Skip to content

Commit e76dd6a

Browse files
ammirsmammirsm
authored
Restructure navigation and update documentation (#1703)
* Restructure navigation and update documentation links in mkdocs.yml. Simplify sections and add new files for better organization and clarity. Adjust community resources and remove unnecessary redirects. * Refactor navigation structure in mkdocs.yml Organize the navigation by grouping related topics and adding overviews for sections. Update titles for clarity, correcting casing inconsistencies. Split existing entries where applicable to enhance documentation usability. * Restructure navigation in mkdocs.yml by adding new sections for Metrics and Assertions, Optimizers, and updating Signatures. Remove redundant entries and clarify module organization. Adjust typo in "Retreive" to "Retrieve" and make minor formatting changes. * Update introductory documentation and enhance MkDocs configuration - Revise title to "# DSPy" in intro.md - Add `hide` options for table of contents and navigation in intro.md - Integrate new navigation features in mkdocs.yml for improved user experience * Restructure FAQs and tutorials, adding community sections for companies using DSPy and development setup. Update navigation in mkdocs.yml to reflect new content and improve organization. * Add comprehensive redirect maps to mkdocs configuration Expand the `redirects` section in `mkdocs.yml` by adding multiple redirect mappings to streamline navigation across various documentation sections, including Quick Start, Building Blocks, Tutorials, and Deep Dive topics. * Remove unnecessary indentation from redirects plugin configuration in mkdocs.yml. * Remove unused markdown extension from MkDocs configuration * Refactor related-projects.md to rename section and expand use cases list - Change title from "DSPy Use Cases" to "Use Cases" - Add a detailed table of use cases from various companies, including links to relevant blogs and articles - Update mkdocs.yml to rename "Tutorials" to "Community Resources" under the Community section * remove companies-using-dspy.md * Add community resources and use cases documentation Create new markdown files for community resources and use cases highlighting helpful blogs, tutorials, videos, and company applications of DSPy. Update the contribution guidelines to include a note on development setup and remove the outdated reference in the navigation file. Adjust project dependencies by removing the unnecessary `json-repair` entry. * Remove debugging section from navigation and update FAQ title in mkdocs configuration * Add json-repair to dependencies in pyproject.toml
1 parent c6429e4 commit e76dd6a

File tree

6 files changed

+224
-42
lines changed

6 files changed

+224
-42
lines changed

‎docs/docs/community/community-resources.md‎

Lines changed: 56 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,56 @@
1+
# Resources
2+
3+
This is the list of tutorials and blog posts on DSPy. If you would like to add your own tutorial, please make a PR.
4+
5+
6+
## A Few Blogs & Videos on using DSPy
7+
8+
9+
10+
### Blogs
11+
12+
| **Name** | **Link** |
13+
|---|---|
14+
| **Why I bet on DSPy** | [Blog](https://blog.isaacbmiller.com/posts/dspy) |
15+
| **Not Your Average Prompt Engineering** | [Blog](https://jina.ai/news/dspy-not-your-average-prompt-engineering/) |
16+
| **Why I'm excited about DSPy** | [Blog](https://substack.stephen.so/p/why-im-excited-about-dspy) |
17+
| **Achieving GPT-4 Performance at Lower Cost** | [Link](https://gradient.ai/blog/achieving-gpt-4-level-performance-at-lower-cost-using-dspy) |
18+
| **Prompt engineering is a task best left to AI models** | [Link](https://www.theregister.com/2024/02/22/prompt_engineering_ai_models/) |
19+
| **What makes DSPy a valuable framework for developing complex language model pipelines?** | [Link](https://medium.com/@sujathamudadla1213/what-makes-dspy-a-valuable-framework-for-developing-complex-language-model-pipelines-edfa5b4bcf9b) |
20+
| **DSPy: A new framework to program your foundation models just by prompting** | [Link](https://www.linkedin.com/pulse/dspy-new-framework-program-your-foundation-models-just-prompting-lli4c/) |
21+
| **Intro to DSPy: Goodbye Prompting, Hello Programming** | [Link](https://medium.com/towards-data-science/intro-to-dspy-goodbye-prompting-hello-programming-4ca1c6ce3eb9) |
22+
| **DSPyGen: Revolutionizing AI** | [Link](https://www.linkedin.com/pulse/launch-alert-dspygen-20242252-revolutionizing-ai-sean-chatman--g9f1c/) |
23+
| **Building an AI Assistant with DSPy** | [Link](https://www.linkedin.com/pulse/building-ai-assistant-dspy-valliappa-lakshmanan-vgnsc/) |
24+
25+
26+
### Videos
27+
| **Name** | **Link** |
28+
|---|---|
29+
| **DSPy Explained! (60K views)** | [Link](https://www.youtube.com/watch?v=41EfOY0Ldkc) |
30+
| **DSPy Intro from Sephora (25K views)** | [Link](https://www.youtube.com/watch?v=D2HurSldDkE) |
31+
| **Structured Outputs with DSPy** | [Link](https://www.youtube.com/watch?v=tVw3CwrN5-8) |
32+
| **DSPy and ColBERT - Weaviate Podcast** | [Link](https://www.youtube.com/watch?v=CDung1LnLbY) |
33+
| **SBTB23 DSPy** | [Link](https://www.youtube.com/watch?v=Dt3H2ninoeY) |
34+
| **Optimization with DSPy and LangChain** | [Link](https://www.youtube.com/watch?v=4EXOmWeqXRc) |
35+
| **Automated Prompt Engineering + Visualization** | [Link](https://www.youtube.com/watch?v=eAZ2LtJ6D5k) |
36+
| **Transforming LM Calls into Pipelines** | [Link](https://www.youtube.com/watch?v=NoaDWKHdkHg) |
37+
| **NeurIPS Hacker Cup: DSPy for Code Gen** | [Link](https://www.youtube.com/watch?v=gpe-rtJN8z8) |
38+
| **MIPRO and DSPy - Weaviate Podcast** | [Link](https://www.youtube.com/watch?v=skMH3DOV_UQ) |
39+
| **Getting Started with RAG in DSPy** | [Link](https://www.youtube.com/watch?v=CEuUG4Umfxs) |
40+
| **Adding Depth to DSPy Programs** | [Link](https://www.youtube.com/watch?v=0c7Ksd6BG88) |
41+
| **Programming Foundation Models with DSPy** | [Link](https://www.youtube.com/watch?v=Y94tw4eDHW0) |
42+
| **DSPy End-to-End: SF Meetup** | [Link](https://www.youtube.com/watch?v=Y81DoFmt-2U) |
43+
| **Monitoring & Tracing DSPy with Langtrace** | [Link](https://langtrace.ai/blog/announcing-dspy-support-in-langtrace) |
44+
| **Teaching chat models to solve chess puzzles using DSPy + Finetuning** | [Link](https://raw.sh/posts/chess_puzzles) |
45+
46+
47+
### Podcasts
48+
49+
Weaviate has a directory of 10 amazing notebooks and 6 podcasts!
50+
Huge shoutout to them for the massive support ❤️. See the [Weaviate DSPy directory](https://weaviate.io/developers/weaviate/more-resources/dspy).
51+
52+
53+
TODO: This list in particular is highly incomplete. There are dozens of other good ones. To allow space, divide into opintionated blogs / podcasts / interviews vs. tutorials & talks.
54+
55+
Credit: Some of these resources were originally compiled in the [Awesome DSPy](https://github.com/ganarajpr/awesome-dspy/tree/master) repo.
56+

‎docs/docs/community/how-to-contribute.md‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
## Development Setup
2+
3+
We are working on a development setup guide. If you're interested in contributing, please reach out to us on Discord.
4+
5+
## Contributing
6+
7+
**What if I have a better idea for prompting or synthetic data generation?** Perfect. We encourage you to think if it's best expressed as a module or an optimizer, and we'd love to merge it in DSPy so everyone can use it. DSPy is not a complete project; it's an ongoing effort to create structure (modules and optimizers) in place of hacky prompt and pipeline engineering tricks.
8+
9+
**How can I add my favorite LM or vector store?**
10+
11+
Check out these walkthroughs on setting up a [Custom LM client](/deep-dive/language_model_clients/custom-lm-client) and [Custom RM client](/deep-dive/retrieval_models_clients/custom-rm-client).
12+

‎docs/docs/community/use-cases.md‎

Lines changed: 107 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,107 @@
1+
# Use Cases
2+
3+
We often get questions like "How are people using DSPy in practice?", both in production and for research. This list was created to collect a few pointers and to encourage others in the community to add their own work below.
4+
5+
This list is ever expanding and highly incomplete (WIP)! We'll be adding a bunch more. If you would like to add your product or research to this list, please make a PR.
6+
7+
## A Few Company Use Cases
8+
9+
| **Name** | **Use Cases** |
10+
|---|---|
11+
| **[JetBlue](https://www.jetblue.com/)** | Multiple chatbot use cases. [Blog](https://www.databricks.com/blog/optimizing-databricks-llm-pipelines-dspy) |
12+
| **[Replit](https://replit.com/)** | Synthesize diffs using code LLMs using a DSPy pipeline. [Blog](https://blog.replit.com/code-repair) |
13+
| **[Databricks](https://www.databricks.com/)** | Research, products, and customer solutions around LM Judges, RAG, classification, and other applications. [Blog](https://www.databricks.com/blog/dspy-databricks) [Blog II](https://www.databricks.com/customers/ddi) |
14+
| **[Sephora](https://www.sephora.com/)** | Undisclosed agent usecases; perspectives shared in [DAIS Session](https://www.youtube.com/watch?v=D2HurSldDkE). |
15+
| **[Zoro UK](https://www.zoro.co.uk/)** | E-commerce applications around structured shopping. [Portkey Session](https://www.youtube.com/watch?v=_vGKSc1tekE) |
16+
| **[VMware](https://www.vmware.com/)** | RAG and other prompt optimization applications. [Interview in The Register.](https://www.theregister.com/2024/02/22/prompt_engineering_ai_models/) [Business Insider.](https://www.businessinsider.com/chaptgpt-large-language-model-ai-prompt-engineering-automated-optimizer-2024-3) |
17+
| **[Haize Labs](https://www.haizelabs.com/)** | Automated red-teaming for LLMs. [Blog](https://blog.haizelabs.com/posts/dspy/) |
18+
| **[Plastic Labs](https://www.plasticlabs.ai/)** | Different pipelines within Honcho. [Blog](https://blog.plasticlabs.ai/blog/User-State-is-State-of-the-Art) |
19+
| **[PingCAP](https://pingcap.com/)** | Building a knowledge graph. [Article](https://www.pingcap.com/article/building-a-graphrag-from-wikipedia-page-using-dspy-openai-and-tidb-vector-database/) |
20+
| **[Salomatic](https://langtrace.ai/blog/case-study-how-salomatic-used-langtrace-to-build-a-reliable-medical-report-generation-system)** | Enriching medical reports using DSPy. [Blog](https://langtrace.ai/blog/case-study-how-salomatic-used-langtrace-to-build-a-reliable-medical-report-generation-system) |
21+
| **[Truelaw](https://www.youtube.com/watch?v=O0F3RAWZNfM)** | How Truelaw builds bespoke LLM pipelines for law firms using DSPy. [Podcast](https://www.youtube.com/watch?v=O0F3RAWZNfM) |
22+
| **[Moody's](https://www.moodys.com/)** | Leveraging DSPy to optimize RAG systems, LLM-as-a-Judge, and agentic systems for financial workflows. |
23+
| **[Normal Computing](https://www.normalcomputing.com/)** | Translate specs from chip companies from English to intermediate formal languages |
24+
| **[Procure.FYI](https://www.procure.fyi/)** | Process messy, publicly available technology spending and pricing data via DSPy. |
25+
| **[RadiantLogic](https://www.radiantlogic.com/)** | AI Data Assistant. DSPy is used for the agent that routes the query, the context extraction module, the text-to-sql conversion engine, and the table summarization module. |
26+
| **[Raia](https://raiahealth.com/)** | Using DSPy for AI-powered Personal Healthcare Agents. |
27+
| **[Hyperlint](https://hyperlint.com)** | Uses DSPy to generate technical documentation. DSPy helps to fetch relevant information and synthesize that into tutorials. |
28+
| **[Starops](https://staropshq.com/) & [Saya](https://heysaya.ai/)** | Building research documents given a user's corpus. Generate prompts to create more articles from example articles. |
29+
| **[Tessel AI](https://tesselai.com/)** | Enhancing human-machine interaction with data use cases. |
30+
| **[Dicer.ai](https://dicer.ai/)** | Uses DSPy for marketing AI to get the most from their paid ads. |
31+
| **[Howie](https://howie.ai)** | Using DSPy to automate meeting scheduling through email. |
32+
| **[Isoform.ai](https://isoform.ai)** | Building custom integrations using DSPy. |
33+
| **[Trampoline AI](https://trampoline.ai)** | Uses DSPy to power their data-augmentation and LM pipelines. |
34+
| **[Pretrain](https://pretrain.com)** | Uses DSPy to automatically optimize AI performance towards user-defined tasks based on uploaded examples. |
35+
36+
WIP. This list mainly includes companies that have public posts or have OKed being included for specific products so far.
37+
38+
39+
## A Few Papers Using DSPy
40+
41+
| **Name** | **Description** |
42+
|---|---|
43+
| **[STORM](https://arxiv.org/abs/2402.14207)** | Writing Wikipedia-like Articles From Scratch. |
44+
| **[PATH](https://arxiv.org/abs/2406.11706)** | Prompts as Auto-Optimized Training Hyperparameters: Training Best-in-Class IR Models from Scratch with 10 Gold Labels |
45+
| **[WangLab @ MEDIQA](https://arxiv.org/abs/2404.14544)** | UofT's winning system at MEDIQA, outperforms the next best system by 20 points |
46+
| **[UMD's Suicide Detection System](https://arxiv.org/abs/2406.06608)** | Outperforms 20-hour expert human prompt engineering by 40% |
47+
| **[IReRa](https://arxiv.org/abs/2401.12178)** | Infer-Retrieve-Rank: Extreme Classification with > 10,000 Labels |
48+
| **[Unreasonably Effective Eccentric Prompts](https://arxiv.org/abs/2402.10949v2)** | General Prompt Optimization |
49+
| **[Palimpzest](https://arxiv.org/abs/2405.14696)** | A Declarative System for Optimizing AI Workloads |
50+
| **[AI Agents that Matter](https://arxiv.org/abs/2407.01502v1)** | Agent Efficiency Optimization |
51+
| **[EDEN](https://arxiv.org/abs/2406.17982v1)** | Empathetic Dialogues for English Learning: Uses adaptive empathetic feedback to improve student grit |
52+
| **[ECG-Chat](https://arxiv.org/pdf/2408.08849)** | Uses DSPy with GraphRAG for medical report generation |
53+
| **[DSPy Assertions](https://arxiv.org/abs/2312.13382)** | Various applications of imposing hard and soft constraints on LM outputs |
54+
| **[DSPy Guardrails](https://boxiyu.github.io/assets/pdf/DSPy_Guardrails.pdf)** | Reduce the attack success rate of CodeAttack, decreasing from 75% to 5% |
55+
| **[Co-STORM](https://arxiv.org/pdf/2408.15232)** | Collaborative STORM: Generate Wikipedia-like articles through collaborative discourse among users and multiple LM agents |
56+
57+
## A Few Repositories (or other OSS examples) using DSPy
58+
59+
| **Name** | **Description/Link** |
60+
|---|---|
61+
| **Stanford CS 224U Homework** | [Github](https://github.com/cgpotts/cs224u/blob/main/hw_openqa.ipynb) |
62+
| **STORM Report Generation (10,000 GitHub stars)** | [Github](https://github.com/stanford-oval/storm) |
63+
| **DSPy Redteaming** | [Github](https://github.com/haizelabs/dspy-redteam) |
64+
| **DSPy Theory of Mind** | [Github](https://github.com/plastic-labs/dspy-opentom) |
65+
| **Indic cross-lingual Natural Language Inference** | [Github](https://github.com/saifulhaq95/DSPy-Indic/blob/main/indicxlni.ipynb) |
66+
| **Optimizing LM for Text2SQL using DSPy** | [Github](https://github.com/jjovalle99/DSPy-Text2SQL) |
67+
| **DSPy PII Masking Demo by Eric Ness** | [Colab](https://colab.research.google.com/drive/1KZR1sGTp_RLWUJPAiK1FKPKI-Qn9neUm?usp=sharing) |
68+
| **DSPy on BIG-Bench Hard Example** | [Github](https://drchrislevy.github.io/posts/dspy/dspy.html) |
69+
| **Building a chess playing agent using DSPy** | [Github](https://medium.com/thoughts-on-machine-learning/building-a-chess-playing-agent-using-dspy-9b87c868f71e) |
70+
| **Ittia Research Fact Checking** | [Github](https://github.com/ittia-research/check) |
71+
| **Strategic Debate via Tree-of-Thought** | [Github](https://github.com/zbambergerNLP/strategic-debate-tot) |
72+
| **Sanskrit to English Translation App**| [Github](https://github.com/ganarajpr/sanskrit-translator-dspy) |
73+
| **DSPy for extracting features from PDFs on arXiv**| [Github](https://github.com/S1M0N38/dspy-arxiv) |
74+
| **DSPygen: DSPy in Ruby on Rails**| [Github](https://github.com/seanchatmangpt/dspygen) |
75+
| **DSPy Inspector**| [Github](https://github.com/Neoxelox/dspy-inspector) |
76+
| **DSPy with FastAPI**| [Github](https://github.com/diicellman/dspy-rag-fastapi) |
77+
| **DSPy for Indian Languages**| [Github](https://github.com/saifulhaq95/DSPy-Indic) |
78+
| **Hurricane: Blog Posts with Generative Feedback Loops!**| [Github](https://github.com/weaviate-tutorials/Hurricane) |
79+
| **RAG example using DSPy, Gradio, FastAPI, and Ollama**| [Github](https://github.com/diicellman/dspy-gradio-rag) |
80+
| **Synthetic Data Generation**| [Github](https://colab.research.google.com/drive/1CweVOu0qhTC0yOfW5QkLDRIKuAuWJKEr?usp=sharing) |
81+
| **Self Discover**| [Github](https://colab.research.google.com/drive/1GkAQKmw1XQgg5UNzzy8OncRe79V6pADB?usp=sharing) |
82+
83+
TODO: This list in particular is highly incomplete. There are a couple dozen other good ones.
84+
85+
## A Few Providers, Integrations, and related Blog Releases
86+
87+
| **Name** | **Link** |
88+
|---|---|
89+
| **Databricks** | [Link](https://www.databricks.com/blog/dspy-databricks) |
90+
| **Zenbase** | [Link](https://zenbase.ai/) |
91+
| **LangWatch** | [Link](https://langwatch.ai/blog/introducing-dspy-visualizer) |
92+
| **Gradient** | [Link](https://gradient.ai/blog/achieving-gpt-4-level-performance-at-lower-cost-using-dspy) |
93+
| **Snowflake** | [Link](https://medium.com/snowflake/dspy-snowflake-140d6d947d73) |
94+
| **Langchain** | [Link](https://python.langchain.com/v0.2/docs/integrations/providers/dspy/) |
95+
| **Weaviate** | [Link](https://weaviate.io/blog/dspy-optimizers) |
96+
| **Qdrant** | [Link](https://qdrant.tech/documentation/frameworks/dspy/) |
97+
| **Weights & Biases Weave** | [Link](https://weave-docs.wandb.ai/guides/integrations/dspy/) |
98+
| **Milvus** | [Link](https://milvus.io/docs/integrate_with_dspy.md) |
99+
| **Neo4j** | [Link](https://neo4j.com/labs/genai-ecosystem/dspy/) |
100+
| **Lightning AI** | [Link](https://lightning.ai/lightning-ai/studios/dspy-programming-with-foundation-models) |
101+
| **Haystack** | [Link](https://towardsdatascience.com/automating-prompt-engineering-with-dspy-and-haystack-926a637a3f43) |
102+
| **Arize** | [Link](https://docs.arize.com/phoenix/tracing/integrations-tracing/dspy) |
103+
| **LlamaIndex** | [Link](https://github.com/stanfordnlp/dspy/blob/main/examples/llamaindex/dspy_llamaindex_rag.ipynb) |
104+
| **Langtrace** | [Link](https://docs.langtrace.ai/supported-integrations/llm-frameworks/dspy) |
105+
| **Langfuse** | [Link](https://langfuse.com/docs/integrations/dspy) |
106+
107+
Credit: Some of these resources were originally compiled in the [Awesome DSPy](https://github.com/ganarajpr/awesome-dspy/tree/master) repo.

‎docs/docs/faqs.md‎

Lines changed: 0 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -165,11 +165,3 @@ with dspy.context(backoff_time = ..):
165165
```
166166

167167
At times, DSPy may have hard-coded arguments that are not relevant for your compatible, in which case, please free to open a PR alerting this or comment out these default settings for your usage.
168-
169-
## Contributing
170-
171-
**What if I have a better idea for prompting or synthetic data generation?** Perfect. We encourage you to think if it's best expressed as a module or an optimizer, and we'd love to merge it in DSPy so everyone can use it. DSPy is not a complete project; it's an ongoing effort to create structure (modules and optimizers) in place of hacky prompt and pipeline engineering tricks.
172-
173-
**How can I add my favorite LM or vector store?**
174-
175-
Check out these walkthroughs on setting up a [Custom LM client](/deep-dive/language_model_clients/custom-lm-client) and [Custom RM client](/deep-dive/retrieval_models_clients/custom-rm-client).

‎docs/docs/intro.md‎

Lines changed: 5 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,12 @@
11
---
22
sidebar_position: 1
3+
hide:
4+
- toc
5+
- navigation
6+
37
---
48

5-
# About DSPy
9+
# DSPy
610

711
![DSPy Logo](static/img/dspy_logo.png)
812

0 commit comments

Comments
 (0)