x

- Remove the client implementation (this breaks backwards compatibility
for existing testers. I could keep the stub in that file if we want, but
not many people are using it yet
- Add SDK as dependency
- Update the 'run_on_dataset' method to be a function that optionally
accepts a client as an argument
- Remove the langchain plus server implementation (you get it for free
with the SDK now)

We could make the SDK optional for now, but the plan is to use w/in the
tracer so it would likely become a hard dependency at some point.

README.md

@@ -2,6 +2,7 @@
 
 ⚡ Building applications with LLMs through composability ⚡
 
+[![Release Notes](https://img.shields.io/github/release/hwchase17/langchain)](https://github.com/hwchase17/langchain/releases)
 [![lint](https://github.com/hwchase17/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/lint.yml)
 [![test](https://github.com/hwchase17/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/test.yml)
 [![linkcheck](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml/badge.svg)](https://github.com/hwchase17/langchain/actions/workflows/linkcheck.yml)
@@ -12,6 +13,8 @@
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/hwchase17/langchain)
 [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/hwchase17/langchain)
 [![GitHub star chart](https://img.shields.io/github/stars/hwchase17/langchain?style=social)](https://star-history.com/#hwchase17/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/hwchase17/langchain)](https://libraries.io/github/hwchase17/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/hwchase17/langchain)](https://github.com/hwchase17/langchain/issues)
 
 
 Looking for the JS/TS version? Check out [LangChain.js](https://github.com/hwchase17/langchainjs).

docs/additional_resources/deploy_llms.rst

@@ -0,0 +1,137 @@
+
+===========================
+Deploying LLMs in Production
+===========================
+
+In today's fast-paced technological landscape, the use of Large Language Models (LLMs) is rapidly expanding. As a result, it's crucial for developers to understand how to effectively deploy these models in production environments. LLM interfaces typically fall into two categories:
+
+- **Case 1: Utilizing External LLM Providers (OpenAI, Anthropic, etc.)**
+    In this scenario, most of the computational burden is handled by the LLM providers, while LangChain simplifies the implementation of business logic around these services. This approach includes features such as prompt templating, chat message generation, caching, vector embedding database creation, preprocessing, etc.
+
+- **Case 2: Self-hosted Open-Source Models**
+    Alternatively, developers can opt to use smaller, yet comparably capable, self-hosted open-source LLM models. This approach can significantly decrease costs, latency, and privacy concerns associated with transferring data to external LLM providers.
+
+Regardless of the framework that forms the backbone of your product, deploying LLM applications comes with its own set of challenges. It's vital to understand the trade-offs and key considerations when evaluating serving frameworks.
+
+Outline
+=======
+
+This guide aims to provide a comprehensive overview of the requirements for deploying LLMs in a production setting, focusing on:
+
+- `Designing a Robust LLM Application Service <#robust>`_
+- `Maintaining Cost-Efficiency <#cost>`_
+- `Ensuring Rapid Iteration <#iteration>`_
+
+Understanding these components is crucial when assessing serving systems. LangChain integrates with several open-source projects designed to tackle these issues, providing a robust framework for productionizing your LLM applications. Some notable frameworks include:
+
+- `Ray Serve <../../../ecosystem/ray_serve.html>`_
+- `BentoML <https://github.com/ssheng/BentoChain>`_
+- `Modal <../../../ecosystem/modal.html>`_
+
+These links will provide further information on each ecosystem, assisting you in finding the best fit for your LLM deployment needs.
+
+Designing a Robust LLM Application Service
+===========================================
+.. _robust:
+
+When deploying an LLM service in production, it's imperative to provide a seamless user experience free from outages. Achieving 24/7 service availability involves creating and maintaining several sub-systems surrounding your application.
+
+Monitoring
+----------
+
+Monitoring forms an integral part of any system running in a production environment. In the context of LLMs, it is essential to monitor both performance and quality metrics.
+
+**Performance Metrics:** These metrics provide insights into the efficiency and capacity of your model. Here are some key examples:
+
+- Query per second (QPS): This measures the number of queries your model processes in a second, offering insights into its utilization.
+- Latency: This metric quantifies the delay from when your client sends a request to when they receive a response.
+- Tokens Per Second (TPS): This represents the number of tokens your model can generate in a second.
+
+**Quality Metrics:** These metrics are typically customized according to the business use-case. For instance, how does the output of your system compare to a baseline, such as a previous version? Although these metrics can be calculated offline, you need to log the necessary data to use them later.
+
+Fault tolerance
+---------------
+
+Your application may encounter errors such as exceptions in your model inference or business logic code, causing failures and disrupting traffic. Other potential issues could arise from the machine running your application, such as unexpected hardware breakdowns or loss of spot-instances during high-demand periods. One way to mitigate these risks is by increasing redundancy through replica scaling and implementing recovery mechanisms for failed replicas. However, model replicas aren't the only potential points of failure. It's essential to build resilience against various failures that could occur at any point in your stack.
+
+
+Zero down time upgrade
+----------------------
+
+System upgrades are often necessary but can result in service disruptions if not handled correctly. One way to prevent downtime during upgrades is by implementing a smooth transition process from the old version to the new one. Ideally, the new version of your LLM service is deployed, and traffic gradually shifts from the old to the new version, maintaining a constant QPS throughout the process.
+
+
+Load balancing
+--------------
+
+Load balancing, in simple terms, is a technique to distribute work evenly across multiple computers, servers, or other resources to optimize the utilization of the system, maximize throughput, minimize response time, and avoid overload of any single resource. Think of it as a traffic officer directing cars (requests) to different roads (servers) so that no single road becomes too congested.
+
+There are several strategies for load balancing. For example, one common method is the *Round Robin* strategy, where each request is sent to the next server in line, cycling back to the first when all servers have received a request. This works well when all servers are equally capable. However, if some servers are more powerful than others, you might use a *Weighted Round Robin* or *Least Connections* strategy, where more requests are sent to the more powerful servers, or to those currently handling the fewest active requests. Let's imagine you're running a LLM chain. If your application becomes popular, you could have hundreds or even thousands of users asking questions at the same time. If one server gets too busy (high load), the load balancer would direct new requests to another server that is less busy. This way, all your users get a timely response and the system remains stable.
+
+
+
+Maintaining Cost-Efficiency and Scalability
+============================================
+.. _cost:
+
+Deploying LLM services can be costly, especially when you're handling a large volume of user interactions. Charges by LLM providers are usually based on tokens used, making a chat system inference on these models potentially expensive. However, several strategies can help manage these costs without compromising the quality of the service.
+
+
+Self-hosting models
+-------------------
+
+Several smaller and open-source LLMs are emerging to tackle the issue of reliance on LLM providers. Self-hosting allows you to maintain similar quality to LLM provider models while managing costs. The challenge lies in building a reliable, high-performing LLM serving system on your own machines. 
+
+Resource Management and Auto-Scaling
+------------------------------------
+
+Computational logic within your application requires precise resource allocation. For instance, if part of your traffic is served by an OpenAI endpoint and another part by a self-hosted model, it's crucial to allocate suitable resources for each. Auto-scaling—adjusting resource allocation based on traffic—can significantly impact the cost of running your application. This strategy requires a balance between cost and responsiveness, ensuring neither resource over-provisioning nor compromised application responsiveness.
+
+Utilizing Spot Instances
+------------------------
+
+On platforms like AWS, spot instances offer substantial cost savings, typically priced at about a third of on-demand instances. The trade-off is a higher crash rate, necessitating a robust fault-tolerance mechanism for effective use.
+
+Independent Scaling
+-------------------
+
+When self-hosting your models, you should consider independent scaling. For example, if you have two translation models, one fine-tuned for French and another for Spanish, incoming requests might necessitate different scaling requirements for each.
+
+Batching requests
+-----------------
+
+In the context of Large Language Models, batching requests can enhance efficiency by better utilizing your GPU resources. GPUs are inherently parallel processors, designed to handle multiple tasks simultaneously. If you send individual requests to the model, the GPU might not be fully utilized as it's only working on a single task at a time. On the other hand, by batching requests together, you're allowing the GPU to work on multiple tasks at once, maximizing its utilization and improving inference speed. This not only leads to cost savings but can also improve the overall latency of your LLM service.
+
+
+In summary, managing costs while scaling your LLM services requires a strategic approach. Utilizing self-hosting models, managing resources effectively, employing auto-scaling, using spot instances, independently scaling models, and batching requests are key strategies to consider. Open-source libraries such as Ray Serve and BentoML are designed to deal with these complexities. 
+
+
+
+Ensuring Rapid Iteration
+========================
+
+.. _iteration:
+
+The LLM landscape is evolving at an unprecedented pace, with new libraries and model architectures being introduced constantly. Consequently, it's crucial to avoid tying yourself to a solution specific to one particular framework. This is especially relevant in serving, where changes to your infrastructure can be time-consuming, expensive, and risky. Strive for infrastructure that is not locked into any specific machine learning library or framework, but instead offers a general-purpose, scalable serving layer. Here are some aspects where flexibility plays a key role:
+
+Model composition
+-----------------
+
+Deploying systems like LangChain demands the ability to piece together different models and connect them via logic. Take the example of building a natural language input SQL query engine. Querying an LLM and obtaining the SQL command is only part of the system. You need to extract metadata from the connected database, construct a prompt for the LLM, run the SQL query on an engine, collect and feed back the response to the LLM as the query runs, and present the results to the user. This demonstrates the need to seamlessly integrate various complex components built in Python into a dynamic chain of logical blocks that can be served together.
+
+Cloud providers
+---------------
+
+Many hosted solutions are restricted to a single cloud provider, which can limit your options in today's multi-cloud world. Depending on where your other infrastructure components are built, you might prefer to stick with your chosen cloud provider.
+
+
+Infrastructure as Code (IaC)
+---------------------------
+
+Rapid iteration also involves the ability to recreate your infrastructure quickly and reliably. This is where Infrastructure as Code (IaC) tools like Terraform, CloudFormation, or Kubernetes YAML files come into play. They allow you to define your infrastructure in code files, which can be version controlled and quickly deployed, enabling faster and more reliable iterations.
+
+
+CI/CD
+-----
+
+In a fast-paced environment, implementing CI/CD pipelines can significantly speed up the iteration process. They help automate the testing and deployment of your LLM applications, reducing the risk of errors and enabling faster feedback and iteration.

docs/dependents.md

@@ -2,191 +2,230 @@
 
 Dependents stats for `hwchase17/langchain`
 
-[![](https://img.shields.io/static/v1?label=Used%20by&message=5152&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
-[![](https://img.shields.io/static/v1?label=Used%20by%20(public)&message=172&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
-[![](https://img.shields.io/static/v1?label=Used%20by%20(private)&message=4980&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
-[![](https://img.shields.io/static/v1?label=Used%20by%20(stars)&message=17239&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by&message=7484&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(public)&message=212&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(private)&message=7272&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(stars)&message=19095&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
 
-[update: 2023-05-17; only dependent repositories with Stars > 100]
+[update: 2023-06-05; only dependent repositories with Stars > 100]
 
 
 | Repository | Stars  |
 | :--------  | -----: |
-|[openai/openai-cookbook](https://github.com/openai/openai-cookbook) | 35401 |
-|[LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) | 32861 |
-|[microsoft/TaskMatrix](https://github.com/microsoft/TaskMatrix) | 32766 |
-|[hpcaitech/ColossalAI](https://github.com/hpcaitech/ColossalAI) | 29560 |
-|[reworkd/AgentGPT](https://github.com/reworkd/AgentGPT) | 22315 |
-|[imartinez/privateGPT](https://github.com/imartinez/privateGPT) | 17474 |
-|[openai/chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) | 16923 |
-|[mindsdb/mindsdb](https://github.com/mindsdb/mindsdb) | 16112 |
-|[jerryjliu/llama_index](https://github.com/jerryjliu/llama_index) | 15407 |
-|[mlflow/mlflow](https://github.com/mlflow/mlflow) | 14345 |
-|[GaiZhenbiao/ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT) | 10372 |
-|[databrickslabs/dolly](https://github.com/databrickslabs/dolly) | 9919 |
-|[AIGC-Audio/AudioGPT](https://github.com/AIGC-Audio/AudioGPT) | 8177 |
-|[logspace-ai/langflow](https://github.com/logspace-ai/langflow) | 6807 |
-|[imClumsyPanda/langchain-ChatGLM](https://github.com/imClumsyPanda/langchain-ChatGLM) | 6087 |
-|[arc53/DocsGPT](https://github.com/arc53/DocsGPT) | 5292 |
-|[e2b-dev/e2b](https://github.com/e2b-dev/e2b) | 4622 |
-|[nsarrazin/serge](https://github.com/nsarrazin/serge) | 4076 |
-|[madawei2699/myGPTReader](https://github.com/madawei2699/myGPTReader) | 3952 |
-|[zauberzeug/nicegui](https://github.com/zauberzeug/nicegui) | 3952 |
-|[go-skynet/LocalAI](https://github.com/go-skynet/LocalAI) | 3762 |
-|[GreyDGL/PentestGPT](https://github.com/GreyDGL/PentestGPT) | 3388 |
-|[mmabrouk/chatgpt-wrapper](https://github.com/mmabrouk/chatgpt-wrapper) | 3243 |
-|[zilliztech/GPTCache](https://github.com/zilliztech/GPTCache) | 3189 |
-|[wenda-LLM/wenda](https://github.com/wenda-LLM/wenda) | 3050 |
-|[marqo-ai/marqo](https://github.com/marqo-ai/marqo) | 2930 |
-|[gkamradt/langchain-tutorials](https://github.com/gkamradt/langchain-tutorials) | 2710 |
-|[PrefectHQ/marvin](https://github.com/PrefectHQ/marvin) | 2545 |
-|[project-baize/baize-chatbot](https://github.com/project-baize/baize-chatbot) | 2479 |
-|[whitead/paper-qa](https://github.com/whitead/paper-qa) | 2399 |
-|[langgenius/dify](https://github.com/langgenius/dify) | 2344 |
-|[GerevAI/gerev](https://github.com/GerevAI/gerev) | 2283 |
-|[hwchase17/chat-langchain](https://github.com/hwchase17/chat-langchain) | 2266 |
-|[guangzhengli/ChatFiles](https://github.com/guangzhengli/ChatFiles) | 1903 |
-|[Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo) | 1884 |
-|[OpenBMB/BMTools](https://github.com/OpenBMB/BMTools) | 1860 |
-|[Farama-Foundation/PettingZoo](https://github.com/Farama-Foundation/PettingZoo) | 1813 |
-|[OpenGVLab/Ask-Anything](https://github.com/OpenGVLab/Ask-Anything) | 1571 |
-|[IntelligenzaArtificiale/Free-Auto-GPT](https://github.com/IntelligenzaArtificiale/Free-Auto-GPT) | 1480 |
-|[hwchase17/notion-qa](https://github.com/hwchase17/notion-qa) | 1464 |
-|[NVIDIA/NeMo-Guardrails](https://github.com/NVIDIA/NeMo-Guardrails) | 1419 |
-|[Unstructured-IO/unstructured](https://github.com/Unstructured-IO/unstructured) | 1410 |
-|[Kav-K/GPTDiscord](https://github.com/Kav-K/GPTDiscord) | 1363 |
-|[paulpierre/RasaGPT](https://github.com/paulpierre/RasaGPT) | 1344 |
-|[StanGirard/quivr](https://github.com/StanGirard/quivr) | 1330 |
-|[lunasec-io/lunasec](https://github.com/lunasec-io/lunasec) | 1318 |
-|[vocodedev/vocode-python](https://github.com/vocodedev/vocode-python) | 1286 |
-|[agiresearch/OpenAGI](https://github.com/agiresearch/OpenAGI) | 1156 |
-|[h2oai/h2ogpt](https://github.com/h2oai/h2ogpt) | 1141 |
-|[jina-ai/thinkgpt](https://github.com/jina-ai/thinkgpt) | 1106 |
-|[yanqiangmiffy/Chinese-LangChain](https://github.com/yanqiangmiffy/Chinese-LangChain) | 1072 |
-|[ttengwang/Caption-Anything](https://github.com/ttengwang/Caption-Anything) | 1064 |
-|[jina-ai/dev-gpt](https://github.com/jina-ai/dev-gpt) | 1057 |
-|[juncongmoo/chatllama](https://github.com/juncongmoo/chatllama) | 1003 |
-|[greshake/llm-security](https://github.com/greshake/llm-security) | 1002 |
-|[visual-openllm/visual-openllm](https://github.com/visual-openllm/visual-openllm) | 957 |
-|[richardyc/Chrome-GPT](https://github.com/richardyc/Chrome-GPT) | 918 |
-|[irgolic/AutoPR](https://github.com/irgolic/AutoPR) | 886 |
-|[mmz-001/knowledge_gpt](https://github.com/mmz-001/knowledge_gpt) | 867 |
-|[thomas-yanxin/LangChain-ChatGLM-Webui](https://github.com/thomas-yanxin/LangChain-ChatGLM-Webui) | 850 |
-|[microsoft/X-Decoder](https://github.com/microsoft/X-Decoder) | 837 |
-|[peterw/Chat-with-Github-Repo](https://github.com/peterw/Chat-with-Github-Repo) | 826 |
-|[cirediatpl/FigmaChain](https://github.com/cirediatpl/FigmaChain) | 782 |
-|[hashintel/hash](https://github.com/hashintel/hash) | 778 |
-|[seanpixel/Teenage-AGI](https://github.com/seanpixel/Teenage-AGI) | 773 |
-|[jina-ai/langchain-serve](https://github.com/jina-ai/langchain-serve) | 738 |
-|[corca-ai/EVAL](https://github.com/corca-ai/EVAL) | 737 |
-|[ai-sidekick/sidekick](https://github.com/ai-sidekick/sidekick) | 717 |
-|[rlancemartin/auto-evaluator](https://github.com/rlancemartin/auto-evaluator) | 703 |
-|[poe-platform/api-bot-tutorial](https://github.com/poe-platform/api-bot-tutorial) | 689 |
-|[SamurAIGPT/Camel-AutoGPT](https://github.com/SamurAIGPT/Camel-AutoGPT) | 666 |
-|[eyurtsev/kor](https://github.com/eyurtsev/kor) | 608 |
-|[run-llama/llama-lab](https://github.com/run-llama/llama-lab) | 559 |
-|[namuan/dr-doc-search](https://github.com/namuan/dr-doc-search) | 544 |
-|[pieroit/cheshire-cat](https://github.com/pieroit/cheshire-cat) | 520 |
-|[griptape-ai/griptape](https://github.com/griptape-ai/griptape) | 514 |
-|[getmetal/motorhead](https://github.com/getmetal/motorhead) | 481 |
-|[hwchase17/chat-your-data](https://github.com/hwchase17/chat-your-data) | 462 |
-|[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 452 |
-|[jina-ai/agentchain](https://github.com/jina-ai/agentchain) | 439 |
-|[SamurAIGPT/ChatGPT-Developer-Plugins](https://github.com/SamurAIGPT/ChatGPT-Developer-Plugins) | 437 |
-|[alexanderatallah/window.ai](https://github.com/alexanderatallah/window.ai) | 433 |
-|[michaelthwan/searchGPT](https://github.com/michaelthwan/searchGPT) | 427 |
-|[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 425 |
-|[mckaywrigley/repo-chat](https://github.com/mckaywrigley/repo-chat) | 422 |
-|[whyiyhw/chatgpt-wechat](https://github.com/whyiyhw/chatgpt-wechat) | 421 |
-|[freddyaboulton/gradio-tools](https://github.com/freddyaboulton/gradio-tools) | 407 |
-|[jonra1993/fastapi-alembic-sqlmodel-async](https://github.com/jonra1993/fastapi-alembic-sqlmodel-async) | 395 |
-|[yeagerai/yeagerai-agent](https://github.com/yeagerai/yeagerai-agent) | 383 |
-|[akshata29/chatpdf](https://github.com/akshata29/chatpdf) | 374 |
-|[OpenGVLab/InternGPT](https://github.com/OpenGVLab/InternGPT) | 368 |
-|[ruoccofabrizio/azure-open-ai-embeddings-qna](https://github.com/ruoccofabrizio/azure-open-ai-embeddings-qna) | 358 |
-|[101dotxyz/GPTeam](https://github.com/101dotxyz/GPTeam) | 357 |
-|[mtenenholtz/chat-twitter](https://github.com/mtenenholtz/chat-twitter) | 354 |
-|[amosjyng/langchain-visualizer](https://github.com/amosjyng/langchain-visualizer) | 343 |
-|[msoedov/langcorn](https://github.com/msoedov/langcorn) | 334 |
-|[showlab/VLog](https://github.com/showlab/VLog) | 330 |
-|[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 324 |
-|[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 323 |
-|[daodao97/chatdoc](https://github.com/daodao97/chatdoc) | 320 |
-|[xuwenhao/geektime-ai-course](https://github.com/xuwenhao/geektime-ai-course) | 308 |
-|[StevenGrove/GPT4Tools](https://github.com/StevenGrove/GPT4Tools) | 301 |
-|[logan-markewich/llama_index_starter_pack](https://github.com/logan-markewich/llama_index_starter_pack) | 300 |
-|[andylokandy/gpt-4-search](https://github.com/andylokandy/gpt-4-search) | 299 |
-|[Anil-matcha/ChatPDF](https://github.com/Anil-matcha/ChatPDF) | 287 |
-|[itamargol/openai](https://github.com/itamargol/openai) | 273 |
-|[BlackHC/llm-strategy](https://github.com/BlackHC/llm-strategy) | 267 |
-|[momegas/megabots](https://github.com/momegas/megabots) | 259 |
-|[bborn/howdoi.ai](https://github.com/bborn/howdoi.ai) | 238 |
-|[Cheems-Seminar/grounded-segment-any-parts](https://github.com/Cheems-Seminar/grounded-segment-any-parts) | 232 |
-|[ur-whitelab/exmol](https://github.com/ur-whitelab/exmol) | 227 |
-|[sullivan-sean/chat-langchainjs](https://github.com/sullivan-sean/chat-langchainjs) | 227 |
-|[explosion/spacy-llm](https://github.com/explosion/spacy-llm) | 226 |
-|[recalign/RecAlign](https://github.com/recalign/RecAlign) | 218 |
-|[jupyterlab/jupyter-ai](https://github.com/jupyterlab/jupyter-ai) | 218 |
-|[alvarosevilla95/autolang](https://github.com/alvarosevilla95/autolang) | 215 |
-|[conceptofmind/toolformer](https://github.com/conceptofmind/toolformer) | 213 |
-|[MagnivOrg/prompt-layer-library](https://github.com/MagnivOrg/prompt-layer-library) | 209 |
-|[JohnSnowLabs/nlptest](https://github.com/JohnSnowLabs/nlptest) | 208 |
-|[airobotlab/KoChatGPT](https://github.com/airobotlab/KoChatGPT) | 197 |
-|[langchain-ai/auto-evaluator](https://github.com/langchain-ai/auto-evaluator) | 195 |
-|[yvann-hub/Robby-chatbot](https://github.com/yvann-hub/Robby-chatbot) | 195 |
-|[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 192 |
-|[daveebbelaar/langchain-experiments](https://github.com/daveebbelaar/langchain-experiments) | 189 |
-|[NimbleBoxAI/ChainFury](https://github.com/NimbleBoxAI/ChainFury) | 187 |
-|[kaleido-lab/dolphin](https://github.com/kaleido-lab/dolphin) | 184 |
-|[Anil-matcha/Website-to-Chatbot](https://github.com/Anil-matcha/Website-to-Chatbot) | 183 |
-|[plchld/InsightFlow](https://github.com/plchld/InsightFlow) | 180 |
-|[OpenBMB/AgentVerse](https://github.com/OpenBMB/AgentVerse) | 166 |
-|[benthecoder/ClassGPT](https://github.com/benthecoder/ClassGPT) | 166 |
-|[jbrukh/gpt-jargon](https://github.com/jbrukh/gpt-jargon) | 161 |
-|[hardbyte/qabot](https://github.com/hardbyte/qabot) | 160 |
-|[shaman-ai/agent-actors](https://github.com/shaman-ai/agent-actors) | 153 |
-|[radi-cho/datasetGPT](https://github.com/radi-cho/datasetGPT) | 153 |
-|[poe-platform/poe-protocol](https://github.com/poe-platform/poe-protocol) | 152 |
-|[paolorechia/learn-langchain](https://github.com/paolorechia/learn-langchain) | 149 |
-|[ajndkr/lanarky](https://github.com/ajndkr/lanarky) | 149 |
-|[fengyuli-dev/multimedia-gpt](https://github.com/fengyuli-dev/multimedia-gpt) | 147 |
-|[yasyf/compress-gpt](https://github.com/yasyf/compress-gpt) | 144 |
-|[homanp/superagent](https://github.com/homanp/superagent) | 143 |
-|[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 141 |
-|[ethanyanjiali/minChatGPT](https://github.com/ethanyanjiali/minChatGPT) | 141 |
-|[ccurme/yolopandas](https://github.com/ccurme/yolopandas) | 139 |
-|[hwchase17/langchain-streamlit-template](https://github.com/hwchase17/langchain-streamlit-template) | 138 |
-|[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 136 |
+|[openai/openai-cookbook](https://github.com/openai/openai-cookbook) | 38024 |
+|[LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) | 33609 |
+|[microsoft/TaskMatrix](https://github.com/microsoft/TaskMatrix) | 33136 |
+|[hpcaitech/ColossalAI](https://github.com/hpcaitech/ColossalAI) | 30032 |
+|[imartinez/privateGPT](https://github.com/imartinez/privateGPT) | 28094 |
+|[reworkd/AgentGPT](https://github.com/reworkd/AgentGPT) | 23430 |
+|[openai/chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) | 17942 |
+|[jerryjliu/llama_index](https://github.com/jerryjliu/llama_index) | 16697 |
+|[mindsdb/mindsdb](https://github.com/mindsdb/mindsdb) | 16410 |
+|[mlflow/mlflow](https://github.com/mlflow/mlflow) | 14517 |
+|[GaiZhenbiao/ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT) | 10793 |
+|[databrickslabs/dolly](https://github.com/databrickslabs/dolly) | 10155 |
+|[openai/evals](https://github.com/openai/evals) | 10076 |
+|[AIGC-Audio/AudioGPT](https://github.com/AIGC-Audio/AudioGPT) | 8619 |
+|[logspace-ai/langflow](https://github.com/logspace-ai/langflow) | 8211 |
+|[imClumsyPanda/langchain-ChatGLM](https://github.com/imClumsyPanda/langchain-ChatGLM) | 8154 |
+|[PromtEngineer/localGPT](https://github.com/PromtEngineer/localGPT) | 6853 |
+|[StanGirard/quivr](https://github.com/StanGirard/quivr) | 6830 |
+|[PipedreamHQ/pipedream](https://github.com/PipedreamHQ/pipedream) | 6520 |
+|[go-skynet/LocalAI](https://github.com/go-skynet/LocalAI) | 6018 |
+|[arc53/DocsGPT](https://github.com/arc53/DocsGPT) | 5643 |
+|[e2b-dev/e2b](https://github.com/e2b-dev/e2b) | 5075 |
+|[langgenius/dify](https://github.com/langgenius/dify) | 4281 |
+|[nsarrazin/serge](https://github.com/nsarrazin/serge) | 4228 |
+|[zauberzeug/nicegui](https://github.com/zauberzeug/nicegui) | 4084 |
+|[madawei2699/myGPTReader](https://github.com/madawei2699/myGPTReader) | 4039 |
+|[wenda-LLM/wenda](https://github.com/wenda-LLM/wenda) | 3871 |
+|[GreyDGL/PentestGPT](https://github.com/GreyDGL/PentestGPT) | 3837 |
+|[zilliztech/GPTCache](https://github.com/zilliztech/GPTCache) | 3625 |
+|[csunny/DB-GPT](https://github.com/csunny/DB-GPT) | 3545 |
+|[gkamradt/langchain-tutorials](https://github.com/gkamradt/langchain-tutorials) | 3404 |
+|[mmabrouk/chatgpt-wrapper](https://github.com/mmabrouk/chatgpt-wrapper) | 3303 |
+|[postgresml/postgresml](https://github.com/postgresml/postgresml) | 3052 |
+|[marqo-ai/marqo](https://github.com/marqo-ai/marqo) | 3014 |
+|[MineDojo/Voyager](https://github.com/MineDojo/Voyager) | 2945 |
+|[PrefectHQ/marvin](https://github.com/PrefectHQ/marvin) | 2761 |
+|[project-baize/baize-chatbot](https://github.com/project-baize/baize-chatbot) | 2673 |
+|[hwchase17/chat-langchain](https://github.com/hwchase17/chat-langchain) | 2589 |
+|[whitead/paper-qa](https://github.com/whitead/paper-qa) | 2572 |
+|[Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo) | 2366 |
+|[GerevAI/gerev](https://github.com/GerevAI/gerev) | 2330 |
+|[OpenGVLab/InternGPT](https://github.com/OpenGVLab/InternGPT) | 2289 |
+|[ParisNeo/gpt4all-ui](https://github.com/ParisNeo/gpt4all-ui) | 2159 |
+|[OpenBMB/BMTools](https://github.com/OpenBMB/BMTools) | 2158 |
+|[guangzhengli/ChatFiles](https://github.com/guangzhengli/ChatFiles) | 2005 |
+|[h2oai/h2ogpt](https://github.com/h2oai/h2ogpt) | 1939 |
+|[Farama-Foundation/PettingZoo](https://github.com/Farama-Foundation/PettingZoo) | 1845 |
+|[OpenGVLab/Ask-Anything](https://github.com/OpenGVLab/Ask-Anything) | 1749 |
+|[IntelligenzaArtificiale/Free-Auto-GPT](https://github.com/IntelligenzaArtificiale/Free-Auto-GPT) | 1740 |
+|[Unstructured-IO/unstructured](https://github.com/Unstructured-IO/unstructured) | 1628 |
+|[hwchase17/notion-qa](https://github.com/hwchase17/notion-qa) | 1607 |
+|[NVIDIA/NeMo-Guardrails](https://github.com/NVIDIA/NeMo-Guardrails) | 1544 |
+|[SamurAIGPT/privateGPT](https://github.com/SamurAIGPT/privateGPT) | 1543 |
+|[paulpierre/RasaGPT](https://github.com/paulpierre/RasaGPT) | 1526 |
+|[yanqiangmiffy/Chinese-LangChain](https://github.com/yanqiangmiffy/Chinese-LangChain) | 1485 |
+|[Kav-K/GPTDiscord](https://github.com/Kav-K/GPTDiscord) | 1402 |
+|[vocodedev/vocode-python](https://github.com/vocodedev/vocode-python) | 1387 |
+|[Chainlit/chainlit](https://github.com/Chainlit/chainlit) | 1336 |
+|[lunasec-io/lunasec](https://github.com/lunasec-io/lunasec) | 1323 |
+|[psychic-api/psychic](https://github.com/psychic-api/psychic) | 1248 |
+|[agiresearch/OpenAGI](https://github.com/agiresearch/OpenAGI) | 1208 |
+|[jina-ai/thinkgpt](https://github.com/jina-ai/thinkgpt) | 1193 |
+|[thomas-yanxin/LangChain-ChatGLM-Webui](https://github.com/thomas-yanxin/LangChain-ChatGLM-Webui) | 1182 |
+|[ttengwang/Caption-Anything](https://github.com/ttengwang/Caption-Anything) | 1137 |
+|[jina-ai/dev-gpt](https://github.com/jina-ai/dev-gpt) | 1135 |
+|[greshake/llm-security](https://github.com/greshake/llm-security) | 1086 |
+|[keephq/keep](https://github.com/keephq/keep) | 1063 |
+|[juncongmoo/chatllama](https://github.com/juncongmoo/chatllama) | 1037 |
+|[richardyc/Chrome-GPT](https://github.com/richardyc/Chrome-GPT) | 1035 |
+|[visual-openllm/visual-openllm](https://github.com/visual-openllm/visual-openllm) | 997 |
+|[mmz-001/knowledge_gpt](https://github.com/mmz-001/knowledge_gpt) | 995 |
+|[jina-ai/langchain-serve](https://github.com/jina-ai/langchain-serve) | 949 |
+|[irgolic/AutoPR](https://github.com/irgolic/AutoPR) | 936 |
+|[microsoft/X-Decoder](https://github.com/microsoft/X-Decoder) | 908 |
+|[poe-platform/api-bot-tutorial](https://github.com/poe-platform/api-bot-tutorial) | 902 |
+|[peterw/Chat-with-Github-Repo](https://github.com/peterw/Chat-with-Github-Repo) | 875 |
+|[cirediatpl/FigmaChain](https://github.com/cirediatpl/FigmaChain) | 822 |
+|[homanp/superagent](https://github.com/homanp/superagent) | 806 |
+|[seanpixel/Teenage-AGI](https://github.com/seanpixel/Teenage-AGI) | 800 |
+|[chatarena/chatarena](https://github.com/chatarena/chatarena) | 796 |
+|[hashintel/hash](https://github.com/hashintel/hash) | 795 |
+|[SamurAIGPT/Camel-AutoGPT](https://github.com/SamurAIGPT/Camel-AutoGPT) | 786 |
+|[rlancemartin/auto-evaluator](https://github.com/rlancemartin/auto-evaluator) | 770 |
+|[corca-ai/EVAL](https://github.com/corca-ai/EVAL) | 769 |
+|[101dotxyz/GPTeam](https://github.com/101dotxyz/GPTeam) | 755 |
+|[noahshinn024/reflexion](https://github.com/noahshinn024/reflexion) | 706 |
+|[eyurtsev/kor](https://github.com/eyurtsev/kor) | 695 |
+|[cheshire-cat-ai/core](https://github.com/cheshire-cat-ai/core) | 681 |
+|[e-johnstonn/BriefGPT](https://github.com/e-johnstonn/BriefGPT) | 656 |
+|[run-llama/llama-lab](https://github.com/run-llama/llama-lab) | 635 |
+|[griptape-ai/griptape](https://github.com/griptape-ai/griptape) | 583 |
+|[namuan/dr-doc-search](https://github.com/namuan/dr-doc-search) | 555 |
+|[getmetal/motorhead](https://github.com/getmetal/motorhead) | 550 |
+|[kreneskyp/ix](https://github.com/kreneskyp/ix) | 543 |
+|[hwchase17/chat-your-data](https://github.com/hwchase17/chat-your-data) | 510 |
+|[Anil-matcha/ChatPDF](https://github.com/Anil-matcha/ChatPDF) | 501 |
+|[whyiyhw/chatgpt-wechat](https://github.com/whyiyhw/chatgpt-wechat) | 497 |
+|[SamurAIGPT/ChatGPT-Developer-Plugins](https://github.com/SamurAIGPT/ChatGPT-Developer-Plugins) | 496 |
+|[microsoft/PodcastCopilot](https://github.com/microsoft/PodcastCopilot) | 492 |
+|[debanjum/khoj](https://github.com/debanjum/khoj) | 485 |
+|[akshata29/chatpdf](https://github.com/akshata29/chatpdf) | 485 |
+|[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 462 |
+|[jina-ai/agentchain](https://github.com/jina-ai/agentchain) | 460 |
+|[alexanderatallah/window.ai](https://github.com/alexanderatallah/window.ai) | 457 |
+|[yeagerai/yeagerai-agent](https://github.com/yeagerai/yeagerai-agent) | 451 |
+|[mckaywrigley/repo-chat](https://github.com/mckaywrigley/repo-chat) | 446 |
+|[michaelthwan/searchGPT](https://github.com/michaelthwan/searchGPT) | 446 |
+|[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 441 |
+|[freddyaboulton/gradio-tools](https://github.com/freddyaboulton/gradio-tools) | 439 |
+|[ruoccofabrizio/azure-open-ai-embeddings-qna](https://github.com/ruoccofabrizio/azure-open-ai-embeddings-qna) | 429 |
+|[StevenGrove/GPT4Tools](https://github.com/StevenGrove/GPT4Tools) | 422 |
+|[jonra1993/fastapi-alembic-sqlmodel-async](https://github.com/jonra1993/fastapi-alembic-sqlmodel-async) | 407 |
+|[msoedov/langcorn](https://github.com/msoedov/langcorn) | 405 |
+|[amosjyng/langchain-visualizer](https://github.com/amosjyng/langchain-visualizer) | 395 |
+|[ajndkr/lanarky](https://github.com/ajndkr/lanarky) | 384 |
+|[mtenenholtz/chat-twitter](https://github.com/mtenenholtz/chat-twitter) | 376 |
+|[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 371 |
+|[langchain-ai/auto-evaluator](https://github.com/langchain-ai/auto-evaluator) | 365 |
+|[xuwenhao/geektime-ai-course](https://github.com/xuwenhao/geektime-ai-course) | 358 |
+|[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 357 |
+|[opentensor/bittensor](https://github.com/opentensor/bittensor) | 347 |
+|[showlab/VLog](https://github.com/showlab/VLog) | 345 |
+|[daodao97/chatdoc](https://github.com/daodao97/chatdoc) | 345 |
+|[logan-markewich/llama_index_starter_pack](https://github.com/logan-markewich/llama_index_starter_pack) | 332 |
+|[poe-platform/poe-protocol](https://github.com/poe-platform/poe-protocol) | 320 |
+|[explosion/spacy-llm](https://github.com/explosion/spacy-llm) | 312 |
+|[andylokandy/gpt-4-search](https://github.com/andylokandy/gpt-4-search) | 311 |
+|[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 310 |
+|[jupyterlab/jupyter-ai](https://github.com/jupyterlab/jupyter-ai) | 294 |
+|[BlackHC/llm-strategy](https://github.com/BlackHC/llm-strategy) | 283 |
+|[itamargol/openai](https://github.com/itamargol/openai) | 281 |
+|[momegas/megabots](https://github.com/momegas/megabots) | 279 |
+|[personoids/personoids-lite](https://github.com/personoids/personoids-lite) | 277 |
+|[yvann-hub/Robby-chatbot](https://github.com/yvann-hub/Robby-chatbot) | 267 |
+|[Anil-matcha/Website-to-Chatbot](https://github.com/Anil-matcha/Website-to-Chatbot) | 266 |
+|[Cheems-Seminar/grounded-segment-any-parts](https://github.com/Cheems-Seminar/grounded-segment-any-parts) | 260 |
+|[sullivan-sean/chat-langchainjs](https://github.com/sullivan-sean/chat-langchainjs) | 248 |
+|[bborn/howdoi.ai](https://github.com/bborn/howdoi.ai) | 245 |
+|[daveebbelaar/langchain-experiments](https://github.com/daveebbelaar/langchain-experiments) | 240 |
+|[MagnivOrg/prompt-layer-library](https://github.com/MagnivOrg/prompt-layer-library) | 237 |
+|[ur-whitelab/exmol](https://github.com/ur-whitelab/exmol) | 234 |
+|[conceptofmind/toolformer](https://github.com/conceptofmind/toolformer) | 234 |
+|[recalign/RecAlign](https://github.com/recalign/RecAlign) | 226 |
+|[OpenBMB/AgentVerse](https://github.com/OpenBMB/AgentVerse) | 220 |
+|[alvarosevilla95/autolang](https://github.com/alvarosevilla95/autolang) | 219 |
+|[JohnSnowLabs/nlptest](https://github.com/JohnSnowLabs/nlptest) | 216 |
+|[kaleido-lab/dolphin](https://github.com/kaleido-lab/dolphin) | 215 |
+|[truera/trulens](https://github.com/truera/trulens) | 208 |
+|[NimbleBoxAI/ChainFury](https://github.com/NimbleBoxAI/ChainFury) | 208 |
+|[airobotlab/KoChatGPT](https://github.com/airobotlab/KoChatGPT) | 207 |
+|[monarch-initiative/ontogpt](https://github.com/monarch-initiative/ontogpt) | 200 |
+|[paolorechia/learn-langchain](https://github.com/paolorechia/learn-langchain) | 195 |
+|[shaman-ai/agent-actors](https://github.com/shaman-ai/agent-actors) | 185 |
+|[Haste171/langchain-chatbot](https://github.com/Haste171/langchain-chatbot) | 184 |
+|[plchld/InsightFlow](https://github.com/plchld/InsightFlow) | 182 |
+|[su77ungr/CASALIOY](https://github.com/su77ungr/CASALIOY) | 180 |
+|[jbrukh/gpt-jargon](https://github.com/jbrukh/gpt-jargon) | 177 |
+|[benthecoder/ClassGPT](https://github.com/benthecoder/ClassGPT) | 174 |
+|[billxbf/ReWOO](https://github.com/billxbf/ReWOO) | 170 |
+|[filip-michalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) | 168 |
+|[hwchase17/langchain-streamlit-template](https://github.com/hwchase17/langchain-streamlit-template) | 168 |
+|[radi-cho/datasetGPT](https://github.com/radi-cho/datasetGPT) | 164 |
+|[hardbyte/qabot](https://github.com/hardbyte/qabot) | 164 |
+|[gia-guar/JARVIS-ChatGPT](https://github.com/gia-guar/JARVIS-ChatGPT) | 158 |
+|[plastic-labs/tutor-gpt](https://github.com/plastic-labs/tutor-gpt) | 154 |
+|[yasyf/compress-gpt](https://github.com/yasyf/compress-gpt) | 154 |
+|[fengyuli-dev/multimedia-gpt](https://github.com/fengyuli-dev/multimedia-gpt) | 154 |
+|[ethanyanjiali/minChatGPT](https://github.com/ethanyanjiali/minChatGPT) | 153 |
+|[hwchase17/chroma-langchain](https://github.com/hwchase17/chroma-langchain) | 153 |
+|[edreisMD/plugnplai](https://github.com/edreisMD/plugnplai) | 148 |
+|[chakkaradeep/pyCodeAGI](https://github.com/chakkaradeep/pyCodeAGI) | 145 |
+|[ccurme/yolopandas](https://github.com/ccurme/yolopandas) | 145 |
+|[shamspias/customizable-gpt-chatbot](https://github.com/shamspias/customizable-gpt-chatbot) | 144 |
+|[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 143 |
+|[PradipNichite/Youtube-Tutorials](https://github.com/PradipNichite/Youtube-Tutorials) | 140 |
+|[gustavz/DataChad](https://github.com/gustavz/DataChad) | 140 |
+|[Klingefjord/chatgpt-telegram](https://github.com/Klingefjord/chatgpt-telegram) | 140 |
+|[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 139 |
+|[handrew/browserpilot](https://github.com/handrew/browserpilot) | 137 |
+|[jmpaz/promptlib](https://github.com/jmpaz/promptlib) | 137 |
+|[SamPink/dev-gpt](https://github.com/SamPink/dev-gpt) | 135 |
+|[menloparklab/langchain-cohere-qdrant-doc-retrieval](https://github.com/menloparklab/langchain-cohere-qdrant-doc-retrieval) | 135 |
 |[hirokidaichi/wanna](https://github.com/hirokidaichi/wanna) | 135 |
-|[Haste171/langchain-chatbot](https://github.com/Haste171/langchain-chatbot) | 134 |
-|[jmpaz/promptlib](https://github.com/jmpaz/promptlib) | 130 |
-|[Klingefjord/chatgpt-telegram](https://github.com/Klingefjord/chatgpt-telegram) | 130 |
-|[filip-michalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) | 128 |
-|[handrew/browserpilot](https://github.com/handrew/browserpilot) | 128 |
-|[shauryr/S2QA](https://github.com/shauryr/S2QA) | 127 |
-|[steamship-core/vercel-examples](https://github.com/steamship-core/vercel-examples) | 127 |
-|[yasyf/summ](https://github.com/yasyf/summ) | 127 |
-|[gia-guar/JARVIS-ChatGPT](https://github.com/gia-guar/JARVIS-ChatGPT) | 126 |
-|[jerlendds/osintbuddy](https://github.com/jerlendds/osintbuddy) | 125 |
-|[ibiscp/LLM-IMDB](https://github.com/ibiscp/LLM-IMDB) | 124 |
-|[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 124 |
-|[hwchase17/chroma-langchain](https://github.com/hwchase17/chroma-langchain) | 124 |
-|[menloparklab/langchain-cohere-qdrant-doc-retrieval](https://github.com/menloparklab/langchain-cohere-qdrant-doc-retrieval) | 123 |
-|[peterw/StoryStorm](https://github.com/peterw/StoryStorm) | 123 |
-|[chakkaradeep/pyCodeAGI](https://github.com/chakkaradeep/pyCodeAGI) | 123 |
-|[petehunt/langchain-github-bot](https://github.com/petehunt/langchain-github-bot) | 115 |
-|[su77ungr/CASALIOY](https://github.com/su77ungr/CASALIOY) | 113 |
-|[eunomia-bpf/GPTtrace](https://github.com/eunomia-bpf/GPTtrace) | 113 |
+|[steamship-core/vercel-examples](https://github.com/steamship-core/vercel-examples) | 134 |
+|[pablomarin/GPT-Azure-Search-Engine](https://github.com/pablomarin/GPT-Azure-Search-Engine) | 133 |
+|[ibiscp/LLM-IMDB](https://github.com/ibiscp/LLM-IMDB) | 133 |
+|[shauryr/S2QA](https://github.com/shauryr/S2QA) | 133 |
+|[jerlendds/osintbuddy](https://github.com/jerlendds/osintbuddy) | 132 |
+|[yuanjie-ai/ChatLLM](https://github.com/yuanjie-ai/ChatLLM) | 132 |
+|[yasyf/summ](https://github.com/yasyf/summ) | 132 |
+|[WongSaang/chatgpt-ui-server](https://github.com/WongSaang/chatgpt-ui-server) | 130 |
+|[peterw/StoryStorm](https://github.com/peterw/StoryStorm) | 127 |
+|[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 126 |
+|[vaibkumr/prompt-optimizer](https://github.com/vaibkumr/prompt-optimizer) | 125 |
+|[preset-io/promptimize](https://github.com/preset-io/promptimize) | 124 |
+|[homanp/vercel-langchain](https://github.com/homanp/vercel-langchain) | 124 |
+|[petehunt/langchain-github-bot](https://github.com/petehunt/langchain-github-bot) | 123 |
+|[eunomia-bpf/GPTtrace](https://github.com/eunomia-bpf/GPTtrace) | 118 |
+|[nicknochnack/LangchainDocuments](https://github.com/nicknochnack/LangchainDocuments) | 116 |
+|[jiran214/GPT-vup](https://github.com/jiran214/GPT-vup) | 112 |
+|[rsaryev/talk-codebase](https://github.com/rsaryev/talk-codebase) | 112 |
 |[zenml-io/zenml-projects](https://github.com/zenml-io/zenml-projects) | 112 |
-|[pablomarin/GPT-Azure-Search-Engine](https://github.com/pablomarin/GPT-Azure-Search-Engine) | 111 |
-|[shamspias/customizable-gpt-chatbot](https://github.com/shamspias/customizable-gpt-chatbot) | 109 |
-|[WongSaang/chatgpt-ui-server](https://github.com/WongSaang/chatgpt-ui-server) | 108 |
-|[davila7/file-gpt](https://github.com/davila7/file-gpt) | 104 |
-|[enhancedocs/enhancedocs](https://github.com/enhancedocs/enhancedocs) | 102 |
-|[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 101 |
-
+|[microsoft/azure-openai-in-a-day-workshop](https://github.com/microsoft/azure-openai-in-a-day-workshop) | 112 |
+|[davila7/file-gpt](https://github.com/davila7/file-gpt) | 112 |
+|[prof-frink-lab/slangchain](https://github.com/prof-frink-lab/slangchain) | 111 |
+|[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 110 |
+|[fixie-ai/fixie-examples](https://github.com/fixie-ai/fixie-examples) | 108 |
+|[miaoshouai/miaoshouai-assistant](https://github.com/miaoshouai/miaoshouai-assistant) | 105 |
+|[flurb18/AgentOoba](https://github.com/flurb18/AgentOoba) | 103 |
+|[solana-labs/chatgpt-plugin](https://github.com/solana-labs/chatgpt-plugin) | 102 |
+|[Significant-Gravitas/Auto-GPT-Benchmarks](https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks) | 102 |
+|[kaarthik108/snowChat](https://github.com/kaarthik108/snowChat) | 100 |
 
 
 _Generated by [github-dependents-info](https://github.com/nvuillam/github-dependents-info)_
 
-[github-dependents-info --repo hwchase17/langchain --markdownfile dependents.md --minstars 100 --sort stars]
+`github-dependents-info --repo hwchase17/langchain --markdownfile dependents.md --minstars 100 --sort stars`

docs/ecosystem/deployments.md

@@ -6,6 +6,11 @@ This section covers several options for that. Note that these options are meant
 
 What follows is a list of template GitHub repositories designed to be easily forked and modified to use your chain. This list is far from exhaustive, and we are EXTREMELY open to contributions here.
 
+## [Anyscale](https://www.anyscale.com/model-serving)
+
+Anyscale is a unified compute platform that makes it easy to develop, deploy, and manage scalable LLM applications in production using Ray.
+With Anyscale you can scale the most challenging LLM-based workloads and both develop and deploy LLM-based apps on a single compute platform.
+
 ## [Streamlit](https://github.com/hwchase17/langchain-streamlit-template)
 
 This repo serves as a template for how to deploy a LangChain with Streamlit.

docs/ecosystem/ray_serve.ipynb

@@ -0,0 +1,233 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Ray Serve\n",
+    "\n",
+    "[Ray Serve](https://docs.ray.io/en/latest/serve/index.html) is a scalable model serving library for building online inference APIs. Serve is particularly well suited for system composition, enabling you to build a complex inference service consisting of multiple chains and business logic all in Python code. "
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Goal of this notebook\n",
+    "This notebook shows a simple example of how to deploy an OpenAI chain into production. You can extend it to deploy your own self-hosted models where you can easily define amount of hardware resources (GPUs and CPUs) needed to run your model in production efficiently. Read more about available options including autoscaling in the Ray Serve [documentation](https://docs.ray.io/en/latest/serve/getting_started.html).\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup Ray Serve\n",
+    "Install ray with `pip install ray[serve]`. "
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## General Skeleton"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The general skeleton for deploying a service is the following:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 0: Import ray serve and request from starlette\n",
+    "from ray import serve\n",
+    "from starlette.requests import Request\n",
+    "\n",
+    "# 1: Define a Ray Serve deployment.\n",
+    "@serve.deployment\n",
+    "class LLMServe:\n",
+    "\n",
+    "    def __init__(self) -> None:\n",
+    "        # All the initialization code goes here\n",
+    "        pass\n",
+    "\n",
+    "    async def __call__(self, request: Request) -> str:\n",
+    "        # You can parse the request here\n",
+    "        # and return a response\n",
+    "        return \"Hello World\"\n",
+    "\n",
+    "# 2: Bind the model to deployment\n",
+    "deployment = LLMServe.bind()\n",
+    "\n",
+    "# 3: Run the deployment\n",
+    "serve.api.run(deployment)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Shutdown the deployment\n",
+    "serve.api.shutdown()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example of deploying and OpenAI chain with custom prompts"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Get an OpenAI API key from [here](https://platform.openai.com/account/api-keys). By running the following code, you will be asked to provide your API key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from getpass import getpass\n",
+    "OPENAI_API_KEY = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@serve.deployment\n",
+    "class DeployLLM:\n",
+    "\n",
+    "    def __init__(self):\n",
+    "        # We initialize the LLM, template and the chain here\n",
+    "        llm = OpenAI(openai_api_key=OPENAI_API_KEY)\n",
+    "        template = \"Question: {question}\\n\\nAnswer: Let's think step by step.\"\n",
+    "        prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
+    "        self.chain = LLMChain(llm=llm, prompt=prompt)\n",
+    "\n",
+    "    def _run_chain(self, text: str):\n",
+    "        return self.chain(text)\n",
+    "\n",
+    "    async def __call__(self, request: Request):\n",
+    "        # 1. Parse the request\n",
+    "        text = request.query_params[\"text\"]\n",
+    "        # 2. Run the chain\n",
+    "        resp = self._run_chain(text)\n",
+    "        # 3. Return the response\n",
+    "        return resp[\"text\"]"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now we can bind the deployment."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Bind the model to deployment\n",
+    "deployment = DeployLLM.bind()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We can assign the port number and host when we want to run the deployment. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Example port number\n",
+    "PORT_NUMBER = 8282\n",
+    "# Run the deployment\n",
+    "serve.api.run(deployment, port=PORT_NUMBER)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now that service is deployed on port `localhost:8282` we can send a post request to get the results back."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "\n",
+    "text = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "response = requests.post(f'http://localhost:{PORT_NUMBER}/?text={text}')\n",
+    "print(response.content.decode())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ray",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/getting_started/tutorials.md

@@ -10,7 +10,8 @@
 
 ### Tutorials
 [LangChain Tutorials](https://www.youtube.com/watch?v=FuqdVNB_8c0&list=PL9V0lbeJ69brU-ojMpU1Y7Ic58Tap0Cw6) by [Edrick](https://www.youtube.com/@edrickdch):
-- ⛓ [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0) 
+- ⛓ [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
+- ⛓ [LangChain 101: The Complete Beginner's Guide](https://youtu.be/P3MAbZ2eMUI) 
 
 [LangChain Crash Course: Build an AutoGPT app in 25 minutes](https://youtu.be/MlK6SIjcjE8) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
 

docs/index.rst

@@ -176,6 +176,8 @@ Additional Resources
 
 - `Gallery <https://github.com/kyrolabs/awesome-langchain>`_: A collection of great projects that use Langchain, compiled by the folks at `Kyrolabs <https://kyrolabs.com>`_. Useful for finding inspiration and example implementations.
 
+- `Deploying LLMs in Production <./additional_resources/deploy_llms.html>`_: A collection of best practices and tutorials for deploying LLMs in production.
+
 - `Tracing <./additional_resources/tracing.html>`_: A guide on using tracing in LangChain to visualize the execution of chains and agents.
 
 - `Model Laboratory <./additional_resources/model_laboratory.html>`_: Experimenting with different prompts, models, and chains is a big part of developing the best possible application. The ModelLaboratory makes it easy to do so.
@@ -194,6 +196,8 @@ Additional Resources
    :hidden:
 
    LangChainHub <https://github.com/hwchase17/langchain-hub>
+   ./additional_resources/deployments.md
+   ./additional_resources/deploy_llms.rst
    Gallery <https://github.com/kyrolabs/awesome-langchain>
    ./additional_resources/tracing.md
    ./additional_resources/model_laboratory.ipynb

docs/integrations/amazon_bedrock.md

@@ -18,7 +18,7 @@ from langchain import Bedrock
 
 ## Text Embedding Models
 
-See a [usage example](../modules/models/text_embedding/examples/bedrock.ipynb).
+See a [usage example](../modules/models/text_embedding/examples/amazon_bedrock.ipynb).
 ```python
 from langchain.embeddings import BedrockEmbeddings
 ```

docs/integrations/annoy.md

@@ -0,0 +1,18 @@
+# Annoy
+
+> [Annoy](https://github.com/spotify/annoy) (`Approximate Nearest Neighbors Oh Yeah`) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mmapped into memory so that many processes may share the same data. 
+## Installation and Setup
+
+
+```bash
+pip install annoy
+```
+
+
+## Vectorstore
+
+See a [usage example](../modules/indexes/vectorstores/examples/annoy.ipynb).
+
+```python
+from langchain.vectorstores import Annoy
+```

docs/integrations/anthropic.md

@@ -0,0 +1,26 @@
+# Anthropic
+
+>[Anthropic](https://en.wikipedia.org/wiki/Anthropic) is an American artificial intelligence (AI) startup and 
+> public-benefit corporation, founded by former members of OpenAI. `Anthropic` specializes in developing general AI 
+> systems and language models, with a company ethos of responsible AI usage.
+> `Anthropic` develops a chatbot, named `Claude`. Similar to `ChatGPT`, `Claude` uses a messaging 
+> interface where users can submit questions or requests and receive highly detailed and relevant responses.
+ 
+## Installation and Setup
+
+
+```bash
+pip install anthropic
+```
+
+See the [setup documentation](https://console.anthropic.com/docs/access).
+
+
+
+## Chat Models
+
+See a [usage example](../modules/models/chat/integrations/anthropic.ipynb)
+
+```python
+from langchain.chat_models import ChatAnthropic
+```

docs/integrations/arxiv.md

@@ -26,3 +26,11 @@ See a [usage example](../modules/indexes/document_loaders/examples/arxiv.ipynb).
 ```python
 from langchain.document_loaders import ArxivLoader
 ```
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/arxiv.ipynb).
+
+```python
+from langchain.retrievers import ArxivRetriever
+```

docs/integrations/azure_cognitive_search_.md

@@ -0,0 +1,24 @@
+# Azure Cognitive Search
+
+>[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.
+
+>Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:
+>- A search engine for full text search over a search index containing user-owned content
+>- Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation
+>- Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more
+>- Programmability through REST APIs and client libraries in Azure SDKs
+>- Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)
+
+
+## Installation and Setup
+
+See [set up instructions](https://learn.microsoft.com/en-us/azure/search/search-create-service-portal).
+
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/azure_cognitive_search.ipynb).
+
+```python
+from langchain.retrievers import AzureCognitiveSearchRetriever
+```

docs/integrations/beam.md

@@ -1,7 +1,8 @@
 # Beam
 
-This page covers how to use Beam within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Beam wrappers.
+>[Beam](https://docs.beam.cloud/introduction) makes it easy to run code on GPUs, deploy scalable web APIs, 
+> schedule cron jobs, and run massively parallel workloads — without managing any infrastructure.
+ 
 
 ## Installation and Setup
 
@@ -9,19 +10,19 @@ It is broken into two parts: installation and setup, and then references to spec
 - Install the Beam CLI with `curl https://raw.githubusercontent.com/slai-labs/get-beam/main/get-beam.sh -sSfL | sh`
 - Register API keys with `beam configure`
 - Set environment variables (`BEAM_CLIENT_ID`) and (`BEAM_CLIENT_SECRET`)
-- Install the Beam SDK `pip install beam-sdk`
+- Install the Beam SDK:
+```bash
+pip install beam-sdk
+```
 
-## Wrappers
+## LLM
 
-### LLM
-
-There exists a Beam LLM wrapper, which you can access with
 
 ```python
 from langchain.llms.beam import Beam
 ```
 
-## Define your Beam app.
+### Example of the Beam app
 
 This is the environment you’ll be developing against once you start the app.
 It's also used to define the maximum response length from the model.
@@ -44,7 +45,7 @@ llm = Beam(model_name="gpt2",
            verbose=False)
 ```
 
-## Deploy your Beam app
+### Deploy the Beam app
 
 Once defined, you can deploy your Beam app by calling your model's `_deploy()` method.
 
@@ -52,9 +53,9 @@ Once defined, you can deploy your Beam app by calling your model's `_deploy()` m
 llm._deploy()
 ```
 
-## Call your Beam app
+### Call the Beam app
 
-Once a beam model is deployed, it can be called by callying your model's `_call()` method.
+Once a beam model is deployed, it can be called by calling your model's `_call()` method.
 This returns the GPT2 text response to your prompt.
 
 ```python

docs/integrations/cassandra.md

@@ -0,0 +1,23 @@
+# Cassandra
+
+>[Cassandra](https://en.wikipedia.org/wiki/Apache_Cassandra) is a free and open-source, distributed, wide-column 
+> store, NoSQL database management system designed to handle large amounts of data across many commodity servers, 
+> providing high availability with no single point of failure. `Cassandra` offers support for clusters spanning 
+> multiple datacenters, with asynchronous masterless replication allowing low latency operations for all clients. 
+> `Cassandra` was designed to implement a combination of `Amazon's Dynamo` distributed storage and replication 
+> techniques combined with `Google's Bigtable` data and storage engine model.
+ 
+## Installation and Setup
+
+```bash
+pip install cassandra-drive
+```
+
+
+## Memory
+
+See a [usage example](../modules/memory/examples/cassandra_chat_message_history.ipynb).
+
+```python
+from langchain.memory import CassandraChatMessageHistory
+```

docs/integrations/chroma.md

@@ -1,20 +1,29 @@
 # Chroma
 
-This page covers how to use the Chroma ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Chroma wrappers.
+>[Chroma](https://docs.trychroma.com/getting-started) is a database for building AI applications with embeddings.
 
 ## Installation and Setup
-- Install the Python package with `pip install chromadb`
-## Wrappers
 
-### VectorStore
+```bash
+pip install chromadb
+```
+
+
+## VectorStore
 
 There exists a wrapper around Chroma vector databases, allowing you to use it as a vectorstore,
 whether for semantic search or example selection.
 
-To import this vectorstore:
 ```python
 from langchain.vectorstores import Chroma
 ```
 
 For a more detailed walkthrough of the Chroma wrapper, see [this notebook](../modules/indexes/vectorstores/getting_started.ipynb)
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/chroma_self_query.ipynb).
+
+```python
+from langchain.retrievers import SelfQueryRetriever
+```

docs/integrations/clickhouse.md

@@ -0,0 +1,52 @@
+# ClickHouse
+
+This page covers how to use ClickHouse Vector Search within LangChain.
+
+[ClickHouse](https://clickhouse.com) is a open source real-time OLAP database with full SQL support and a wide range of functions to assist users in writing analytical queries. Some of these functions and data structures perform distance operations between vectors, enabling ClickHouse to be used as a vector database.
+
+Due to the fully parallelized query pipeline, ClickHouse can process vector search operations very quickly, especially when performing exact matching through a linear scan over all rows, delivering processing speed comparable to dedicated vector databases.
+
+High compression levels, tunable through custom compression codecs, enable very large datasets to be stored and queried. ClickHouse is not memory-bound, allowing multi-TB datasets containing embeddings to be queried.
+
+The capabilities for computing the distance between two vectors are just another SQL function and can be effectively combined with more traditional SQL filtering and aggregation capabilities. This allows vectors to be stored and queried alongside metadata, and even rich text, enabling a broad array of use cases and applications.
+
+Finally, experimental ClickHouse capabilities like [Approximate Nearest Neighbour (ANN) indices](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) support faster approximate matching of vectors and provide a promising development aimed to further enhance the vector matching capabilities of ClickHouse.
+
+## Installation
+- Install clickhouse server by [binary](https://clickhouse.com/docs/en/install) or [docker image](https://hub.docker.com/r/clickhouse/clickhouse-server/)
+- Install the Python SDK with `pip install clickhouse-connect`
+
+### Configure clickhouse vector index
+
+Customize `ClickhouseSettings` object with parameters
+
+    ```python
+    from langchain.vectorstores import ClickHouse, ClickhouseSettings
+    config = ClickhouseSettings(host="<clickhouse-server-host>", port=8123, ...)
+    index = Clickhouse(embedding_function, config)
+    index.add_documents(...)
+    ```
+  
+## Wrappers
+supported functions:
+- `add_texts`
+- `add_documents`
+- `from_texts`
+- `from_documents`
+- `similarity_search`
+- `asimilarity_search`
+- `similarity_search_by_vector`
+- `asimilarity_search_by_vector`
+- `similarity_search_with_relevance_scores`
+
+### VectorStore
+
+There exists a wrapper around open source Clickhouse database, allowing you to use it as a vectorstore,
+whether for semantic search or similar example retrieval.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import Clickhouse
+```
+
+For a more detailed walkthrough of the MyScale wrapper, see [this notebook](../modules/indexes/vectorstores/examples/clickhouse.ipynb)

docs/integrations/cohere.md

@@ -1,25 +1,38 @@
 # Cohere
 
-This page covers how to use the Cohere ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Cohere wrappers.
+>[Cohere](https://cohere.ai/about) is a Canadian startup that provides natural language processing models
+> that help companies improve human-machine interactions.
 
 ## Installation and Setup
-- Install the Python SDK with `pip install cohere`
-- Get an Cohere api key and set it as an environment variable (`COHERE_API_KEY`)
+- Install the Python SDK :
+```bash
+pip install cohere
+```
 
-## Wrappers
+Get a [Cohere api key](https://dashboard.cohere.ai/) and set it as an environment variable (`COHERE_API_KEY`)
 
-### LLM
+
+## LLM
 
 There exists an Cohere LLM wrapper, which you can access with 
+See a [usage example](../modules/models/llms/integrations/cohere.ipynb).
+
 ```python
 from langchain.llms import Cohere
 ```
 
-### Embeddings
+## Text Embedding Model
 
-There exists an Cohere Embeddings wrapper, which you can access with 
+There exists an Cohere Embedding model, which you can access with 
 ```python
 from langchain.embeddings import CohereEmbeddings
 ```
 For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/cohere.ipynb)
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/cohere-reranker.ipynb).
+
+```python
+from langchain.retrievers.document_compressors import CohereRerank
+```

docs/integrations/databerry.md

@@ -1,25 +1,17 @@
 # Databerry
 
-This page covers how to use the [Databerry](https://databerry.ai) within LangChain.
+>[Databerry](https://databerry.ai) is an [open source](https://github.com/gmpetrov/databerry) document retrieval platform that helps to connect your personal data with Large Language Models.
 
-## What is Databerry?
 
-Databerry is an [open source](https://github.com/gmpetrov/databerry) document retrievial platform that helps to connect your personal data with Large Language Models.
+## Installation and Setup
 
-![Databerry](../_static/DataberryDashboard.png)
+We need to sign up for Databerry, create a datastore, add some data and get your datastore api endpoint url. 
+We need the [API Key](https://docs.databerry.ai/api-reference/authentication).
 
-## Quick start
+## Retriever
 
-Retrieving documents stored in Databerry from LangChain is very easy!
+See a [usage example](../modules/indexes/retrievers/examples/databerry.ipynb).
 
 ```python
 from langchain.retrievers import DataberryRetriever
-
-retriever = DataberryRetriever(
-    datastore_url="https://api.databerry.ai/query/clg1xg2h80000l708dymr0fxc",
-    # api_key="DATABERRY_API_KEY", # optional if datastore is public
-    # top_k=10 # optional
-)
-
-docs = retriever.get_relevant_documents("What's Databerry?")
 ```

docs/integrations/elasticsearch.md

@@ -0,0 +1,24 @@
+# Elasticsearch
+
+>[Elasticsearch](https://www.elastic.co/elasticsearch/) is a distributed, RESTful search and analytics engine. 
+> It provides a distributed, multi-tenant-capable full-text search engine with an HTTP web interface and schema-free 
+> JSON documents.
+
+
+## Installation and Setup
+
+```bash
+pip install elasticsearch
+```
+
+## Retriever
+
+>In information retrieval, [Okapi BM25](https://en.wikipedia.org/wiki/Okapi_BM25) (BM is an abbreviation of best matching) is a ranking function used by search engines to estimate the relevance of documents to a given search query. It is based on the probabilistic retrieval framework developed in the 1970s and 1980s by Stephen E. Robertson, Karen Spärck Jones, and others.
+
+>The name of the actual ranking function is BM25. The fuller name, Okapi BM25, includes the name of the first system to use it, which was the Okapi information retrieval system, implemented at London's City University in the 1980s and 1990s. BM25 and its newer variants, e.g. BM25F (a version of BM25 that can take document structure and anchor text into account), represent TF-IDF-like retrieval functions used in document retrieval.
+
+See a [usage example](../modules/indexes/retrievers/examples/elastic_search_bm25.ipynb).
+
+```python
+from langchain.retrievers import ElasticSearchBM25Retriever
+```

docs/integrations/google_vertex_ai.md

@@ -0,0 +1,24 @@
+# Google Vertex AI
+
+>[Vertex AI](https://cloud.google.com/vertex-ai/docs/start/introduction-unified-platform) is a machine learning (ML) 
+> platform that lets you train and deploy ML models and AI applications. 
+> `Vertex AI` combines data engineering, data science, and ML engineering workflows, enabling your teams to 
+> collaborate using a common toolset.
+ 
+## Installation and Setup
+
+
+```bash
+pip install google-cloud-aiplatform
+```
+
+See the [setup instructions](../modules/models/chat/integrations/google_vertex_ai_palm.ipynb)
+
+
+## Chat Models
+
+See a [usage example](../modules/models/chat/integrations/google_vertex_ai_palm.ipynb)
+
+```python
+from langchain.chat_models import ChatVertexAI
+```

docs/integrations/huggingface.md

@@ -47,7 +47,7 @@ To use a the wrapper for a model hosted on Hugging Face Hub:
 ```python
 from langchain.embeddings import HuggingFaceHubEmbeddings
 ```
-For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/huggingfacehub.ipynb)
+For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/huggingface_hub.ipynb)
 
 ### Tokenizer
 

docs/integrations/momento.md

@@ -1,20 +1,21 @@
 # Momento
 
+>[Momento Cache](https://docs.momentohq.com/) is the world's first truly serverless caching service. It provides instant elasticity, scale-to-zero 
+> capability, and blazing-fast performance.  
+> With Momento Cache, you grab the SDK, you get an end point, input a few lines into your code, and you're off and running.
+
 This page covers how to use the [Momento](https://gomomento.com) ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Momento wrappers.
 
 ## Installation and Setup
 
 - Sign up for a free account [here](https://docs.momentohq.com/getting-started) and get an auth token
 - Install the Momento Python SDK with `pip install momento`
 
-## Wrappers
 
-### Cache
+## Cache
 
 The Cache wrapper allows for [Momento](https://gomomento.com) to be used as a serverless, distributed, low-latency cache for LLM prompts and responses.
 
-#### Standard Cache
 
 The standard cache is the go-to use case for [Momento](https://gomomento.com) users in any environment.
 
@@ -44,10 +45,10 @@ cache_name = "langchain"
 langchain.llm_cache = MomentoCache(cache_client, cache_name)
 ```
 
-### Memory
+## Memory
 
 Momento can be used as a distributed memory store for LLMs.
 
-#### Chat Message History Memory
+### Chat Message History Memory
 
 See [this notebook](../modules/memory/examples/momento_chat_message_history.ipynb) for a walkthrough of how to use Momento as a memory store for chat message history.

docs/integrations/openai.md

@@ -35,7 +35,6 @@ from langchain.llms import AzureOpenAI
 For a more detailed walkthrough of the `Azure` wrapper, see [this notebook](../modules/models/llms/integrations/azure_openai_example.ipynb)
 
 
-
 ## Text Embedding Model
 
 ```python
@@ -44,6 +43,14 @@ from langchain.embeddings import OpenAIEmbeddings
 For a more detailed walkthrough of this, see [this notebook](../modules/models/text_embedding/examples/openai.ipynb)
 
 
+## Chat Model
+
+```python
+from langchain.chat_models import ChatOpenAI
+```
+For a more detailed walkthrough of this, see [this notebook](../modules/models/chat/integrations/openai.ipynb)
+
+
 ## Tokenizer
 
 There are several places you can use the `tiktoken` tokenizer. By default, it is used to count tokens
@@ -71,3 +78,11 @@ See a [usage example](../modules/indexes/document_loaders/examples/chatgpt_loade
 ```python
 from langchain.document_loaders.chatgpt import ChatGPTLoader
 ```
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/chatgpt-plugin.ipynb).
+
+```python
+from langchain.retrievers import ChatGPTPluginRetriever
+```

docs/integrations/pinecone.md

@@ -4,17 +4,19 @@ This page covers how to use the Pinecone ecosystem within LangChain.
 It is broken into two parts: installation and setup, and then references to specific Pinecone wrappers.
 
 ## Installation and Setup
-- Install the Python SDK with `pip install pinecone-client`
-## Wrappers
+Install the Python SDK:
+```bash
+pip install pinecone-client
+```
 
-### VectorStore
+
+## Vectorstore
 
 There exists a wrapper around Pinecone indexes, allowing you to use it as a vectorstore,
 whether for semantic search or example selection.
 
-To import this vectorstore:
 ```python
 from langchain.vectorstores import Pinecone
 ```
 
-For a more detailed walkthrough of the Pinecone wrapper, see [this notebook](../modules/indexes/vectorstores/examples/pinecone.ipynb)
+For a more detailed walkthrough of the Pinecone vectorstore, see [this notebook](../modules/indexes/vectorstores/examples/pinecone.ipynb)

docs/integrations/predictionguard.md

@@ -1,19 +1,23 @@
 # Prediction Guard
 
-This page covers how to use the Prediction Guard ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific Prediction Guard wrappers.
+>[Prediction Guard](https://docs.predictionguard.com/) gives a quick and easy access to state-of-the-art open and closed access LLMs, without  needing to spend days and weeks figuring out all of the implementation details, managing a bunch of different API specs, and setting up the infrastructure for model deployments.
+
 
 ## Installation and Setup
-- Install the Python SDK with `pip install predictionguard`
+- Install the Python SDK:
+```bash
+pip install predictionguard
+```
+
 - Get an Prediction Guard access token (as described [here](https://docs.predictionguard.com/)) and set it as an environment variable (`PREDICTIONGUARD_TOKEN`)
 
-## LLM Wrapper
+## LLM 
 
-There exists a Prediction Guard LLM wrapper, which you can access with 
 ```python
 from langchain.llms import PredictionGuard
 ```
 
+### Example
 You can provide the name of the Prediction Guard model as an argument when initializing the LLM:
 ```python
 pgllm = PredictionGuard(model="MPT-7B-Instruct")
@@ -24,14 +28,12 @@ You can also provide your access token directly as an argument:
 pgllm = PredictionGuard(model="MPT-7B-Instruct", token="<your access token>")
 ```
 
-Finally, you can provide an "output" argument that is used to structure/ control the output of the LLM:
+Also, you can provide an "output" argument that is used to structure/ control the output of the LLM:
 ```python
 pgllm = PredictionGuard(model="MPT-7B-Instruct", output={"type": "boolean"})
 ```
 
-## Example usage
-
-Basic usage of the controlled or guarded LLM wrapper:
+#### Basic usage of the controlled or guarded LLM:
 ```python
 import os
 
@@ -72,7 +74,7 @@ pgllm = PredictionGuard(model="MPT-7B-Instruct",
 pgllm(prompt.format(query="What kind of post is this?"))
 ```
 
-Basic LLM Chaining with the Prediction Guard wrapper:
+#### Basic LLM Chaining with the Prediction Guard:
 ```python
 import os
 

docs/integrations/promptlayer.md

@@ -1,31 +1,35 @@
 # PromptLayer
 
-This page covers how to use [PromptLayer](https://www.promptlayer.com) within LangChain.
-It is broken into two parts: installation and setup, and then references to specific PromptLayer wrappers.
+>[PromptLayer](https://docs.promptlayer.com/what-is-promptlayer/wxpF9EZkUwvdkwvVE9XEvC/how-promptlayer-works/dvgGSxNe6nB1jj8mUVbG8r) 
+> is a devtool that allows you to track, manage, and share your GPT prompt engineering. 
+> It acts as a middleware between your code and OpenAI's python library, recording all your API requests 
+> and saving relevant metadata for easy exploration and search in the [PromptLayer](https://www.promptlayer.com) dashboard.
 
 ## Installation and Setup
 
-If you want to work with PromptLayer:
-- Install the promptlayer python library `pip install promptlayer`
+- Install the `promptlayer` python library 
+```bash
+pip install promptlayer
+```
 - Create a PromptLayer account
 - Create an api token and set it as an environment variable (`PROMPTLAYER_API_KEY`)
 
-## Wrappers
 
-### LLM
+## LLM
 
-There exists an PromptLayer OpenAI LLM wrapper, which you can access with
 ```python
 from langchain.llms import PromptLayerOpenAI
 ```
 
-To tag your requests, use the argument `pl_tags` when instanializing the LLM
+### Example
+
+To tag your requests, use the argument `pl_tags` when instantiating the LLM
 ```python
 from langchain.llms import PromptLayerOpenAI
 llm = PromptLayerOpenAI(pl_tags=["langchain-requests", "chatbot"])
 ```
 
-To get the PromptLayer request id, use the argument `return_pl_id` when instanializing the LLM
+To get the PromptLayer request id, use the argument `return_pl_id` when instantiating the LLM
 ```python
 from langchain.llms import PromptLayerOpenAI
 llm = PromptLayerOpenAI(return_pl_id=True)
@@ -42,8 +46,14 @@ You can use the PromptLayer request ID to add a prompt, score, or other metadata
 
 This LLM is identical to the [OpenAI LLM](./openai.md), except that
 - all your requests will be logged to your PromptLayer account
-- you can add `pl_tags` when instantializing to tag your requests on PromptLayer
-- you can add `return_pl_id` when instantializing to return a PromptLayer request id to use [while tracking requests](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
+- you can add `pl_tags` when instantiating to tag your requests on PromptLayer
+- you can add `return_pl_id` when instantiating to return a PromptLayer request id to use [while tracking requests](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
 
+## Chat Model
+
+```python
+from langchain.chat_models import PromptLayerChatOpenAI
+```
+
+See a [usage example](../modules/models/chat/integrations/promptlayer_chatopenai.ipynb).
 
-PromptLayer also provides native wrappers for [`PromptLayerChatOpenAI`](../modules/models/chat/integrations/promptlayer_chatopenai.ipynb) and `PromptLayerOpenAIChat`

docs/integrations/roam.md

@@ -0,0 +1,17 @@
+# Roam
+
+>[ROAM](https://roamresearch.com/) is a note-taking tool for networked thought, designed to create a personal knowledge base.
+ 
+## Installation and Setup
+
+There isn't any special setup for it.
+
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/roam.ipynb).
+
+```python
+from langchain.document_loaders import RoamLoader
+```

docs/integrations/slack.md

@@ -0,0 +1,17 @@
+# Slack
+
+>[Slack](https://slack.com/) is an instant messaging program.
+ 
+## Installation and Setup
+
+There isn't any special setup for it.
+
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/slack.ipynb).
+
+```python
+from langchain.document_loaders import SlackDirectoryLoader
+```

docs/integrations/spacy.md

@@ -0,0 +1,20 @@
+# spaCy
+
+>[spaCy](https://spacy.io/) is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython.
+ 
+## Installation and Setup
+
+
+```bash
+pip install spacy
+```
+
+
+
+## Text Splitter
+
+See a [usage example](../modules/indexes/text_splitters/examples/spacy.ipynb).
+
+```python
+from langchain.llms import SpacyTextSplitter
+```

docs/integrations/spreedly.md

@@ -0,0 +1,15 @@
+# Spreedly
+
+>[Spreedly](https://docs.spreedly.com/) is a service that allows you to securely store credit cards and use them to transact against any number of payment gateways and third party APIs. It does this by simultaneously providing a card tokenization/vault service as well as a gateway and receiver integration service. Payment methods tokenized by Spreedly are stored at `Spreedly`, allowing you to independently store a card and then pass that card to different end points based on your business requirements.
+ 
+## Installation and Setup
+
+See [setup instructions](../modules/indexes/document_loaders/examples/spreedly.ipynb).
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/spreedly.ipynb).
+
+```python
+from langchain.document_loaders import SpreedlyLoader
+```

docs/integrations/stripe.md

@@ -0,0 +1,16 @@
+# Stripe
+
+>[Stripe](https://stripe.com/en-ca) is an Irish-American financial services and software as a service (SaaS) company. It offers payment-processing software and application programming interfaces for e-commerce websites and mobile applications.
+
+
+## Installation and Setup
+
+See [setup instructions](../modules/indexes/document_loaders/examples/stripe.ipynb).
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/stripe.ipynb).
+
+```python
+from langchain.document_loaders import StripeLoader
+```

docs/integrations/telegram.md

@@ -0,0 +1,17 @@
+# Telegram
+
+>[Telegram Messenger](https://web.telegram.org/a/) is a globally accessible freemium, cross-platform, encrypted, cloud-based and centralized instant messaging service. The application also provides optional end-to-end encrypted chats and video calling, VoIP, file sharing and several other features.
+
+
+## Installation and Setup
+
+See [setup instructions](../modules/indexes/document_loaders/examples/telegram.ipynb).
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/telegram.ipynb).
+
+```python
+from langchain.document_loaders import TelegramChatFileLoader
+from langchain.document_loaders import TelegramChatApiLoader
+```

docs/integrations/tensorflow_hub.md

@@ -0,0 +1,22 @@
+# Tensorflow Hub
+
+>[TensorFlow Hub](https://www.tensorflow.org/hub) is a repository of trained machine learning models ready for fine-tuning and deployable anywhere.
+
+>[TensorFlow Hub](https://tfhub.dev/) lets you search and discover hundreds of trained, ready-to-deploy machine learning models in one place.
+ 
+## Installation and Setup
+
+
+```bash
+pip install tensorflow-hub
+pip install tensorflow_text
+```
+
+
+## Text Embedding Models
+
+See a [usage example](../modules/models/text_embedding/examples/tensorflowhub.ipynb)
+
+```python
+from langchain.embeddings import TensorflowHubEmbeddings
+```

docs/integrations/tomarkdown.md

@@ -0,0 +1,16 @@
+# 2Markdown
+
+>[2markdown](https://2markdown.com/) service transforms website content into structured markdown files.
+
+
+## Installation and Setup
+
+We need the `API key`. See [instructions how to get it](https://2markdown.com/login).
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/tomarkdown.ipynb).
+
+```python
+from langchain.document_loaders import ToMarkdownLoader
+```

docs/integrations/trello.md

@@ -0,0 +1,22 @@
+# Trello
+
+>[Trello](https://www.atlassian.com/software/trello) is a web-based project management and collaboration tool that allows individuals and teams to organize and track their tasks and projects. It provides a visual interface known as a "board" where users can create lists and cards to represent their tasks and activities.
+>The TrelloLoader allows us to load cards from a `Trello` board.
+
+
+## Installation and Setup
+
+```bash
+pip install py-trello beautifulsoup4
+```
+
+See [setup instructions](../modules/indexes/document_loaders/examples/trello.ipynb).
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/trello.ipynb).
+
+```python
+from langchain.document_loaders import TrelloLoader
+```

docs/integrations/twitter.md

@@ -0,0 +1,21 @@
+# Twitter
+
+>[Twitter](https://twitter.com/) is an online social media and social networking service.
+
+
+## Installation and Setup
+
+```bash
+pip install tweepy
+```
+
+We must initialize the loader with the `Twitter API` token, and we need to set up the Twitter `username`.
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/twitter.ipynb).
+
+```python
+from langchain.document_loaders import TwitterTweetLoader
+```

docs/integrations/vespa.md

@@ -0,0 +1,21 @@
+# Vespa
+
+>[Vespa](https://vespa.ai/) is a fully featured search engine and vector database. 
+> It supports vector search (ANN), lexical search, and search in structured data, all in the same query.
+ 
+## Installation and Setup
+
+
+```bash
+pip install pyvespa
+```
+
+
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/vespa.ipynb).
+
+```python
+from langchain.retrievers import VespaRetriever
+```

docs/integrations/weather.md

@@ -0,0 +1,21 @@
+# Weather
+
+>[OpenWeatherMap](https://openweathermap.org/) is an open source weather service provider.
+
+
+
+## Installation and Setup
+
+```bash
+pip install pyowm
+```
+
+We must set up the `OpenWeatherMap API token`.
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/weather.ipynb).
+
+```python
+from langchain.document_loaders import WeatherDataLoader
+```

docs/integrations/whatsapp.md

@@ -0,0 +1,18 @@
+# WhatsApp
+
+>[WhatsApp](https://www.whatsapp.com/) (also called `WhatsApp Messenger`) is a freeware, cross-platform, centralized instant messaging (IM) and voice-over-IP (VoIP) service. It allows users to send text and voice messages, make voice and video calls, and share images, documents, user locations, and other content.
+
+
+## Installation and Setup
+
+There isn't any special setup for it.
+
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/whatsapp_chat.ipynb).
+
+```python
+from langchain.document_loaders import WhatsAppChatLoader
+```

docs/integrations/wikipedia.md

@@ -0,0 +1,28 @@
+# Wikipedia
+
+>[Wikipedia](https://wikipedia.org/) is a multilingual free online encyclopedia written and maintained by a community of volunteers, known as Wikipedians, through open collaboration and using a wiki-based editing system called MediaWiki. `Wikipedia` is the largest and most-read reference work in history.
+
+
+## Installation and Setup
+
+```bash
+pip install wikipedia
+```
+
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/wikipedia.ipynb).
+
+```python
+from langchain.document_loaders import WikipediaLoader
+```
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/wikipedia.ipynb).
+
+```python
+from langchain.retrievers import WikipediaRetriever
+```

docs/integrations/youtube.md

@@ -0,0 +1,22 @@
+# YouTube
+
+>[YouTube](https://www.youtube.com/) is an online video sharing and social media platform created by Google.
+> We download the `YouTube` transcripts and video information.
+
+## Installation and Setup
+
+```bash
+pip install youtube-transcript-api
+pip install pytube
+```
+See a [usage example](../modules/indexes/document_loaders/examples/youtube_transcript.ipynb).
+
+
+## Document Loader
+
+See a [usage example](../modules/indexes/document_loaders/examples/youtube_transcript.ipynb).
+
+```python
+from langchain.document_loaders import YoutubeLoader
+from langchain.document_loaders import GoogleApiYoutubeLoader
+```

docs/integrations/zep.md

@@ -0,0 +1,28 @@
+# Zep
+
+>[Zep](https://docs.getzep.com/) - A long-term memory store for LLM applications.
+
+>`Zep` stores, summarizes, embeds, indexes, and enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.
+>- Long-term memory persistence, with access to historical messages irrespective of your summarization strategy.
+>- Auto-summarization of memory messages based on a configurable message window. A series of summaries are stored, providing flexibility for future summarization strategies.
+>- Vector search over memories, with messages automatically embedded on creation.
+>- Auto-token counting of memories and summaries, allowing finer-grained control over prompt assembly.
+>- Python and JavaScript SDKs.
+
+
+`Zep` [project](https://github.com/getzep/zep) 
+
+## Installation and Setup
+
+```bash
+pip install zep_python
+```
+
+
+## Retriever
+
+See a [usage example](../modules/indexes/retrievers/examples/zep_memorystore.ipynb).
+
+```python
+from langchain.retrievers import ZepRetriever
+```

docs/integrations/zilliz.md

@@ -1,19 +1,20 @@
 # Zilliz
 
-This page covers how to use the Zilliz Cloud ecosystem within LangChain.
-Zilliz uses the Milvus integration. 
-It is broken into two parts: installation and setup, and then references to specific Milvus wrappers.
+>[Zilliz Cloud](https://zilliz.com/doc/quick_start) is a fully managed service on cloud for `LF AI Milvus®`,
+
 
 ## Installation and Setup
-- Install the Python SDK with `pip install pymilvus`
-## Wrappers
 
-### VectorStore
+Install the Python SDK:
+```bash
+pip install pymilvus
+```
 
-There exists a wrapper around Zilliz indexes, allowing you to use it as a vectorstore,
+## Vectorstore
+
+A wrapper around Zilliz indexes allows you to use it as a vectorstore,
 whether for semantic search or example selection.
 
-To import this vectorstore:
 ```python
 from langchain.vectorstores import Milvus
 ```

docs/modules/agents.rst

@@ -5,108 +5,101 @@ Agents
    `Conceptual Guide <https://docs.langchain.com/docs/components/agents>`_
 
 
-Some applications will require not just a predetermined chain of calls to LLMs/other tools,
+Some applications require not just a predetermined chain of calls to LLMs/other tools,
 but potentially an unknown chain that depends on the user's input.
-In these types of chains, there is a “agent” which has access to a suite of tools.
+In these types of chains, there is an **agent** which has access to a suite of **tools**.
 Depending on the user input, the agent can then decide which, if any, of these tools to call.
 
 At the moment, there are two main types of agents:
 
-1. "Action Agents": these agents decide an action to take and take that action one step at a time
-2. "Plan-and-Execute Agents": these agents first decide a plan of actions to take, and then execute those actions one at a time.
+1. **Action Agents**: these agents decide the actions to take and execute that actions one action at a time.
+2. **Plan-and-Execute Agents**: these agents first decide a plan of actions to take, and then execute those actions one at a time.
 
 When should you use each one? Action Agents are more conventional, and good for small tasks.
-For more complex or long running tasks, the initial planning step helps to maintain long term objectives and focus. However, that comes at the expense of generally more calls and higher latency.
-These two agents are also not mutually exclusive - in fact, it is often best to have an Action Agent be in charge of the execution for the Plan and Execute agent.
+For more complex or long running tasks, the initial planning step helps to maintain long term objectives and focus.
+However, that comes at the expense of generally more calls and higher latency.
+These two agents are also not mutually exclusive - in fact, it is often best to have an Action Agent be in charge
+of the execution for the Plan and Execute agent.
 
 Action Agents
 -------------
 
-High level pseudocode of agents looks something like:
+High level pseudocode of the Action Agents:
 
-- Some user input is received
-- The `agent` decides which `tool` - if any - to use, and what the input to that tool should be
-- That `tool` is then called with that `tool input`, and an `observation` is recorded (this is just the output of calling that tool with that tool input)
-- That history of `tool`, `tool input`, and `observation` is passed back into the `agent`, and it decides what step to take next
-- This is repeated until the `agent` decides it no longer needs to use a `tool`, and then it responds directly to the user.
+- The **user input** is received
+- The **agent** decides which **tool** - if any - to use, and what the **tool input** should be
+- That **tool** is then called with the **tool input**, and an **observation** is recorded (the output of this calling)
+- That history of **tool**, **tool input**, and **observation** is passed back into the **agent**, and it decides the next step
+- This is repeated until the **agent** decides it no longer needs to use a **tool**, and then it responds directly to the user.
 
-The different abstractions involved in agents are as follows:
 
-- Agent: this is where the logic of the application lives. Agents expose an interface that takes in user input along with a list of previous steps the agent has taken, and returns either an `AgentAction` or `AgentFinish`
-    - `AgentAction` corresponds to the tool to use and the input to that tool
-    - `AgentFinish` means the agent is done, and has information around what to return to the user
-- Tools: these are the actions an agent can take. What tools you give an agent highly depend on what you want the agent to do
-- Toolkits: these are groups of tools designed for a specific use case. For example, in order for an agent to interact with a SQL database in the best way it may need access to one tool to execute queries and another tool to inspect tables.
-- Agent Executor: this wraps an agent and a list of tools. This is responsible for the loop of running the agent iteratively until the stopping criteria is met.
+The different abstractions involved in agents are:
 
-The most important abstraction of the four above to understand is that of the agent.
-Although an agent can be defined in whatever way one chooses, the typical way to construct an agent is with:
+- **Agent**: this is where the logic of the application lives. Agents expose an interface that takes in user input
+  along with a list of previous steps the agent has taken, and returns either an **AgentAction** or **AgentFinish**
 
-- PromptTemplate: this is responsible for taking the user input and previous steps and constructing a prompt to send to the language model
-- Language Model: this takes the prompt constructed by the PromptTemplate and returns some output
-- Output Parser: this takes the output of the Language Model and parses it into an `AgentAction` or `AgentFinish` object.
+  - **AgentAction** corresponds to the tool to use and the input to that tool
+  - **AgentFinish** means the agent is done, and has information around what to return to the user
+- **Tools**: these are the actions an agent can take. What tools you give an agent highly depend on what you want the agent to do
+- **Toolkits**: these are groups of tools designed for a specific use case. For example, in order for an agent to
+  interact with a SQL database in the best way it may need access to one tool to execute queries and another tool to inspect tables.
+- **Agent Executor**: this wraps an agent and a list of tools. This is responsible for the loop of running the agent
+  iteratively until the stopping criteria is met.
+
+
+|
+- `Getting Started <./agents/getting_started.html>`_: An overview of agents. It covers how to use all things related to agents in an end-to-end manner.
+
+
+|
+**Agent Construction:**
+
+Although an agent can be constructed in many way, the typical way to construct an agent is with:
+
+- **PromptTemplate**: this is responsible for taking the user input and previous steps and constructing a prompt
+  to send to the language model
+- **Language Model**: this takes the prompt constructed by the PromptTemplate and returns some output
+- **Output Parser**: this takes the output of the Language Model and parses it into an **AgentAction** or **AgentFinish** object.
+
+
+|
+**Additional Documentation:**
+
+
+- `Tools <./agents/tools.html>`_: Different types of **tools** LangChain supports natively. We also cover how to add your own tools.
+
+- `Agents <./agents/agents.html>`_: Different types of **agents** LangChain supports natively. We also cover how to
+  modify and create your own agents.
+
+- `Toolkits <./agents/toolkits.html>`_: Various **toolkits** that LangChain supports out of the box, and how to
+  create an agent from them.
+
+- `Agent Executor <./agents/agent_executors.html>`_: The **Agent Executor** class, which is responsible for calling
+  the agent and tools in a loop. We go over different ways to customize this, and options you can use for more control.
+
+
+Plan-and-Execute Agents
+-----------------------
+High level pseudocode of the **Plan-and-Execute Agents**:
+
+- The **user input** is received
+- The **planner** lists out the steps to take
+- The **executor** goes through the list of steps, executing them
+
+The most typical implementation is to have the planner be a language model, and the executor be an action agent.
+
+|
+- `Plan-and-Execute Agents <./agents/plan_and_execute.html>`_
 
-In this section of documentation, we first start with a Getting Started notebook to cover how to use all things related to agents in an end-to-end manner.
 
 .. toctree::
    :maxdepth: 1
    :hidden:
 
    ./agents/getting_started.ipynb
-
-
-We then split the documentation into the following sections:
-
-**Tools**
-
-In this section we cover the different types of tools LangChain supports natively.
-We then cover how to add your own tools.
-
-
-**Agents**
-
-In this section we cover the different types of agents LangChain supports natively.
-We then cover how to modify and create your own agents.
-
-
-**Toolkits**
-
-In this section we go over the various toolkits that LangChain supports out of the box,
-and how to create an agent from them.
-
-
-**Agent Executor**
-
-In this section we go over the Agent Executor class, which is responsible for calling
-the agent and tools in a loop. We go over different ways to customize this, and options you
-can use for more control.
-
-**Go Deeper**
-
-.. toctree::
-   :maxdepth: 1
-
    ./agents/tools.rst
    ./agents/agents.rst
    ./agents/toolkits.rst
    ./agents/agent_executors.rst
-
-Plan-and-Execute Agents
------------------------
-
-High level pseudocode of agents looks something like:
-
-- Some user input is received
-- The planner lists out the steps to take
-- The executor goes through the list of steps, executing them
-
-The most typical implementation is to have the planner be a language model,
-and the executor be an action agent.
-
-**Go Deeper**
-
-.. toctree::
-   :maxdepth: 1
-
    ./agents/plan_and_execute.ipynb
 

docs/modules/agents/streaming_stdout_final_only.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "23234b50-e6c6-4c87-9f97-259c15f36894",
    "metadata": {
@@ -11,6 +12,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "29dd6333-307c-43df-b848-65001c01733b",
    "metadata": {},
@@ -36,6 +38,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "19a813f7",
    "metadata": {},
@@ -84,6 +87,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "53a743b8",
    "metadata": {},
@@ -92,11 +96,12 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "23602c62",
    "metadata": {},
    "source": [
-    "By default, we assume that the token sequence ``\"\\nFinal\", \" Answer\", \":\"`` indicates that the agent has reached an answers. We can, however, also pass a custom sequence to use as answer prefix."
+    "By default, we assume that the token sequence ``\"Final\", \"Answer\", \":\"`` indicates that the agent has reached an answers. We can, however, also pass a custom sequence to use as answer prefix."
    ]
   },
   {
@@ -108,26 +113,75 @@
    "source": [
     "llm = OpenAI(\n",
     "    streaming=True,\n",
-    "    callbacks=[FinalStreamingStdOutCallbackHandler(answer_prefix_tokens=[\"\\nThe\", \" answer\", \":\"])],\n",
+    "    callbacks=[FinalStreamingStdOutCallbackHandler(answer_prefix_tokens=[\"The\", \"answer\", \":\"])],\n",
     "    temperature=0\n",
     ")"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "b1a96cc0",
    "metadata": {},
    "source": [
-    "Be aware you likely need to include whitespaces and new line characters in your token. "
+    "For convenience, the callback automatically strips whitespaces and new line characters when comparing to `answer_prefix_tokens`. I.e., if `answer_prefix_tokens = [\"The\", \" answer\", \":\"]` then both `[\"\\nThe\", \" answer\", \":\"]` and `[\"The\", \" answer\", \":\"]` would be recognized a the answer prefix."
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "9278b522",
+   "metadata": {},
+   "source": [
+    "If you don't know the tokenized version of your answer prefix, you can determine it with the following code:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9278b522",
+   "id": "2f8f0640",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from langchain.callbacks.base import BaseCallbackHandler\n",
+    "\n",
+    "class MyCallbackHandler(BaseCallbackHandler):\n",
+    "    def on_llm_new_token(self, token, **kwargs) -> None:\n",
+    "        # print every token on a new line\n",
+    "        print(f\"#{token}#\")\n",
+    "\n",
+    "llm = OpenAI(streaming=True, callbacks=[MyCallbackHandler()])\n",
+    "tools = load_tools([\"wikipedia\", \"llm-math\"], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)\n",
+    "agent.run(\"It's 2023 now. How many years ago did Konrad Adenauer become Chancellor of Germany.\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "61190e58",
+   "metadata": {},
+   "source": [
+    "### Also streaming the answer prefixes"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "1255776f",
+   "metadata": {},
+   "source": [
+    "When the parameter `stream_prefix = True` is set, the answer prefix itself will also be streamed. This can be useful when the answer prefix itself is part of the answer. For example, when your answer is a JSON like\n",
+    "\n",
+    "`\n",
+    "{\n",
+    "    \"action\": \"Final answer\",\n",
+    "    \"action_input\": \"Konrad Adenauer became Chancellor 74 years ago.\"\n",
+    "}\n",
+    "`\n",
+    "\n",
+    "and you don't only want the action_input to be streamed, but the entire JSON."
+   ]
   }
  ],
  "metadata": {

docs/modules/agents/tools/examples/pubmed.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "64f20f38",
+   "metadata": {},
+   "source": [
+    "# PubMed Tool\n",
+    "\n",
+    "This notebook goes over how to use PubMed as a tool\n",
+    "\n",
+    "PubMed® comprises more than 35 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full text content from PubMed Central and publisher web sites."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c80b9273",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.tools import PubmedQueryRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f203c965",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool = PubmedQueryRun()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "baee7a2a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Published: <Year>2023</Year><Month>May</Month><Day>31</Day>\\nTitle: Dermatology in the wake of an AI revolution: who gets a say?\\nSummary: \\n\\nPublished: <Year>2023</Year><Month>May</Month><Day>30</Day>\\nTitle: What is ChatGPT and what do we do with it? Implications of the age of AI for nursing and midwifery practice and education: An editorial.\\nSummary: \\n\\nPublished: <Year>2023</Year><Month>Jun</Month><Day>02</Day>\\nTitle: The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education.\\nSummary: The nursing field has undergone notable changes over time and is projected to undergo further modifications in the future, owing to the advent of sophisticated technologies and growing healthcare needs. The advent of ChatGPT, an AI-powered language model, is expected to exert a significant influence on the nursing profession, specifically in the domains of patient care and instruction. The present article delves into the ramifications of ChatGPT within the nursing domain and accentuates its capacity and constraints to transform the discipline.'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tool.run(\"chatgpt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "965903ba",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/callbacks/filecallbackhandler.ipynb

@@ -0,0 +1,175 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "63b87b91",
+   "metadata": {},
+   "source": [
+    "# Logging to file\n",
+    "This example shows how to print logs to file. It shows how to use the `FileCallbackHandler`, which does the same thing as [`StdOutCallbackHandler`](https://python.langchain.com/en/latest/modules/callbacks/getting_started.html#using-an-existing-handler), but instead writes the output to file. It also uses the `loguru` library to log other outputs that are not captured by the handler."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6cb156cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3m1 + 2 = \u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32m2023-06-01 18:36:38.929\u001b[0m | \u001b[1mINFO    \u001b[0m | \u001b[36m__main__\u001b[0m:\u001b[36m<module>\u001b[0m:\u001b[36m20\u001b[0m - \u001b[1m\n",
+      "\n",
+      "3\u001b[0m\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "from loguru import logger\n",
+    "\n",
+    "from langchain.callbacks import FileCallbackHandler\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "\n",
+    "logfile = 'output.log'\n",
+    "\n",
+    "logger.add(logfile, colorize=True, enqueue=True)\n",
+    "handler = FileCallbackHandler(logfile)\n",
+    "\n",
+    "llm = OpenAI()\n",
+    "prompt = PromptTemplate.from_template(\"1 + {number} = \")\n",
+    "\n",
+    "# this chain will both print to stdout (because verbose=True) and write to 'output.log'\n",
+    "# if verbose=False, the FileCallbackHandler will still write to 'output.log'\n",
+    "chain = LLMChain(llm=llm, prompt=prompt, callbacks=[handler], verbose=True)\n",
+    "answer = chain.run(number=2)\n",
+    "logger.info(answer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c50d54f",
+   "metadata": {},
+   "source": [
+    "Now we can open the file `output.log` to see that the output has been captured."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "aa32dc0a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install ansi2html > /dev/null"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4af00719",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\n",
+       "<html>\n",
+       "<head>\n",
+       "<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\">\n",
+       "<title></title>\n",
+       "<style type=\"text/css\">\n",
+       ".ansi2html-content { display: inline; white-space: pre-wrap; word-wrap: break-word; }\n",
+       ".body_foreground { color: #AAAAAA; }\n",
+       ".body_background { background-color: #000000; }\n",
+       ".inv_foreground { color: #000000; }\n",
+       ".inv_background { background-color: #AAAAAA; }\n",
+       ".ansi1 { font-weight: bold; }\n",
+       ".ansi3 { font-style: italic; }\n",
+       ".ansi32 { color: #00aa00; }\n",
+       ".ansi36 { color: #00aaaa; }\n",
+       "</style>\n",
+       "</head>\n",
+       "<body class=\"body_foreground body_background\" style=\"font-size: normal;\" >\n",
+       "<pre class=\"ansi2html-content\">\n",
+       "\n",
+       "\n",
+       "<span class=\"ansi1\">&gt; Entering new LLMChain chain...</span>\n",
+       "Prompt after formatting:\n",
+       "<span class=\"ansi1 ansi32\"></span><span class=\"ansi1 ansi3 ansi32\">1 + 2 = </span>\n",
+       "\n",
+       "<span class=\"ansi1\">&gt; Finished chain.</span>\n",
+       "<span class=\"ansi32\">2023-06-01 18:36:38.929</span> | <span class=\"ansi1\">INFO    </span> | <span class=\"ansi36\">__main__</span>:<span class=\"ansi36\">&lt;module&gt;</span>:<span class=\"ansi36\">20</span> - <span class=\"ansi1\">\n",
+       "\n",
+       "3</span>\n",
+       "\n",
+       "</pre>\n",
+       "</body>\n",
+       "\n",
+       "</html>\n"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import display, HTML\n",
+    "from ansi2html import Ansi2HTMLConverter\n",
+    "\n",
+    "with open('output.log', 'r') as f:\n",
+    "    content = f.read()\n",
+    "\n",
+    "conv = Ansi2HTMLConverter()\n",
+    "html = conv.convert(content, full=True)\n",
+    "\n",
+    "display(HTML(html))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/chains.rst

@@ -6,14 +6,13 @@ Chains
 
 
 Using an LLM in isolation is fine for some simple applications,
-but many more complex ones require chaining LLMs - either with each other or with other experts.
-LangChain provides a standard interface for Chains, as well as some common implementations of chains for ease of use.
+but more complex applications require chaining LLMs - either with each other or with other experts.
+LangChain provides a standard interface for **Chains**, as well as several common implementations of chains.
 
-The following sections of documentation are provided:
+|
+- `Getting Started <./chains/getting_started.html>`_: An overview of chains.
 
-- `Getting Started <./chains/getting_started.html>`_: A getting started guide for chains, to get you up and running quickly.
-
-- `How-To Guides <./chains/how_to_guides.html>`_: A collection of how-to guides. These highlight how to use various types of chains.
+- `How-To Guides <./chains/how_to_guides.html>`_: How-to guides about various types of chains.
 
 - `Reference <../reference/modules/chains.html>`_: API reference documentation for all Chain classes.
 

docs/modules/chains/index_examples/summarize.ipynb

@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "e9db25f3",
    "metadata": {},
    "outputs": [],
@@ -318,6 +318,141 @@
     "chain({\"input_documents\": docs}, return_only_outputs=True)"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "b882e209",
+   "metadata": {},
+   "source": [
+    "## The custom `MapReduceChain`\n",
+    "\n",
+    "**Multi input prompt**\n",
+    "\n",
+    "You can also use prompt with multi input. In this example, we will use a MapReduce chain to answer specifc question about our code."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f7ad9ee2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains.combine_documents.map_reduce import MapReduceDocumentsChain\n",
+    "from langchain.chains.combine_documents.stuff import StuffDocumentsChain\n",
+    "\n",
+    "map_template_string = \"\"\"Give the following python code information, generate a description that explains what the code does and also mention the time complexity.\n",
+    "Code:\n",
+    "{code}\n",
+    "\n",
+    "Return the the description in the following format:\n",
+    "name of the function: description of the function\n",
+    "\"\"\"\n",
+    "\n",
+    "\n",
+    "reduce_template_string = \"\"\"Give the following following python fuctions name and their descritpion, answer the following question\n",
+    "{code_description}\n",
+    "Question: {question}\n",
+    "Answer:\n",
+    "\"\"\"\n",
+    "\n",
+    "MAP_PROMPT = PromptTemplate(input_variables=[\"code\"], template=map_template_string)\n",
+    "REDUCE_PROMPT = PromptTemplate(input_variables=[\"code_description\", \"question\"], template=reduce_template_string)\n",
+    "\n",
+    "llm = OpenAI()\n",
+    "\n",
+    "map_llm_chain = LLMChain(llm=llm, prompt=MAP_PROMPT)\n",
+    "reduce_llm_chain = LLMChain(llm=llm, prompt=REDUCE_PROMPT)\n",
+    "\n",
+    "generative_result_reduce_chain = StuffDocumentsChain(\n",
+    "    llm_chain=reduce_llm_chain,\n",
+    "    document_variable_name=\"code_description\",\n",
+    ")\n",
+    "\n",
+    "combine_documents = MapReduceDocumentsChain(\n",
+    "    llm_chain=map_llm_chain,\n",
+    "    combine_document_chain=generative_result_reduce_chain,\n",
+    "    document_variable_name=\"code\",\n",
+    ")\n",
+    "\n",
+    "map_reduce = MapReduceChain(\n",
+    "    combine_documents_chain=combine_documents,\n",
+    "    text_splitter=CharacterTextSplitter(separator=\"\\n##\\n\", chunk_size=100, chunk_overlap=0),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "0d4caccb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "code = \"\"\"\n",
+    "def bubblesort(list):\n",
+    "   for iter_num in range(len(list)-1,0,-1):\n",
+    "      for idx in range(iter_num):\n",
+    "         if list[idx]>list[idx+1]:\n",
+    "            temp = list[idx]\n",
+    "            list[idx] = list[idx+1]\n",
+    "            list[idx+1] = temp\n",
+    "    return list\n",
+    "##\n",
+    "def insertion_sort(InputList):\n",
+    "   for i in range(1, len(InputList)):\n",
+    "      j = i-1\n",
+    "      nxt_element = InputList[i]\n",
+    "   while (InputList[j] > nxt_element) and (j >= 0):\n",
+    "      InputList[j+1] = InputList[j]\n",
+    "      j=j-1\n",
+    "   InputList[j+1] = nxt_element\n",
+    "   return InputList\n",
+    "##\n",
+    "def shellSort(input_list):\n",
+    "   gap = len(input_list) // 2\n",
+    "   while gap > 0:\n",
+    "      for i in range(gap, len(input_list)):\n",
+    "         temp = input_list[i]\n",
+    "         j = i\n",
+    "   while j >= gap and input_list[j - gap] > temp:\n",
+    "      input_list[j] = input_list[j - gap]\n",
+    "      j = j-gap\n",
+    "      input_list[j] = temp\n",
+    "   gap = gap//2\n",
+    "   return input_list\n",
+    "\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "d5a9a35b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Created a chunk of size 247, which is longer than the specified 100\n",
+      "Created a chunk of size 267, which is longer than the specified 100\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'shellSort has a better time complexity than both bubblesort and insertion_sort, as it has a time complexity of O(n^2), while the other two have a time complexity of O(n^2).'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "map_reduce.run(input_text=code, question=\"Which function has a better time complexity?\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "f61350f9",
@@ -470,7 +605,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.8.16"
   },
   "vscode": {
    "interpreter": {

docs/modules/indexes.rst

@@ -5,53 +5,41 @@ Indexes
    `Conceptual Guide <https://docs.langchain.com/docs/components/indexing>`_
 
 
-Indexes refer to ways to structure documents so that LLMs can best interact with them.
-This module contains utility functions for working with documents, different types of indexes, and then examples for using those indexes in chains.
+**Indexes** refer to ways to structure documents so that LLMs can best interact with them.
 
 The most common way that indexes are used in chains is in a "retrieval" step.
 This step refers to taking a user's query and returning the most relevant documents.
-We draw this distinction because (1) an index can be used for other things besides retrieval, and (2) retrieval can use other logic besides an index to find relevant documents.
-We therefore have a concept of a "Retriever" interface - this is the interface that most chains work with.
+We draw this distinction because (1) an index can be used for other things besides retrieval, and
+(2) retrieval can use other logic besides an index to find relevant documents.
+We therefore have a concept of a **Retriever** interface - this is the interface that most chains work with.
+
+Most of the time when we talk about indexes and retrieval we are talking about indexing and retrieving
+unstructured data (like text documents).
+For interacting with structured data (SQL tables, etc) or APIs, please see the corresponding use case
+sections for links to relevant functionality.
+
+|
+- `Getting Started <./indexes/getting_started.html>`_: An overview of the indexes.
+
+
+Index Types
+---------------------
+
+- `Document Loaders <./indexes/document_loaders.html>`_: How to load documents from a variety of sources.
+
+- `Text Splitters <./indexes/text_splitters.html>`_: An overview and different types of the **Text Splitters**.
+
+- `VectorStores <./indexes/vectorstores.html>`_: An overview and different types of the  **Vector Stores**.
+
+- `Retrievers <./indexes/retrievers.html>`_: An overview and different types of the **Retrievers**.
 
-Most of the time when we talk about indexes and retrieval we are talking about indexing and retrieving unstructured data (like text documents).
-For interacting with structured data (SQL tables, etc) or APIs, please see the corresponding use case sections for links to relevant functionality.
-The primary index and retrieval types supported by LangChain are currently centered around vector databases, and therefore
-a lot of the functionality we dive deep on those topics.
 
-For an overview of everything related to this, please see the below notebook for getting started:
 
 .. toctree::
    :maxdepth: 1
+   :hidden:
 
    ./indexes/getting_started.ipynb
-
-We then provide a deep dive on the four main components.
-
-**Document Loaders**
-
-How to load documents from a variety of sources.
-
-**Text Splitters**
-
-An overview of the abstractions and implementions around splitting text.
-
-
-**VectorStores**
-
-An overview of VectorStores and the many integrations LangChain provides.
-
-
-**Retrievers**
-
-An overview of Retrievers and the implementations LangChain provides.
-
-Go Deeper
----------
-
-
-.. toctree::
-   :maxdepth: 1
-
    ./indexes/document_loaders.rst
    ./indexes/text_splitters.rst
    ./indexes/vectorstores.rst

docs/modules/indexes/document_loaders.rst

@@ -30,6 +30,7 @@ For detailed instructions on how to get set up with Unstructured, see installati
    :maxdepth: 1
    :glob:
 
+   ./document_loaders/examples/audio.ipynb
    ./document_loaders/examples/conll-u.ipynb
    ./document_loaders/examples/copypaste.ipynb
    ./document_loaders/examples/csv.ipynb

docs/modules/indexes/document_loaders/examples/confluence.ipynb

@@ -1,15 +1,18 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
-   "source": [
+  "source": [
     "# Confluence\n",
     "\n",
     ">[Confluence](https://www.atlassian.com/software/confluence) is a wiki collaboration platform that saves and organizes all of the project-related material. `Confluence` is a knowledge base that primarily handles content management activities. \n",
     "\n",
-    "A loader for `Confluence` pages currently supports both `username/api_key` and `Oauth2 login`.\n",
-    "See [instructions](https://support.atlassian.com/atlassian-account/docs/manage-api-tokens-for-your-atlassian-account/).\n",
+    "A loader for `Confluence` pages.\n",
+    "\n",
+    "\n",
+    "This currently supports `username/api_key`, `Oauth2 login`. Additionally, on-prem installations also support `token` authentication. \n",
     "\n",
     "\n",
     "Specify a list `page_id`-s and/or `space_key` to load in the corresponding pages into Document objects, if both are specified the union of both sets will be returned.\n",
@@ -20,9 +23,17 @@
     "Hint: `space_key` and `page_id` can both be found in the URL of a page in Confluence - https://yoursite.atlassian.com/wiki/spaces/<space_key>/pages/<page_id>\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Before using ConfluenceLoader make sure you have the latest version of the atlassian-python-api package installed:"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {
     "tags": []
    },
@@ -31,6 +42,29 @@
     "#!pip install atlassian-python-api"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Examples"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Username and Password or Username and API Token (Atlassian Cloud only)\n",
+    "\n",
+    "This example authenticates using either a username and password or, if you're connecting to an Atlassian Cloud hosted version of Confluence, a username and an API Token.\n",
+    "You can generate an API token at: https://id.atlassian.com/manage-profile/security/api-tokens.\n",
+    "\n",
+    "The `limit` parameter specifies how many documents will be retrieved in a single call, not how many documents will be retrieved in total.\n",
+    "By default the code will return up to 1000 documents in 50 documents batches. To control the total number of documents use the `max_pages` parameter. \n",
+    "Plese note the maximum value for the `limit` parameter in the atlassian-python-api package is currently 100.  "
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -46,6 +80,34 @@
     ")\n",
     "documents = loader.load(space_key=\"SPACE\", include_attachments=True, limit=50)"
    ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Personal Access Token (Server/On-Prem only)\n",
+    "\n",
+    "This method is valid for the Data Center/Server on-prem edition only.\n",
+    "For more information on how to generate a Personal Access Token (PAT) check the official Confluence documentation at: https://confluence.atlassian.com/enterprise/using-personal-access-tokens-1026032365.html.\n",
+    "When using a PAT you provide only the token value, you cannot provide a username. \n",
+    "Please note that ConfluenceLoader will run under the permissions of the user that generated the PAT and will only be able to load documents for which said user has access to.  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import ConfluenceLoader\n",
+    "\n",
+    "loader = ConfluenceLoader(\n",
+    "    url=\"https://yoursite.atlassian.com/wiki\",\n",
+    "    token=\"12345\"\n",
+    ")\n",
+    "documents = loader.load(space_key=\"SPACE\", include_attachments=True, limit=50, max_pages=50)"
+   ]
   }
  ],
  "metadata": {
@@ -64,7 +126,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.9.13"
   },
   "vscode": {
    "interpreter": {

docs/modules/indexes/document_loaders/examples/excel.ipynb

@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "22a849cc",
+   "metadata": {},
+   "source": [
+    "# Microsoft Excel\n",
+    "\n",
+    "The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. The page content will be the raw text of the Excel file. If you use the loader in `\"elements\"` mode, an HTML representation of the Excel file will be available in the document metadata under the `text_as_html` key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e6616e3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredExcelLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a654e4d9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='\\n  \\n    \\n      Team\\n      Location\\n      Stanley Cups\\n    \\n    \\n      Blues\\n      STL\\n      1\\n    \\n    \\n      Flyers\\n      PHI\\n      2\\n    \\n    \\n      Maple Leafs\\n      TOR\\n      13\\n    \\n  \\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'filename': 'stanley-cups.xlsx', 'file_directory': 'example_data', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'page_number': 1, 'page_name': 'Stanley Cups', 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'category': 'Table'})"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader = UnstructuredExcelLoader(\n",
+    "    \"example_data/stanley-cups.xlsx\",\n",
+    "    mode=\"elements\"\n",
+    ")\n",
+    "docs = loader.load()\n",
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ab94bde",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/indexes/document_loaders/examples/slack.ipynb

@@ -41,7 +41,7 @@
    "source": [
     "# Optionally set your Slack URL. This will give you proper URLs in the docs sources.\n",
     "SLACK_WORKSPACE_URL = \"https://xxx.slack.com\"\n",
-    "LOCAL_ZIPFILE = \"\" # Paste the local paty to your Slack zip file here.\n",
+    "LOCAL_ZIPFILE = \"\" # Paste the local path to your Slack zip file here.\n",
     "\n",
     "loader = SlackDirectoryLoader(LOCAL_ZIPFILE, SLACK_WORKSPACE_URL)"
    ]

docs/modules/indexes/document_loaders/examples/telegram.ipynb

@@ -54,7 +54,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "3e64cac2",
    "metadata": {},
@@ -117,7 +116,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/indexes/document_loaders/examples/trello.ipynb

@@ -171,7 +171,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {

docs/modules/indexes/document_loaders/examples/whatsapp_chat.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### WhatsApp Chat\n",
+    "# WhatsApp Chat\n",
     "\n",
     ">[WhatsApp](https://www.whatsapp.com/) (also called `WhatsApp Messenger`) is a freeware, cross-platform, centralized instant messaging (IM) and voice-over-IP (VoIP) service. It allows users to send text and voice messages, make voice and video calls, and share images, documents, user locations, and other content.\n",
     "\n",

docs/modules/indexes/document_loaders/examples/youtube_transcript.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "df770c72",
    "metadata": {},
@@ -55,11 +56,12 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "6b278a1b",
    "metadata": {},
    "source": [
-    "## Add video info"
+    "### Add video info"
    ]
   },
   {
@@ -79,20 +81,36 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = YoutubeLoader.from_youtube_url(\"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=True)"
+    "loader = YoutubeLoader.from_youtube_url(\"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=True)\n",
+    "loader.load()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "fc417e31",
+   "metadata": {},
+   "source": [
+    "### Add language preferences\n",
+    "\n",
+    "Language param : It's a list of language codes in a descending priority, `en` by default.\n",
+    "\n",
+    "translation param : It's a translate preference when the youtube does'nt have your select language, `en` by default."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "97b98e92",
+   "id": "08510625",
    "metadata": {},
    "outputs": [],
    "source": [
+    "loader = YoutubeLoader.from_youtube_url(\"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=True, language=['en','id'], translation='en')\n",
     "loader.load()"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "65796cc5",
    "metadata": {},

docs/modules/indexes/retrievers/examples/azure_cognitive_search.ipynb

@@ -5,7 +5,16 @@
    "id": "1edb9e6b",
    "metadata": {},
    "source": [
-    "# Azure Cognitive Search Retriever\n",
+    "# Azure Cognitive Search\n",
+    "\n",
+    ">[Azure Cognitive Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search) (formerly known as `Azure Search`) is a cloud search service that gives developers infrastructure, APIs, and tools for building a rich search experience over private, heterogeneous content in web, mobile, and enterprise applications.\n",
+    "\n",
+    ">Search is foundational to any app that surfaces text to users, where common scenarios include catalog or document search, online retail apps, or data exploration over proprietary content. When you create a search service, you'll work with the following capabilities:\n",
+    ">- A search engine for full text search over a search index containing user-owned content\n",
+    ">- Rich indexing, with lexical analysis and optional AI enrichment for content extraction and transformation\n",
+    ">- Rich query syntax for text search, fuzzy search, autocomplete, geo-search and more\n",
+    ">- Programmability through REST APIs and client libraries in Azure SDKs\n",
+    ">- Azure integration at the data layer, machine learning layer, and AI (Cognitive Services)\n",
     "\n",
     "This notebook shows how to use Azure Cognitive Search (ACS) within LangChain."
    ]
@@ -120,7 +129,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/indexes/retrievers/examples/pubmed.ipynb

@@ -0,0 +1,80 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "3df0dcf8",
+   "metadata": {},
+   "source": [
+    "# PubMed Retriever\n",
+    "\n",
+    "This notebook goes over how to use PubMed as a retriever\n",
+    "\n",
+    "PubMed® comprises more than 35 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full text content from PubMed Central and publisher web sites."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "aecaff63",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import PubMedRetriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f2f7e8d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = PubMedRetriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ed115aa1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='', metadata={'uid': '37268021', 'title': 'Dermatology in the wake of an AI revolution: who gets a say?', 'pub_date': '<Year>2023</Year><Month>May</Month><Day>31</Day>'}),\n",
+       " Document(page_content='', metadata={'uid': '37267643', 'title': 'What is ChatGPT and what do we do with it? Implications of the age of AI for nursing and midwifery practice and education: An editorial.', 'pub_date': '<Year>2023</Year><Month>May</Month><Day>30</Day>'}),\n",
+       " Document(page_content='The nursing field has undergone notable changes over time and is projected to undergo further modifications in the future, owing to the advent of sophisticated technologies and growing healthcare needs. The advent of ChatGPT, an AI-powered language model, is expected to exert a significant influence on the nursing profession, specifically in the domains of patient care and instruction. The present article delves into the ramifications of ChatGPT within the nursing domain and accentuates its capacity and constraints to transform the discipline.', metadata={'uid': '37266721', 'title': 'The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education.', 'pub_date': '<Year>2023</Year><Month>Jun</Month><Day>02</Day>'})]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(\"chatgpt\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/indexes/retrievers/examples/wikipedia.ipynb

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "9fc6205b",
    "metadata": {},
@@ -14,7 +13,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "51489529-5dcd-4b86-bda6-de0a39d8ffd1",
    "metadata": {},
@@ -23,7 +21,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "1435c804-069d-4ade-9a7b-006b97b767c1",
    "metadata": {},
@@ -44,7 +41,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "6c15470b-a16b-4e0d-bc6a-6998bafbb5a4",
    "metadata": {},
@@ -58,7 +54,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "ae3c3d16",
    "metadata": {},
@@ -67,7 +62,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "6fafb73b-d6ec-4822-b161-edf0aaf5224a",
    "metadata": {},
@@ -151,7 +145,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "2670363b-3806-4c7e-b14d-90a4d5d2a200",
    "metadata": {},
@@ -273,7 +266,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/indexes/retrievers/examples/zep_memorystore.ipynb

@@ -2,21 +2,15 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "# Zep Memory\n",
+    "# Zep\n",
     "\n",
-    "## Retriever Example\n",
+    ">[Zep](https://docs.getzep.com/) - A long-term memory store for LLM applications.\n",
     "\n",
-    "This notebook demonstrates how to search historical chat message histories using the [Zep Long-term Memory Store](https://getzep.github.io/).\n",
+    "More on `Zep`:\n",
     "\n",
-    "We'll demonstrate:\n",
-    "\n",
-    "1. Adding conversation history to the Zep memory store.\n",
-    "2. Vector search over the conversation history.\n",
-    "\n",
-    "More on Zep:\n",
-    "\n",
-    "Zep stores, summarizes, embeds, indexes, and enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.\n",
+    "`Zep` stores, summarizes, embeds, indexes, and enriches conversational AI chat histories, and exposes them via simple, low-latency APIs.\n",
     "\n",
     "Key Features:\n",
     "\n",
@@ -28,15 +22,37 @@
     "\n",
     "Zep's Go Extractor model is easily extensible, with a simple, clean interface available to build new enrichment functionality, such as summarizers, entity extractors, embedders, and more.\n",
     "\n",
-    "Zep project: [https://github.com/getzep/zep](https://github.com/getzep/zep)\n"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "`Zep` project: [https://github.com/getzep/zep](https://github.com/getzep/zep)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Retriever Example\n",
+    "\n",
+    "This notebook demonstrates how to search historical chat message histories using the [Zep Long-term Memory Store](https://getzep.github.io/).\n",
+    "\n",
+    "We'll demonstrate:\n",
+    "\n",
+    "1. Adding conversation history to the Zep memory store.\n",
+    "2. Vector search over the conversation history.\n",
+    "\n"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-05-25T15:03:27.863217Z",
+     "start_time": "2023-05-25T15:03:25.690273Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "from langchain.memory.chat_message_histories import ZepChatMessageHistory\n",
@@ -45,29 +61,30 @@
     "\n",
     "# Set this to your Zep server URL\n",
     "ZEP_API_URL = \"http://localhost:8000\""
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-05-25T15:03:27.863217Z",
-     "start_time": "2023-05-25T15:03:25.690273Z"
-    }
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "### Initialize the Zep Chat Message History Class and add a chat message history to the memory store\n",
     "\n",
     "**NOTE:** Unlike other Retrievers, the content returned by the Zep Retriever is session/user specific. A `session_id` is required when instantiating the Retriever."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-05-25T15:03:29.118416Z",
+     "start_time": "2023-05-25T15:03:29.022464Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "session_id = str(uuid4())  # This is a unique identifier for the user/session\n",
@@ -77,18 +94,21 @@
     "    session_id=session_id,\n",
     "    url=ZEP_API_URL,\n",
     ")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-05-25T15:03:29.118416Z",
-     "start_time": "2023-05-25T15:03:29.022464Z"
-    }
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-05-25T15:03:30.271181Z",
+     "start_time": "2023-05-25T15:03:30.180442Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "# Preload some messages into the memory. The default message window is 12 messages. We want to push beyond this to demonstrate auto-summarization.\n",
@@ -157,35 +177,42 @@
     "        if msg[\"role\"] == \"human\"\n",
     "        else AIMessage(content=msg[\"content\"])\n",
     "    )\n"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-05-25T15:03:30.271181Z",
-     "start_time": "2023-05-25T15:03:30.180442Z"
-    }
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "### Use the Zep Retriever to vector search over the Zep memory\n",
     "\n",
     "Zep provides native vector search over historical conversation memory. Embedding happens automatically.\n",
     "\n",
     "NOTE: Embedding of messages occurs asynchronously, so the first query may not return results. Subsequent queries will return results as the embeddings are generated."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-05-25T15:03:32.979155Z",
+     "start_time": "2023-05-25T15:03:32.590310Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": "[Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759001673780126, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),\n Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602262941130749, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),\n Document(page_content='Who were her contemporaries?', metadata={'score': 0.757553366415519, 'uuid': '41f9c41a-a205-41e1-b48b-a0a4cd943fc8', 'created_at': '2023-05-25T15:03:30.243995Z', 'role': 'human', 'token_count': 8}),\n Document(page_content='Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', metadata={'score': 0.7546211059317948, 'uuid': '34678311-0098-4f1a-8fd4-5615ac692deb', 'created_at': '2023-05-25T15:03:30.231427Z', 'role': 'ai', 'token_count': 31}),\n Document(page_content='Which books of hers were made into movies?', metadata={'score': 0.7496714959247069, 'uuid': '18046c3a-9666-4d3e-b4f0-43d1394732b7', 'created_at': '2023-05-25T15:03:30.236837Z', 'role': 'human', 'token_count': 11})]"
+      "text/plain": [
+       "[Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759001673780126, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),\n",
+       " Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602262941130749, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),\n",
+       " Document(page_content='Who were her contemporaries?', metadata={'score': 0.757553366415519, 'uuid': '41f9c41a-a205-41e1-b48b-a0a4cd943fc8', 'created_at': '2023-05-25T15:03:30.243995Z', 'role': 'human', 'token_count': 8}),\n",
+       " Document(page_content='Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', metadata={'score': 0.7546211059317948, 'uuid': '34678311-0098-4f1a-8fd4-5615ac692deb', 'created_at': '2023-05-25T15:03:30.231427Z', 'role': 'ai', 'token_count': 31}),\n",
+       " Document(page_content='Which books of hers were made into movies?', metadata={'score': 0.7496714959247069, 'uuid': '18046c3a-9666-4d3e-b4f0-43d1394732b7', 'created_at': '2023-05-25T15:03:30.236837Z', 'role': 'human', 'token_count': 11})]"
+      ]
      },
      "execution_count": 4,
      "metadata": {},
@@ -202,31 +229,38 @@
     ")\n",
     "\n",
     "await zep_retriever.aget_relevant_documents(\"Who wrote Parable of the Sower?\")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-05-25T15:03:32.979155Z",
-     "start_time": "2023-05-25T15:03:32.590310Z"
-    }
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
     "We can also use the Zep sync API to retrieve results:"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-05-25T15:03:34.713354Z",
+     "start_time": "2023-05-25T15:03:34.577974Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [
     {
      "data": {
-      "text/plain": "[Document(page_content='Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', metadata={'score': 0.8897321402776546, 'uuid': '1c09603a-52c1-40d7-9d69-29f26256029c', 'created_at': '2023-05-25T15:03:30.268257Z', 'role': 'ai', 'token_count': 56}),\n Document(page_content=\"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", metadata={'score': 0.8857628682610436, 'uuid': 'f6706e8c-6c91-452f-8c1b-9559fd924657', 'created_at': '2023-05-25T15:03:30.265302Z', 'role': 'human', 'token_count': 23}),\n Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759670375149477, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),\n Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602854653476563, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),\n Document(page_content='You might want to read Ursula K. Le Guin or Joanna Russ.', metadata={'score': 0.7595293992240313, 'uuid': 'f22f2498-6118-4c74-8718-aa89ccd7e3d6', 'created_at': '2023-05-25T15:03:30.261198Z', 'role': 'ai', 'token_count': 18})]"
+      "text/plain": [
+       "[Document(page_content='Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', metadata={'score': 0.8897321402776546, 'uuid': '1c09603a-52c1-40d7-9d69-29f26256029c', 'created_at': '2023-05-25T15:03:30.268257Z', 'role': 'ai', 'token_count': 56}),\n",
+       " Document(page_content=\"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", metadata={'score': 0.8857628682610436, 'uuid': 'f6706e8c-6c91-452f-8c1b-9559fd924657', 'created_at': '2023-05-25T15:03:30.265302Z', 'role': 'human', 'token_count': 23}),\n",
+       " Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759670375149477, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),\n",
+       " Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602854653476563, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),\n",
+       " Document(page_content='You might want to read Ursula K. Le Guin or Joanna Russ.', metadata={'score': 0.7595293992240313, 'uuid': 'f22f2498-6118-4c74-8718-aa89ccd7e3d6', 'created_at': '2023-05-25T15:03:30.261198Z', 'role': 'ai', 'token_count': 18})]"
+      ]
      },
      "execution_count": 5,
      "metadata": {},
@@ -235,48 +269,44 @@
    ],
    "source": [
     "zep_retriever.get_relevant_documents(\"Who wrote Parable of the Sower?\")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2023-05-25T15:03:34.713354Z",
-     "start_time": "2023-05-25T15:03:34.577974Z"
-    }
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "outputs": [],
-   "source": [],
    "metadata": {
-    "collapsed": false,
     "ExecuteTime": {
      "end_time": "2023-05-18T20:09:21.298710Z",
      "start_time": "2023-05-18T20:09:21.297169Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
     }
-   }
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }

docs/modules/indexes/text_splitters/examples/sentence_transformer_token_splitter.ipynb

@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "73dbcdb9",
+   "metadata": {},
+   "source": [
+    "# SentenceTransformersTokenTextSplitter\n",
+    "\n",
+    "This notebook demonstrates how to use the `SentenceTransformersTokenTextSplitter` text splitter.\n",
+    "\n",
+    "Language models have a token limit. You should not exceed the token limit. When you split your text into chunks it is therefore a good idea to count the number of tokens. There are many tokenizers. When you count tokens in your text you should use the same tokenizer as used in the language model. \n",
+    "\n",
+    "The `SentenceTransformersTokenTextSplitter` is a specialized text splitter for use with the sentence-transformer models. The default behaviour is to split the text into chunks that fit the token window of the sentence transformer model that you would like to use."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9dd5419e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import SentenceTransformersTokenTextSplitter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b43e5d54",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "splitter = SentenceTransformersTokenTextSplitter(chunk_overlap=0)\n",
+    "text = \"Lorem \""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1df84cb4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2\n"
+     ]
+    }
+   ],
+   "source": [
+    "count_start_and_stop_tokens = 2\n",
+    "text_token_count = splitter.count_tokens(text=text) - count_start_and_stop_tokens\n",
+    "print(text_token_count)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d7ad2213",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tokens in text to split: 514\n"
+     ]
+    }
+   ],
+   "source": [
+    "token_multiplier = splitter.maximum_tokens_per_chunk // text_token_count + 1\n",
+    "\n",
+    "# `text_to_split` does not fit in a single chunk\n",
+    "text_to_split = text * token_multiplier\n",
+    "\n",
+    "print(f\"tokens in text to split: {splitter.count_tokens(text=text_to_split)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "818aea04",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "lorem\n"
+     ]
+    }
+   ],
+   "source": [
+    "text_chunks = splitter.split_text(text=text_to_split)\n",
+    "\n",
+    "print(text_chunks[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e9ba4f23",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/indexes/vectorstores/examples/chroma.ipynb

@@ -151,6 +151,15 @@
     "## Similarity search with score"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "346347d7",
+   "metadata": {},
+   "source": [
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 10,

docs/modules/indexes/vectorstores/examples/clickhouse.ipynb

@@ -0,0 +1,399 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "683953b3",
+   "metadata": {},
+   "source": [
+    "# ClickHouse Vector Search\n",
+    "\n",
+    "> [ClickHouse](https://clickhouse.com/) is the fastest and most resource efficient open-source database for real-time apps and analytics with full SQL support and a wide range of functions to assist users in writing analytical queries. Lately added data structures and distance search functions (like `L2Distance`) as well as [approximate nearest neighbor search indexes](https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/annindexes) enable ClickHouse to be used as a high performance and scalable vector database to store and search vectors with SQL.\n",
+    "\n",
+    "This notebook shows how to use functionality related to the `ClickHouse` vector search."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43ead5d5-2c1f-4dce-a69a-cb00e4f9d6f0",
+   "metadata": {},
+   "source": [
+    "## Setting up envrionments"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2c434bc",
+   "metadata": {},
+   "source": [
+    "Setting up local clickhouse server with docker (optional)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "249a7751",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:43:43.035606Z",
+     "start_time": "2023-06-03T08:43:42.618531Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "! docker run -d -p 8123:8123 -p9000:9000 --name langchain-clickhouse-server --ulimit nofile=262144:262144 clickhouse/clickhouse-server:23.4.2.11"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7bd3c1c0",
+   "metadata": {},
+   "source": [
+    "Setup up clickhouse client driver"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9d614bf8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install clickhouse-connect"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15a1d477-9cdb-4d82-b019-96951ecb2b72",
+   "metadata": {},
+   "source": [
+    "We want to use OpenAIEmbeddings so we have to get the OpenAI API Key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "91003ea5-0c8c-436c-a5de-aaeaeef2f458",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:49:35.383673Z",
+     "start_time": "2023-06-03T08:49:33.984547Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "if not os.environ['OPENAI_API_KEY']:\n",
+    "    os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "aac9563e",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:33:31.554934Z",
+     "start_time": "2023-06-03T08:33:31.549590Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import Clickhouse, ClickhouseSettings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a3c3999a",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:33:32.527387Z",
+     "start_time": "2023-06-03T08:33:32.501312Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6e104aee",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:33:35.503823Z",
+     "start_time": "2023-06-03T08:33:33.745832Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Inserting data...: 100%|██████████| 42/42 [00:00<00:00, 2801.49it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "for d in docs:\n",
+    "    d.metadata = {'some': 'metadata'}\n",
+    "settings = ClickhouseSettings(table=\"clickhouse_vector_search_example\")\n",
+    "docsearch = Clickhouse.from_documents(docs, embeddings, config=settings)\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9c608226",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3a8b105",
+   "metadata": {},
+   "source": [
+    "## Get connection info and data schema"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "69996818",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:28:58.252991Z",
+     "start_time": "2023-06-03T08:28:58.197560Z"
+    },
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[92m\u001b[1mdefault.clickhouse_vector_search_example @ localhost:8123\u001b[0m\n",
+      "\n",
+      "\u001b[1musername: None\u001b[0m\n",
+      "\n",
+      "Table Schema:\n",
+      "---------------------------------------------------\n",
+      "|\u001b[94mid                      \u001b[0m|\u001b[96mNullable(String)        \u001b[0m|\n",
+      "|\u001b[94mdocument                \u001b[0m|\u001b[96mNullable(String)        \u001b[0m|\n",
+      "|\u001b[94membedding               \u001b[0m|\u001b[96mArray(Float32)          \u001b[0m|\n",
+      "|\u001b[94mmetadata                \u001b[0m|\u001b[96mObject('json')          \u001b[0m|\n",
+      "|\u001b[94muuid                    \u001b[0m|\u001b[96mUUID                    \u001b[0m|\n",
+      "---------------------------------------------------\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(docsearch))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "324ac147",
+   "metadata": {},
+   "source": [
+    "### Clickhouse table schema"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b5bd7c5b",
+   "metadata": {},
+   "source": [
+    "> Clickhouse table will be automatically created if not exist by default. Advanced users could pre-create the table with optimized settings. For distributed Clickhouse cluster with sharding, table engine should be configured as `Distributed`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "54f4f561",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Clickhouse Table DDL:\n",
+      "\n",
+      "CREATE TABLE IF NOT EXISTS default.clickhouse_vector_search_example(\n",
+      "    id Nullable(String),\n",
+      "    document Nullable(String),\n",
+      "    embedding Array(Float32),\n",
+      "    metadata JSON,\n",
+      "    uuid UUID DEFAULT generateUUIDv4(),\n",
+      "    CONSTRAINT cons_vec_len CHECK length(embedding) = 1536,\n",
+      "    INDEX vec_idx embedding TYPE annoy(100,'L2Distance') GRANULARITY 1000\n",
+      ") ENGINE = MergeTree ORDER BY uuid SETTINGS index_granularity = 8192\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"Clickhouse Table DDL:\\n\\n{docsearch.schema}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f59360c0",
+   "metadata": {},
+   "source": [
+    "## Filtering\n",
+    "\n",
+    "You can have direct access to ClickHouse SQL where statement. You can write `WHERE` clause following standard SQL.\n",
+    "\n",
+    "**NOTE**: Please be aware of SQL injection, this interface must not be directly called by end-user.\n",
+    "\n",
+    "If you custimized your `column_map` under your setting, you search with filter like this:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "232055f6",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:29:36.680805Z",
+     "start_time": "2023-06-03T08:29:34.963676Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Inserting data...: 100%|██████████| 42/42 [00:00<00:00, 6939.56it/s]\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.vectorstores import Clickhouse, ClickhouseSettings\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "\n",
+    "loader = TextLoader('../../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "\n",
+    "for i, d in enumerate(docs):\n",
+    "    d.metadata = {'doc_id': i}\n",
+    "\n",
+    "docsearch = Clickhouse.from_documents(docs, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ddbcee77",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:29:43.487436Z",
+     "start_time": "2023-06-03T08:29:43.040831Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.6779101415357189 {'doc_id': 0} Madam Speaker, Madam...\n",
+      "0.6997970363474885 {'doc_id': 8} And so many families...\n",
+      "0.7044504914336727 {'doc_id': 1} Groups of citizens b...\n",
+      "0.7053558702165094 {'doc_id': 6} And I’m taking robus...\n"
+     ]
+    }
+   ],
+   "source": [
+    "meta = docsearch.metadata_column\n",
+    "output = docsearch.similarity_search_with_relevance_scores('What did the president say about Ketanji Brown Jackson?', \n",
+    "                                                           k=4, where_str=f\"{meta}.doc_id<10\")\n",
+    "for d, dist in output:\n",
+    "    print(dist, d.metadata, d.page_content[:20] + '...')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a359ed74",
+   "metadata": {},
+   "source": [
+    "## Deleting your data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "fb6a9d36",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-06-03T08:30:24.822384Z",
+     "start_time": "2023-06-03T08:30:24.798571Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "docsearch.drop()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/indexes/vectorstores/examples/docarray_hnsw.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "2ce41f46-5711-4311-b04d-2fe233ac5b1b",
    "metadata": {},
@@ -13,6 +14,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "7ee37d28",
    "metadata": {},
@@ -55,6 +57,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "8dbb6de2",
    "metadata": {
@@ -98,6 +101,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "ed6f905b-4853-4a44-9730-614aa8e22b78",
    "metadata": {},
@@ -145,6 +149,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "3febb987-e903-416f-af26-6897d84c8d61",
    "metadata": {},
@@ -152,6 +157,15 @@
     "### Similarity search with score"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "bb1df11a",
+   "metadata": {},
+   "source": [
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 7,

docs/modules/indexes/vectorstores/examples/docarray_in_memory.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "a3afefb0-7e99-4912-a222-c6b186da11af",
    "metadata": {},
@@ -13,6 +14,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "5031a3ec",
    "metadata": {},
@@ -54,6 +56,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "6e57a389-f637-4b8f-9ab2-759ae7485f78",
    "metadata": {},
@@ -95,6 +98,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "efbb6684-3846-4332-a624-ddd4d75844c1",
    "metadata": {},
@@ -142,6 +146,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "43896697-f99e-47b6-9117-47a25e9afa9c",
    "metadata": {},
@@ -149,6 +154,15 @@
     "### Similarity search with score"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "414a9bc9",
+   "metadata": {},
+   "source": [
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 7,

docs/modules/indexes/vectorstores/examples/faiss.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -29,6 +30,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "38237514-b3fa-44a4-9cff-30cd6bf50073",
    "metadata": {},
@@ -45,7 +47,7 @@
    },
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "OpenAI API Key: ········\n"
@@ -137,12 +139,13 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "f13473b5",
    "metadata": {},
    "source": [
     "## Similarity Search with score\n",
-    "There are some FAISS specific methods. One of them is `similarity_search_with_score`, which allows you to return not only the documents but also the similarity score of the query to them."
+    "There are some FAISS specific methods. One of them is `similarity_search_with_score`, which allows you to return not only the documents but also the distance score of the query to them. The returned distance score is L2 distance. Therefore, a lower score is better."
    ]
   },
   {
@@ -178,6 +181,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "f34420cf",
    "metadata": {},
@@ -197,6 +201,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "31bda7fd",
    "metadata": {},
@@ -257,6 +262,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "57da60d4",
    "metadata": {},

docs/modules/indexes/vectorstores/examples/mongodb_atlas_vector_search.ipynb

@@ -118,15 +118,14 @@
     "\n",
     "db_name = \"lanchain_db\"\n",
     "collection_name = \"langchain_col\"\n",
-    "namespace = f\"{db_name}.{collection_name}\"\n",
+    "collection = client[db_name][collection_name]\n",
     "index_name = \"langchain_demo\"\n",
     "\n",
     "# insert the documents in MongoDB Atlas with their embedding\n",
     "docsearch = MongoDBAtlasVectorSearch.from_documents(\n",
     "    docs,\n",
     "    embeddings,\n",
-    "    client=client,\n",
-    "    namespace=namespace,\n",
+    "    collection=collection,\n",
     "    index_name=index_name\n",
     ")\n",
     "\n",

docs/modules/indexes/vectorstores/examples/myscale.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -13,6 +14,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "43ead5d5-2c1f-4dce-a69a-cb00e4f9d6f0",
    "metadata": {},
@@ -33,6 +35,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "15a1d477-9cdb-4d82-b019-96951ecb2b72",
    "metadata": {},
@@ -54,6 +57,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "a9d16fa3",
    "metadata": {},
@@ -169,6 +173,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "e3a8b105",
    "metadata": {},
@@ -187,6 +192,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "f59360c0",
    "metadata": {},
@@ -231,6 +237,24 @@
     "docsearch = MyScale.from_documents(docs, embeddings)"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "8d867b05",
+   "metadata": {},
+   "source": [
+    "### Similarity search with score"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "9ec25cc5",
+   "metadata": {},
+   "source": [
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 16,
@@ -257,6 +281,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "a359ed74",
    "metadata": {},

docs/modules/indexes/vectorstores/examples/pgvector.ipynb

@@ -24,13 +24,48 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 60,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: pgvector in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.1.8)\n",
+      "Requirement already satisfied: numpy in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from pgvector) (1.24.3)\n",
+      "Requirement already satisfied: openai in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.27.7)\n",
+      "Requirement already satisfied: requests>=2.20 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (2.28.2)\n",
+      "Requirement already satisfied: tqdm in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (4.65.0)\n",
+      "Requirement already satisfied: aiohttp in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (3.8.4)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (3.1.0)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (3.4)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (1.26.15)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (2023.5.7)\n",
+      "Requirement already satisfied: attrs>=17.3.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (23.1.0)\n",
+      "Requirement already satisfied: multidict<7.0,>=4.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (6.0.4)\n",
+      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (4.0.2)\n",
+      "Requirement already satisfied: yarl<2.0,>=1.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.9.2)\n",
+      "Requirement already satisfied: frozenlist>=1.1.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.3.3)\n",
+      "Requirement already satisfied: aiosignal>=1.1.2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.3.1)\n",
+      "Requirement already satisfied: psycopg2-binary in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (2.9.6)\n",
+      "Requirement already satisfied: tiktoken in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.4.0)\n",
+      "Requirement already satisfied: regex>=2022.1.18 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from tiktoken) (2023.5.5)\n",
+      "Requirement already satisfied: requests>=2.26.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from tiktoken) (2.28.2)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (3.1.0)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (3.4)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (1.26.15)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (2023.5.7)\n"
+     ]
+    }
+   ],
    "source": [
-    "!pip install pgvector"
+    "# Pip install necessary package\n",
+    "!pip install pgvector\n",
+    "!pip install openai\n",
+    "!pip install psycopg2-binary\n",
+    "!pip install tiktoken"
    ]
   },
   {
@@ -42,9 +77,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "OpenAI API Key:········\n"
+     ]
+    }
+   ],
    "source": [
     "import os\n",
     "import getpass\n",
@@ -54,7 +97,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 61,
    "metadata": {
     "tags": []
    },
@@ -65,7 +108,7 @@
        "False"
       ]
      },
-     "execution_count": 1,
+     "execution_count": 61,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -79,7 +122,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 62,
    "metadata": {
     "tags": []
    },
@@ -94,7 +137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 63,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -129,6 +172,29 @@
     "# postgresql+psycopg2://username:password@localhost:5432/database_name"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# ## PGVector needs the connection string to the database.\n",
+    "# ## We will load it from the environment variables.\n",
+    "# import os\n",
+    "# CONNECTION_STRING = PGVector.connection_string_from_db_params(\n",
+    "#     driver=os.environ.get(\"PGVECTOR_DRIVER\", \"psycopg2\"),\n",
+    "#     host=os.environ.get(\"PGVECTOR_HOST\", \"localhost\"),\n",
+    "#     port=int(os.environ.get(\"PGVECTOR_PORT\", \"5432\")),\n",
+    "#     database=os.environ.get(\"PGVECTOR_DATABASE\", \"rd-embeddings\"),\n",
+    "#     user=os.environ.get(\"PGVECTOR_USER\", \"admin\"),\n",
+    "#     password=os.environ.get(\"PGVECTOR_PASSWORD\", \"password\"),\n",
+    "# )\n",
+    "\n",
+    "\n",
+    "# ## Example\n",
+    "# # postgresql+psycopg2://username:password@localhost:5432/database_name"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -145,7 +211,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -165,7 +231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 70,
    "metadata": {},
    "outputs": [
     {
@@ -173,7 +239,7 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------------\n",
-      "Score:  0.6076628081132506\n",
+      "Score:  0.6076804864602984\n",
       "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
       "\n",
       "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
@@ -183,7 +249,7 @@
       "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
       "--------------------------------------------------------------------------------\n",
       "--------------------------------------------------------------------------------\n",
-      "Score:  0.6076628081132506\n",
+      "Score:  0.6076804864602984\n",
       "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
       "\n",
       "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
@@ -193,24 +259,32 @@
       "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
       "--------------------------------------------------------------------------------\n",
       "--------------------------------------------------------------------------------\n",
-      "Score:  0.6076804780049968\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "Score:  0.659062774389974\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
       "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
       "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \n",
       "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \n",
+      "\n",
+      "We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
+      "\n",
+      "We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
       "--------------------------------------------------------------------------------\n",
       "--------------------------------------------------------------------------------\n",
-      "Score:  0.6076804780049968\n",
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "Score:  0.659062774389974\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
       "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
       "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \n",
       "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \n",
+      "\n",
+      "We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
+      "\n",
+      "We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
       "--------------------------------------------------------------------------------\n"
      ]
     }
@@ -224,7 +298,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -232,7 +305,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -241,12 +313,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 55,
    "metadata": {},
    "outputs": [],
    "source": [
+    "data=docs\n",
+    "api_key=os.environ['OPENAI_API_KEY']\n",
     "db = PGVector.from_documents(\n",
-    "    documents=data,\n",
+    "    documents=docs,\n",
     "    embedding=embeddings,\n",
     "    collection_name=collection_name,\n",
     "    connection_string=connection_string,\n",
@@ -257,7 +331,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -266,10 +339,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
+    "connection_string = CONNECTION_STRING \n",
+    "embedding=embeddings\n",
+    "collection_name=\"state_of_the_union\"\n",
+    "from langchain.vectorstores.pgvector import DistanceStrategy\n",
     "store = PGVector(\n",
     "    connection_string=connection_string, \n",
     "    embedding_function=embedding, \n",
@@ -279,6 +356,127 @@
     "\n",
     "retriever = store.as_retriever()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "vectorstore=<langchain.vectorstores.pgvector.PGVector object at 0x7fe9a1b1c670> search_type='similarity' search_kwargs={}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(retriever)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6075870262188066), (Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6075870262188066), (Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6589478388546668), (Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', metadata={'source': '../../../state_of_the_union.txt'}), 0.6589478388546668)]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# When we have an existing PG VEctor \n",
+    "DEFAULT_DISTANCE_STRATEGY = DistanceStrategy.EUCLIDEAN\n",
+    "db1 = PGVector.from_existing_index(\n",
+    "    embedding=embeddings,\n",
+    "    collection_name=\"state_of_the_union\",\n",
+    "    distance_strategy=DEFAULT_DISTANCE_STRATEGY,\n",
+    "    pre_delete_collection = False,\n",
+    "    connection_string=CONNECTION_STRING,\n",
+    ")\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs_with_score: List[Tuple[Document, float]] = db1.similarity_search_with_score(query)\n",
+    "print(docs_with_score)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6075870262188066\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "--------------------------------------------------------------------------------\n",
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6075870262188066\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "--------------------------------------------------------------------------------\n",
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6589478388546668\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
+      "\n",
+      "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \n",
+      "\n",
+      "We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \n",
+      "\n",
+      "We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
+      "\n",
+      "We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
+      "--------------------------------------------------------------------------------\n",
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6589478388546668\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
+      "\n",
+      "We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \n",
+      "\n",
+      "We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \n",
+      "\n",
+      "We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
+      "\n",
+      "We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
+      "--------------------------------------------------------------------------------\n"
+     ]
+    }
+   ],
+   "source": [
+    "for doc, score in docs_with_score:\n",
+    "    print(\"-\" * 80)\n",
+    "    print(\"Score: \", score)\n",
+    "    print(doc.page_content)\n",
+    "    print(\"-\" * 80)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -297,7 +495,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.9.7"
   }
  },
  "nbformat": 4,

docs/modules/indexes/vectorstores/examples/qdrant.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -33,6 +34,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "7b2f111b-357a-4f42-9730-ef0603bdc1b5",
    "metadata": {},
@@ -49,7 +51,7 @@
    },
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
       "OpenAI API Key: ········\n"
@@ -104,6 +106,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "eeead681",
    "metadata": {},
@@ -140,6 +143,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "59f0b954",
    "metadata": {},
@@ -170,6 +174,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "749658ce",
    "metadata": {},
@@ -200,6 +205,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "c9e21ce9",
    "metadata": {},
@@ -231,6 +237,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "93540013",
    "metadata": {},
@@ -279,6 +286,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1f9215c8",
    "metadata": {
@@ -341,13 +349,15 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1bda9bf5",
    "metadata": {},
    "source": [
     "## Similarity search with score\n",
     "\n",
-    "Sometimes we might want to perform the search, but also obtain a relevancy score to know how good is a particular result."
+    "Sometimes we might want to perform the search, but also obtain a relevancy score to know how good is a particular result. \n",
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
    ]
   },
   {
@@ -400,6 +410,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "525e3582",
    "metadata": {},
@@ -410,6 +421,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1c2c58dc",
    "metadata": {},
@@ -423,6 +435,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "c58c30bf",
    "metadata": {
@@ -503,6 +516,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "691a82d6",
    "metadata": {},
@@ -540,6 +554,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "0c851b4f",
    "metadata": {},
@@ -602,6 +617,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "0358ecde",
    "metadata": {},

docs/modules/indexes/vectorstores/examples/supabase.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -9,6 +10,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "cc80fa84-1f2f-48b4-bd39-3e6412f012f1",
    "metadata": {},
@@ -85,6 +87,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "69bff365-3039-4ff8-a641-aa190166179d",
    "metadata": {},
@@ -236,6 +239,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "18152965",
    "metadata": {},
@@ -243,6 +247,15 @@
     "## Similarity search with score\n"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "ea13e80a",
+   "metadata": {},
+   "source": [
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -276,6 +289,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "794a7552",
    "metadata": {},

docs/modules/indexes/vectorstores/examples/tigris.ipynb

@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Tigris\n",
+    "\n",
+    "> [Tigris](htttps://tigrisdata.com) is an open source Serverless NoSQL Database and Search Platform designed to simplify building high-performance vector search applications.\n",
+    "> Tigris eliminates the infrastructure complexity of managing, operating, and synchronizing multiple tools, allowing you to focus on building great applications instead."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "This notebook guides you how to use Tigris as your VectorStore"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Pre requisites**\n",
+    "1. An OpenAI account. You can sign up for an account [here](https://platform.openai.com/)\n",
+    "2. [Sign up for a free Tigris account](https://console.preview.tigrisdata.cloud). Once you have signed up for the Tigris account, create a new project called `vectordemo`. Next, make a note of the *Uri* for the region you've created your project in, the **clientId** and **clientSecret**. You can get all this information from the **Application Keys** section of the project."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "Let's first install our dependencies:"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "!pip install tigrisdb openapi-schema-pydantic openai tiktoken"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "We will load the `OpenAI` api key and `Tigris` credentials in our environment"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')\n",
+    "os.environ['TIGRIS_PROJECT'] = getpass.getpass('Tigris Project Name:')\n",
+    "os.environ['TIGRIS_CLIENT_ID'] = getpass.getpass('Tigris Client Id:')\n",
+    "os.environ['TIGRIS_CLIENT_SECRET'] = getpass.getpass('Tigris Client Secret:')"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import Tigris\n",
+    "from langchain.document_loaders import TextLoader"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Initialize Tigris vector store\n",
+    "Let's import our test dataset:"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "loader = TextLoader('../../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "vector_store = Tigris.from_documents(docs, embeddings, index_name=\"my_embeddings\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Similarity Search"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "found_docs = vector_store.similarity_search(query)\n",
+    "print(found_docs)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Similarity Search with score (vector distance)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = vector_store.similarity_search_with_score(query)\n",
+    "for (doc, score) in result:\n",
+    "    print(f\"document={doc}, score={score}\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

docs/modules/indexes/vectorstores/examples/vectara.ipynb

@@ -1,21 +1,23 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
    "source": [
     "# Vectara\n",
     "\n",
-    ">[Vectara](https://Vectara.com/docs/) is a API platform for building LLM-powered applications. It provides a simple to use API for document indexing and query that is managed by Vectara and is optimized for performance and accuracy. \n",
+    ">[Vectara](https://vectara.com/) is a API platform for building LLM-powered applications. It provides a simple to use API for document indexing and query that is managed by Vectara and is optimized for performance and accuracy. \n",
     "\n",
     "\n",
     "This notebook shows how to use functionality related to the `Vectara` vector database. \n",
     "\n",
-    "See the [Vectara API documentation ](https://Vectara.com/docs/) for more information on how to use the API."
+    "See the [Vectara API documentation ](https://docs.vectara.com/docs/) for more information on how to use the API."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "7b2f111b-357a-4f42-9730-ef0603bdc1b5",
    "metadata": {},
@@ -87,6 +89,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "eeead681",
    "metadata": {},
@@ -113,6 +116,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1f9215c8",
    "metadata": {
@@ -169,6 +173,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "1bda9bf5",
    "metadata": {},
@@ -222,6 +227,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "691a82d6",
    "metadata": {},

docs/modules/indexes/vectorstores/examples/weaviate.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -47,6 +48,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "6b34828d-e627-4d85-aabd-eeb15d9f4b00",
    "metadata": {},
@@ -165,6 +167,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "a15863ee",
    "metadata": {},
@@ -172,6 +175,16 @@
     "## Similarity search with score"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "64e03db8",
+   "metadata": {},
+   "source": [
+    "Sometimes we might want to perform the search, but also obtain a relevancy score to know how good is a particular result. \n",
+    "The returned distance score is cosine distance. Therefore, a lower score is better."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -214,6 +227,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "05fd146c",
    "metadata": {},

docs/modules/memory.rst

@@ -9,16 +9,15 @@ By default, Chains and Agents are stateless,
 meaning that they treat each incoming query independently (as are the underlying LLMs and chat models).
 In some applications (chatbots being a GREAT example) it is highly important
 to remember previous interactions, both at a short term but also at a long term level.
-The concept of “Memory” exists to do exactly that.
+The **Memory** does exactly that.
 
 LangChain provides memory components in two forms.
 First, LangChain provides helper utilities for managing and manipulating previous chat messages.
 These are designed to be modular and useful regardless of how they are used.
 Secondly, LangChain provides easy ways to incorporate these utilities into chains.
 
-The following sections of documentation are provided:
-
-- `Getting Started <./memory/getting_started.html>`_: An overview of how to get started with different types of memory.
+|
+- `Getting Started <./memory/getting_started.html>`_: An overview of different types of memory.
 
 - `How-To Guides <./memory/how_to_guides.html>`_: A collection of how-to guides. These highlight different types of memory, as well as how to use memory in chains.
 
@@ -28,6 +27,7 @@ The following sections of documentation are provided:
    :maxdepth: 1
    :caption: Memory
    :name: Memory
+   :hidden:
 
-   ./memory/getting_started.ipynb
+   ./memory/getting_started.html
    ./memory/how_to_guides.rst

docs/modules/memory/examples/momento_chat_message_history.ipynb

@@ -5,7 +5,7 @@
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# Momento\n",
+    "# Momento Chat Message History\n",
     "\n",
     "This notebook goes over how to use [Momento Cache](https://gomomento.com) to store chat message history using the `MomentoChatMessageHistory` class. See the Momento [docs](https://docs.momentohq.com/getting-started) for more detail on how to get set up with Momento.\n",
     "\n",
@@ -27,7 +27,7 @@
     "\n",
     "session_id = \"foo\"\n",
     "cache_name = \"langchain\"\n",
-    "ttl = timedelta(days=1),\n",
+    "ttl = timedelta(days=1)\n",
     "history = MomentoChatMessageHistory.from_client_params(\n",
     "    session_id, \n",
     "    cache_name,\n",

docs/modules/models.rst

@@ -11,38 +11,28 @@ but we have individual pages for each model type.
 The pages contain more detailed "how-to" guides for working with that model,
 as well as a list of different model providers.
 
-**LLMs**
-
-Large Language Models (LLMs) are the first type of models we cover.
-These models take a text string as input, and return a text string as output.
+|
+- `Getting Started <./models/getting_started.html>`_: An overview of the models.
 
 
-**Chat Models**
+Model Types
+-----------
 
-Chat Models are the second type of models we cover.
-These models are usually backed by a language model, but their APIs are more structured.
-Specifically, these models take a list of Chat Messages as input, and return a Chat Message.
+- `LLMs <./models/llms.html>`_: **Large Language Models (LLMs)** take a text string as input and return a text string as output.
 
-**Text Embedding Models**
+- `Chat Models <./models/chat.html>`_: **Chat Models** are usually backed by a language model, but their APIs are more structured.
+  Specifically, these models take a list of Chat Messages as input, and return a Chat Message.
 
-The third type of models we cover are text embedding models.
-These models take text as input and return a list of floats.
+- `Text Embedding Models <./models/text_embedding.html>`_: **Text embedding models** take text as input and return a list of floats.
 
-Getting Started
----------------
-
-.. toctree::
-   :maxdepth: 1
-
-   ./models/getting_started.ipynb
-
-
-Go Deeper
----------
 
 .. toctree::
    :maxdepth: 1
+   :caption: Models
+   :name: models
+   :hidden:
 
+   ./models/getting_started.html
    ./models/llms.rst
    ./models/chat.rst
    ./models/text_embedding.rst

docs/modules/models/chat/integrations/anthropic.ipynb

@@ -7,7 +7,12 @@
    "source": [
     "# Anthropic\n",
     "\n",
-    "This notebook covers how to get started with Anthropic chat models."
+    "\n",
+    ">[Anthropic](https://en.wikipedia.org/wiki/Anthropic) is an American artificial intelligence (AI) startup and \n",
+    "> public-benefit corporation, founded by former members of OpenAI. `Anthropic` specializes in developing general AI \n",
+    "> systems and language models, with a company ethos of responsible AI usage.\n",
+    "> `Anthropic` develops a chatbot, named `Claude`. Similar to `ChatGPT`, `Claude` uses a messaging \n",
+    "> interface where users can submit questions or requests and receive highly detailed and relevant responses.\n"
    ]
   },
   {
@@ -171,7 +176,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/models/chat/integrations/google_vertex_ai_palm.ipynb

@@ -4,9 +4,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Google Cloud Platform Vertex AI PaLM \n",
+    "# Google Vertex AI PaLM \n",
     "\n",
-    "Note: This is seperate from the Google PaLM integration. Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there. \n",
+    ">[Vertex AI](https://cloud.google.com/vertex-ai/docs/start/introduction-unified-platform) is a machine learning (ML) \n",
+    "> platform that lets you train and deploy ML models and AI applications. \n",
+    "> `Vertex AI` combines data engineering, data science, and ML engineering workflows, enabling your teams to \n",
+    "> collaborate using a common toolset.\n",
+    "\n",
+    "**Note:** This is seperate from the Google PaLM integration. Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there. \n",
     "\n",
     "PaLM API on Vertex AI is a Preview offering, subject to the Pre-GA Offerings Terms of the [GCP Service Specific Terms](https://cloud.google.com/terms/service-terms). \n",
     "\n",
@@ -157,7 +162,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {

docs/modules/models/chat/integrations/promptlayer_chatopenai.ipynb

@@ -1,18 +1,19 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "959300d4",
    "metadata": {},
    "source": [
     "# PromptLayer ChatOpenAI\n",
     "\n",
-    "This example showcases how to connect to [PromptLayer](https://www.promptlayer.com) to start recording your ChatOpenAI requests."
+    ">[PromptLayer](https://docs.promptlayer.com/what-is-promptlayer/wxpF9EZkUwvdkwvVE9XEvC/how-promptlayer-works/dvgGSxNe6nB1jj8mUVbG8r) \n",
+    "> is a devtool that allows you to track, manage, and share your GPT prompt engineering. \n",
+    "> It acts as a middleware between your code and OpenAI's python library, recording all your API requests \n",
+    "> and saving relevant metadata for easy exploration and search in the [PromptLayer](https://www.promptlayer.com) dashboard."
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "6a45943e",
    "metadata": {},
@@ -56,7 +57,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "8564ce7d",
    "metadata": {},
@@ -78,7 +78,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "bf0294de",
    "metadata": {},
@@ -110,7 +109,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "a2d76826",
    "metadata": {},
@@ -125,7 +123,6 @@
    "source": []
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "c43803d1",
    "metadata": {},
@@ -161,7 +158,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "base",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -175,7 +172,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.8 (default, Apr 13 2021, 12:59:45) \n[Clang 10.0.0 ]"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {

docs/modules/models/llms/integrations/aviary.ipynb

@@ -0,0 +1,103 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9597802c",
+   "metadata": {},
+   "source": [
+    "# Aviary\n",
+    "\n",
+    "[Aviary](https://www.anyscale.com/) is an open source tooklit for evaluating and deploying production open source LLMs. \n",
+    "\n",
+    "This example goes over how to use LangChain to interact with `Aviary`. You can try Aviary out [https://aviary.anyscale.com](here).\n",
+    "\n",
+    "You can find out more about Aviary at https://github.com/ray-project/aviary. \n",
+    "\n",
+    "One Aviary instance can serve multiple models. You can get a list of the available models by using the cli:\n",
+    "\n",
+    "`% aviary models`\n",
+    "\n",
+    "Or you can connect directly to the endpoint and get a list of available models by using the `/models` endpoint.\n",
+    "\n",
+    "The constructor requires a url for an Aviary backend, and optionally a token to validate the connection. \n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "6fb585dd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.llms import Aviary\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3fec5a59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = Aviary(model='amazon/LightGPT', aviary_url=os.environ['AVIARY_URL'], aviary_token=os.environ['AVIARY_TOKEN'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4efd54dd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Love is an emotion that involves feelings of attraction, affection and empathy for another person. It can also refer to a deep bond between two people or groups of people. Love can be expressed in many different ways, such as through words, actions, gestures, music, art, literature, and other forms of communication.\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = llm.predict('What is the meaning of love?')\n",
+    "print(result) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "27e526b6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/models/llms/integrations/azure_openai_example.ipynb

@@ -17,8 +17,8 @@
     "```bash\n",
     "# Set this to `azure`\n",
     "export OPENAI_API_TYPE=azure\n",
-    "# The API version you want to use: set this to `2022-12-01` for the released version.\n",
-    "export OPENAI_API_VERSION=2022-12-01\n",
+    "# The API version you want to use: set this to `2023-03-15-preview` for the released version.\n",
+    "export OPENAI_API_VERSION=2023-03-15-preview\n",
     "# The base URL for your Azure OpenAI resource.  You can find this in the Azure portal under your Azure OpenAI resource.\n",
     "export OPENAI_API_BASE=https://your-resource-name.openai.azure.com\n",
     "# The API key for your Azure OpenAI resource.  You can find this in the Azure portal under your Azure OpenAI resource.\n",
@@ -70,7 +70,7 @@
    "source": [
     "import os\n",
     "os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
-    "os.environ[\"OPENAI_API_VERSION\"] = \"2022-12-01\"\n",
+    "os.environ[\"OPENAI_API_VERSION\"] = \"2023-03-15-preview\"\n",
     "os.environ[\"OPENAI_API_BASE\"] = \"...\"\n",
     "os.environ[\"OPENAI_API_KEY\"] = \"...\""
    ]

docs/modules/models/llms/integrations/beam.ipynb

@@ -6,7 +6,11 @@
     "id": "J-yvaDTmTTza"
    },
    "source": [
-    "# Beam integration for langchain\n",
+    "# Beam\n",
+    "\n",
+    ">[Beam](https://docs.beam.cloud/introduction) makes it easy to run code on GPUs, deploy scalable web APIs, \n",
+    "> schedule cron jobs, and run massively parallel workloads — without managing any infrastructure.\n",
+    "\n",
     "\n",
     "Calls the Beam API wrapper to deploy and make subsequent calls to an instance of the gpt2 LLM in a cloud deployment. Requires installation of the Beam library and registration of Beam Client ID and Client Secret. By calling the wrapper an instance of the model is created and run, with returned text relating to the prompt. Additional calls can then be made by directly calling the Beam API.\n",
     "\n",
@@ -151,9 +155,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }

docs/modules/models/llms/integrations/bedrock.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Amazon Bedrock"
+    "# Bedrock"
    ]
   },
   {

docs/modules/models/llms/integrations/huggingface_pipelines.ipynb

@@ -5,9 +5,9 @@
    "id": "959300d4",
    "metadata": {},
    "source": [
-    "# Hugging Face Local Pipelines\n",
+    "# Hugging Face Pipeline\n",
     "\n",
-    "Hugging Face models can be run locally through the `HuggingFacePipeline` class.\n",
+    "`Hugging Face` models can be run locally through the `HuggingFacePipeline` class.\n",
     "\n",
     "The [Hugging Face Model Hub](https://huggingface.co/models) hosts over 120k models, 20k datasets, and 50k demo apps (Spaces), all open source and publicly available, in an online platform where people can easily collaborate and build ML together.\n",
     "\n",
@@ -137,7 +137,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/models/llms/integrations/jsonformer_experimental.ipynb

@@ -5,9 +5,9 @@
    "id": "fdd7864c-93e6-4eb4-a923-b80d2ae4377d",
    "metadata": {},
    "source": [
-    "# Structured Decoding with JSONFormer\n",
+    "# Jsonformer\n",
     "\n",
-    "[JSONFormer](https://github.com/1rgs/jsonformer) is a library that wraps local HuggingFace pipeline models for structured decoding of a subset of the JSON Schema.\n",
+    "[Jsonformer](https://github.com/1rgs/jsonformer) is a library that wraps local `HuggingFace pipeline` models for structured decoding of a subset of the JSON Schema.\n",
     "\n",
     "It works by filling in the structure tokens and then sampling the content tokens from the model.\n",
     "\n",
@@ -272,7 +272,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/models/llms/integrations/predictionguard.ipynb

@@ -1,222 +1,233 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "mesCTyhnJkNS"
+   },
+   "source": [
+    "# Prediction Guard\n",
+    "\n",
+    ">[Prediction Guard](https://docs.predictionguard.com/) gives a quick and easy access to state-of-the-art open and closed access LLMs, without  needing to spend days and weeks figuring out all of the implementation details, managing a bunch of different API specs, and setting up the infrastructure for model deployments."
+   ]
   },
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3RqWPav7AtKL"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install predictionguard langchain"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "import os\n",
-        "\n",
-        "import predictionguard as pg\n",
-        "from langchain.llms import PredictionGuard\n",
-        "from langchain import PromptTemplate, LLMChain"
-      ],
-      "metadata": {
-        "id": "2xe8JEUwA7_y"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# Basic LLM usage\n",
-        "\n"
-      ],
-      "metadata": {
-        "id": "mesCTyhnJkNS"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Optional, add your OpenAI API Key. This is optional, as Prediction Guard allows\n",
-        "# you to access all the latest open access models (see https://docs.predictionguard.com)\n",
-        "os.environ[\"OPENAI_API_KEY\"] = \"<your OpenAI api key>\"\n",
-        "\n",
-        "# Your Prediction Guard API key. Get one at predictionguard.com\n",
-        "os.environ[\"PREDICTIONGUARD_TOKEN\"] = \"<your Prediction Guard access token>\""
-      ],
-      "metadata": {
-        "id": "kp_Ymnx1SnDG"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")"
-      ],
-      "metadata": {
-        "id": "Ua7Mw1N4HcER"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "pgllm(\"Tell me a joke\")"
-      ],
-      "metadata": {
-        "id": "Qo2p5flLHxrB"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# Control the output structure/ type of LLMs"
-      ],
-      "metadata": {
-        "id": "EyBYaP_xTMXH"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "template = \"\"\"Respond to the following query based on the context.\n",
-        "\n",
-        "Context: EVERY comment, DM + email suggestion has led us to this EXCITING announcement! 🎉 We have officially added TWO new candle subscription box options! 📦\n",
-        "Exclusive Candle Box - $80 \n",
-        "Monthly Candle Box - $45 (NEW!)\n",
-        "Scent of The Month Box - $28 (NEW!)\n",
-        "Head to stories to get ALLL the deets on each box! 👆 BONUS: Save 50% on your first box with code 50OFF! 🎉\n",
-        "\n",
-        "Query: {query}\n",
-        "\n",
-        "Result: \"\"\"\n",
-        "prompt = PromptTemplate(template=template, input_variables=[\"query\"])"
-      ],
-      "metadata": {
-        "id": "55uxzhQSTPqF"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# Without \"guarding\" or controlling the output of the LLM.\n",
-        "pgllm(prompt.format(query=\"What kind of post is this?\"))"
-      ],
-      "metadata": {
-        "id": "yersskWbTaxU"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "# With \"guarding\" or controlling the output of the LLM. See the \n",
-        "# Prediction Guard docs (https://docs.predictionguard.com) to learn how to \n",
-        "# control the output with integer, float, boolean, JSON, and other types and\n",
-        "# structures.\n",
-        "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\", \n",
-        "                        output={\n",
-        "                                \"type\": \"categorical\",\n",
-        "                                \"categories\": [\n",
-        "                                    \"product announcement\", \n",
-        "                                    \"apology\", \n",
-        "                                    \"relational\"\n",
-        "                                    ]\n",
-        "                                })\n",
-        "pgllm(prompt.format(query=\"What kind of post is this?\"))"
-      ],
-      "metadata": {
-        "id": "PzxSbYwqTm2w"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "markdown",
-      "source": [
-        "# Chaining"
-      ],
-      "metadata": {
-        "id": "v3MzIUItJ8kV"
-      }
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")"
-      ],
-      "metadata": {
-        "id": "pPegEZExILrT"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "template = \"\"\"Question: {question}\n",
-        "\n",
-        "Answer: Let's think step by step.\"\"\"\n",
-        "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
-        "llm_chain = LLMChain(prompt=prompt, llm=pgllm, verbose=True)\n",
-        "\n",
-        "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
-        "\n",
-        "llm_chain.predict(question=question)"
-      ],
-      "metadata": {
-        "id": "suxw62y-J-bg"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [
-        "template = \"\"\"Write a {adjective} poem about {subject}.\"\"\"\n",
-        "prompt = PromptTemplate(template=template, input_variables=[\"adjective\", \"subject\"])\n",
-        "llm_chain = LLMChain(prompt=prompt, llm=pgllm, verbose=True)\n",
-        "\n",
-        "llm_chain.predict(adjective=\"sad\", subject=\"ducks\")"
-      ],
-      "metadata": {
-        "id": "l2bc26KHKr7n"
-      },
-      "execution_count": null,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "source": [],
-      "metadata": {
-        "id": "I--eSa2PLGqq"
-      },
-      "execution_count": null,
-      "outputs": []
-    }
-  ]
-}
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "3RqWPav7AtKL"
+   },
+   "outputs": [],
+   "source": [
+    "! pip install predictionguard langchain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "2xe8JEUwA7_y"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "import predictionguard as pg\n",
+    "from langchain.llms import PredictionGuard\n",
+    "from langchain import PromptTemplate, LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "kp_Ymnx1SnDG"
+   },
+   "outputs": [],
+   "source": [
+    "# Optional, add your OpenAI API Key. This is optional, as Prediction Guard allows\n",
+    "# you to access all the latest open access models (see https://docs.predictionguard.com)\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"<your OpenAI api key>\"\n",
+    "\n",
+    "# Your Prediction Guard API key. Get one at predictionguard.com\n",
+    "os.environ[\"PREDICTIONGUARD_TOKEN\"] = \"<your Prediction Guard access token>\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Ua7Mw1N4HcER"
+   },
+   "outputs": [],
+   "source": [
+    "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Qo2p5flLHxrB"
+   },
+   "outputs": [],
+   "source": [
+    "pgllm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "EyBYaP_xTMXH"
+   },
+   "source": [
+    "# Control the output structure/ type of LLMs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "55uxzhQSTPqF"
+   },
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Respond to the following query based on the context.\n",
+    "\n",
+    "Context: EVERY comment, DM + email suggestion has led us to this EXCITING announcement! 🎉 We have officially added TWO new candle subscription box options! 📦\n",
+    "Exclusive Candle Box - $80 \n",
+    "Monthly Candle Box - $45 (NEW!)\n",
+    "Scent of The Month Box - $28 (NEW!)\n",
+    "Head to stories to get ALLL the deets on each box! 👆 BONUS: Save 50% on your first box with code 50OFF! 🎉\n",
+    "\n",
+    "Query: {query}\n",
+    "\n",
+    "Result: \"\"\"\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"query\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "yersskWbTaxU"
+   },
+   "outputs": [],
+   "source": [
+    "# Without \"guarding\" or controlling the output of the LLM.\n",
+    "pgllm(prompt.format(query=\"What kind of post is this?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "PzxSbYwqTm2w"
+   },
+   "outputs": [],
+   "source": [
+    "# With \"guarding\" or controlling the output of the LLM. See the \n",
+    "# Prediction Guard docs (https://docs.predictionguard.com) to learn how to \n",
+    "# control the output with integer, float, boolean, JSON, and other types and\n",
+    "# structures.\n",
+    "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\", \n",
+    "                        output={\n",
+    "                                \"type\": \"categorical\",\n",
+    "                                \"categories\": [\n",
+    "                                    \"product announcement\", \n",
+    "                                    \"apology\", \n",
+    "                                    \"relational\"\n",
+    "                                    ]\n",
+    "                                })\n",
+    "pgllm(prompt.format(query=\"What kind of post is this?\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "v3MzIUItJ8kV"
+   },
+   "source": [
+    "# Chaining"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "pPegEZExILrT"
+   },
+   "outputs": [],
+   "source": [
+    "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "suxw62y-J-bg"
+   },
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
+    "llm_chain = LLMChain(prompt=prompt, llm=pgllm, verbose=True)\n",
+    "\n",
+    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "\n",
+    "llm_chain.predict(question=question)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "l2bc26KHKr7n"
+   },
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Write a {adjective} poem about {subject}.\"\"\"\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"adjective\", \"subject\"])\n",
+    "llm_chain = LLMChain(prompt=prompt, llm=pgllm, verbose=True)\n",
+    "\n",
+    "llm_chain.predict(adjective=\"sad\", subject=\"ducks\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "I--eSa2PLGqq"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/modules/models/llms/integrations/rellm_experimental.ipynb

@@ -5,11 +5,10 @@
    "id": "fdd7864c-93e6-4eb4-a923-b80d2ae4377d",
    "metadata": {},
    "source": [
-    "# Structured Decoding with RELLM\n",
+    "# ReLLM\n",
     "\n",
-    "[RELLM](https://github.com/r2d4/rellm) is a library that wraps local Hugging Face pipeline models for structured decoding.\n",
-    "\n",
-    "It works by generating tokens one at a time. At each step, it masks tokens that don't conform to the provided partial regular expression.\n",
+    ">[ReLLM](https://github.com/r2d4/rellm) is a library that wraps local Hugging Face pipeline models for structured decoding.\n",
+    ">It works by generating tokens one at a time. At each step, it masks tokens that don't conform to the provided partial regular expression.\n",
     "\n",
     "\n",
     "**Warning - this module is still experimental**"
@@ -200,7 +199,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/models/llms/integrations/sagemaker.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# SageMakerEndpoint\n",
+    "# SageMaker Endpoint\n",
     "\n",
     "[Amazon SageMaker](https://aws.amazon.com/sagemaker/) is a system that can build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows.\n",
     "\n",

docs/modules/models/text_embedding/examples/amazon_bedrock.ipynb

@@ -5,7 +5,9 @@
    "id": "75e378f5-55d7-44b6-8e2e-6d7b8b171ec4",
    "metadata": {},
    "source": [
-    "# Bedrock Embeddings"
+    "# Amazon Bedrock\n",
+    "\n",
+    ">[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes FMs from leading AI startups and Amazon available via an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case.\n"
    ]
   },
   {
@@ -67,7 +69,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/modules/models/text_embedding/examples/azureopenai.ipynb

@@ -5,7 +5,7 @@
    "id": "c3852491",
    "metadata": {},
    "source": [
-    "# AzureOpenAI\n",
+    "# Azure OpenAI\n",
     "\n",
     "Let's load the OpenAI Embedding class with environment variables set to indicate to use Azure endpoints."
    ]
@@ -93,7 +93,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {

docs/modules/models/text_embedding/examples/google_vertex_ai_palm.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Google Cloud Platform Vertex AI PaLM \n",
+    "# Google Vertex AI PaLM \n",
     "\n",
     "Note: This is seperate from the Google PaLM integration. Google has chosen to offer an enterprise version of PaLM through GCP, and this supports the models made available through there. \n",
     "\n",
@@ -100,7 +100,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {

docs/modules/models/text_embedding/examples/huggingface_instruct.ipynb

@@ -5,8 +5,8 @@
    "id": "59428e05",
    "metadata": {},
    "source": [
-    "# InstructEmbeddings\n",
-    "Let's load the HuggingFace instruct Embeddings class."
+    "# HuggingFace Instruct\n",
+    "Let's load the `HuggingFace instruct Embeddings` class."
    ]
   },
   {
@@ -85,7 +85,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {

docs/modules/models/text_embedding/examples/mosaicml.ipynb

@@ -1,11 +1,10 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# MosaicML embeddings\n",
+    "# MosaicML\n",
     "\n",
     "[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
     "\n",
@@ -92,6 +91,11 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
@@ -101,9 +105,10 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/modules/models/text_embedding/examples/sagemaker-endpoint.ipynb

@@ -5,9 +5,9 @@
    "id": "1f83f273",
    "metadata": {},
    "source": [
-    "# SageMaker Endpoint Embeddings\n",
+    "# SageMaker Endpoint\n",
     "\n",
-    "Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
+    "Let's load the `SageMaker Endpoints Embeddings` class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
     "\n",
     "For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). **Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
     "\n",
@@ -122,7 +122,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.6"
   },
   "vscode": {
    "interpreter": {