improve.
-- **[Evaluating](/understanding/evaluating/evaluating.md)**: every strategy has pros and cons and a key part of building, shipping and evolving your application is evaluating whether your change has improved your application in terms of accuracy, performance, clarity, cost and more. Reliably evaluating your changes is a big part of LLM application development.
+- **[Evaluating](/understanding/evaluating/evaluating.md)**: every strategy has pros and cons and a key part of building, shipping and evolving your application is evaluating whether your change has improved your application in terms of accuracy, performance, clarity, cost and more. Reliably evaluating your changes is a crucial part of LLM application development.
## Let's get started!
diff --git a/docs/use_cases/agents.md b/docs/use_cases/agents.md
index 5b7664afe4..7ecb67838c 100644
--- a/docs/use_cases/agents.md
+++ b/docs/use_cases/agents.md
@@ -25,4 +25,4 @@ more information + a detailed analysis.
## Learn more
-Our Putting It All Together section has [more on agents](/understanding/putting_it_all_together/agents.md)
+Our Putting It All Together section has [more on agents](/docs/understanding/putting_it_all_together/agents.md)
diff --git a/docs/use_cases/chatbots.md b/docs/use_cases/chatbots.md
index b75d3389a2..a801dec805 100644
--- a/docs/use_cases/chatbots.md
+++ b/docs/use_cases/chatbots.md
@@ -1,16 +1,16 @@
# Chatbots
-Chatbots are another extremely popular use case for LLM's. Instead of a single question and answer, a chatbot can handle multiple back-and-forth queries and answers, getting clarification or answering follow-up questions.
+Chatbots are another extremely popular use case for LLMs. Instead of a single question and answer, a chatbot can handle multiple back-and-forth queries and answers, getting clarification or answering follow-up questions.
LlamaIndex gives you the tools to build knowledge-augmented chatbots and agents.
-Here's some relevant resources:
+Here are some relevant resources:
-- [Building a chatbot](/understanding/putting_it_all_together/chatbots/building_a_chatbot.md) tutorial
+- [Building a chatbot](/docs/understanding/putting_it_all_together/chatbots/building_a_chatbot.md) tutorial
- [create-llama](https://blog.llamaindex.ai/create-llama-a-command-line-tool-to-generate-llamaindex-apps-8f7683021191), a command line tool that generates a full-stack chatbot application for you
- [SECinsights.ai](https://www.secinsights.ai/), an open-source application that uses LlamaIndex to build a chatbot that answers questions about SEC filings
- [RAGs](https://blog.llamaindex.ai/introducing-rags-your-personalized-chatgpt-experience-over-your-data-2b9d140769b1), a project inspired by OpenAI's GPTs that lets you build a low-code chatbot over your data using Streamlit
-- Our [OpenAI agents](/module_guides/deploying/agents/modules.md) are all chat bots in nature
+- Our [OpenAI agents](/docs/module_guides/deploying/agents/modules.md) are all chat bots in nature
## External sources
diff --git a/docs/use_cases/extraction.md b/docs/use_cases/extraction.md
index 0554c3a0d1..e76b1ca035 100644
--- a/docs/use_cases/extraction.md
+++ b/docs/use_cases/extraction.md
@@ -10,5 +10,5 @@ Once you have structured data you can send them to a database, or you can parse
Examples:
-- [Extracting names and locations from descriptions of people](/examples/output_parsing/df_program.ipynb)
-- [Extracting album data from music reviews](/examples/llm/llama_api.ipynb)
+- [Extracting names and locations from descriptions of people](/docs/examples/output_parsing/df_program.ipynb)
+- [Extracting album data from music reviews](/docs/examples/llm/llama_api.ipynb)
diff --git a/docs/use_cases/multimodal.md b/docs/use_cases/multimodal.md
index f9e9aea984..e180f87c3f 100644
--- a/docs/use_cases/multimodal.md
+++ b/docs/use_cases/multimodal.md
@@ -98,7 +98,7 @@ maxdepth: 1
### Using Chroma for Multi-Modal retrieval with single vector store
Chroma vector DB supports single vector store for indexing both images and texts.
-Check out out Chroma + LlamaIndex integration with single Multi-Modal Vector Store for both images/texts index and retrieval.
+Check out Chroma + LlamaIndex integration with single Multi-Modal Vector Store for both images/texts index and retrieval.
```{toctree}
---
--
GitLab