safe format prompt variables in strings with JSON #15734
Merged
+52
−101
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dosubot
bot
added
the
size:L
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
jerryjliu
changed the title
jerryjliu
changed the base branch from
main
to
jerry/force_openai_struct_output
dosubot
bot
added
size:XXL
dosubot
bot
added
size:M
dosubot
bot
added
size:L
dosubot
bot
added
size:M
dosubot
bot
removed
the
size:M
dosubot
bot
added
the
size:L
barduinor
added a commit
to box-community/llama_index
that referenced
this pull request
Sep 23, 2024
* v0.11.5 (run-llama#15834) * Box bug fix 202409 (run-llama#15836) * fix document matadata for box file * fix BoxSearchOptions class initialization * bump versions to 0.2.1 * Add oreilly course cookbooks (run-llama#15845) * correct course name (run-llama#15859) * clone llama-deploy docs during docs builds (run-llama#15794) * chore(deps-dev): bump cryptography from 43.0.0 to 43.0.1 in /llama-index-core (run-llama#15840) * Refresh Opensearch index after delete operation (run-llama#15854) * Update ImageReader file loading logic (run-llama#15848) * Minor bug in SQQE (run-llama#15861) * v0.11.6 (run-llama#15863) * remove widgets from recent notebooks (run-llama#15864) * Fix image document deserialization issue (run-llama#15857) * Bugfix: Remove warnings during data insertion for Hybrid Search due to duplicated columns in the schema (run-llama#15846) * Add TablestoreVectorStore. (run-llama#15657) * Removed unused `llama-index-llms-anthropic` dependency from Bedrock Converse (run-llama#15869) Removed unused `llama-index-llms-anthropic` dependency. Incremented to `0.3.0`. * Update bedrock.py (run-llama#15879) Fix minor issue in error message * Add tool calling example in NVIDIA notebook (run-llama#15842) * NVIDIA: Completion fixes (run-llama#15820) * Fix PGVectorStore with latest pydantic, update pydantic imports (run-llama#15886) * add type ignore for streaming agents (run-llama#15887) * [wip] force openai structured output (run-llama#15706) * feature: Make SentenceSplitter's secondary_chunking_regex optional (run-llama#15882) * Bug fix for KuzuPropertyGraphStore: Allow upserting relations even when chunks are absent (run-llama#15889) * Missing tablestore (run-llama#15890) * v0.11.7 (run-llama#15891) * nit: extend workflow tutorial (run-llama#15901) * Modify generate_qa_embedding_pairs to use LLM from Settings (run-llama#15904) * docs: document how to disable global timeout along with more docs (run-llama#15912) document how to disable global timeout along with more docs * fix: model_name property and pydantic v2 in Azure Inference package (run-llama#15907) * fix: model_name property and pydantic v2 * fix: tests * Add InternalServerError to retry decorator (run-llama#15921) * Add InternalServerError to retry decorator * Bump version * docs: fix broken link (run-llama#15924) * Adding vector store for Azure Cosmos DB NoSql (run-llama#14158) * Initial changes * initial changes fixed with example * Initial commit with all the code and test changes * fixing test cases * adding jupyter notebook * cleaning files * resolving comments * fix linting * more linting * add a basic readme --------- Co-authored-by: Aayush Kataria <aayushkataria3011@gmail.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> * update docs for custom embeddings (run-llama#15929) * Add doc.id to Langchain format conversions (run-llama#15928) * Update RankLLM with new rerankers (run-llama#15892) * Feature Request run-llama#15810 :: Add DynamoDBChatStore (run-llama#15917) * Adding support for `MetadataFilters` to WordLift Vector Store (run-llama#15905) * Repair and route colab links to official repo (run-llama#15900) * feat: Add a retry policy to steps (run-llama#15757) * Fix error handling in sharepoint reader (run-llama#15868) * feat: add llama-index llms alibabacloud_aisearch integration (run-llama#15850) * Opensearch Serverless filtered query support using knn_score script (run-llama#15899) * Mistral AI LLM Integration fixes (run-llama#15906) * Fix RagCLI (run-llama#15931) * v0.11.8 (run-llama#15933) * docs: document retry policy (run-llama#15938) * docs: update AI21 docs and readme (run-llama#15937) * docs: update ai21 docs and readme with jamba 1.5 and tool calling * docs: update ai21 docs and readme with jamba 1.5 and tool calling * docs: update ai21 docs and readme with jamba 1.5 and tool calling * Retry retriable errors in neo4j integrations (run-llama#15915) * Add four alibabacloud-aisearch llama-index integrations: rerank, node_parser, readers, embeddings (run-llama#15934) * Differentiate sync and async calls in OpenSearchVectorClient (run-llama#15945) * feat(postgres): add support for engine parameters (run-llama#15951) * feat(postgres): add support for engine parameters - Introduced engine_params to support passing parameters to create_engine. - Updated create_engine and create_async_engine calls to include engine_params. - Initialized engine_params in the constructor. * style(lint): reformat for readability * refactor(postgres): rename engine_params to create_engine_kwargs * refactor(postgres): rename engine_params to create_engine_kwargs * chore: bump version to 0.2.3 * fix(postgres): rename engine_params to create_engine_kwargs * update falkordb client (run-llama#15940) * update falkordb client * bump version * update version * fix * fix: Error when parsing output if tool name contains non-English characters (run-llama#15956) * fix attribute error in PGVectorStore (run-llama#15961) * Catch nest_asyncio errors (run-llama#15975) * NUDGE (run-llama#15954) * Add support for o1 openai models (run-llama#15979) * force temp to 1.0 for o1 (run-llama#15983) * Update concepts.md - fix link for Structured Data Extraction page (run-llama#15982) * Fix the import path example for SimpleMongoReader (run-llama#15988) * Do not pass system prompt from fn calling runner to fn calling worker (run-llama#15986) * Add callback manager to retriever query engine from args (run-llama#15990) * v0.11.9 (run-llama#15992) * Fix: get all documents from Elasticsearch KVStore (run-llama#16006) * Fix Pydantic numeric validation in openai/base.py (run-llama#15993) * feat: add quip reader (run-llama#16000) * [docs/example] Human in loop workflow example (run-llama#16011) * start choose own adventure hitl nb * hitl example * note on alternative implementation * add module guides and run prepare_for_build * fix: removed author info from quip reader (run-llama#16012) fix: removed author info * Fix Pydantic models definition (run-llama#16008) * chore(deps): bump litellm from 1.43.7 to 1.44.8 in /llama-index-integrations/embeddings/llama-index-embeddings-litellm (run-llama#16013) * Hotfix: Fix Citations Text (run-llama#16015) * Jacques/opik integration (run-llama#16007) * update llamacloud index with image nodes (run-llama#15996) * chore: add o1 models pinned versions (run-llama#16025) * add sparse embedding abstraction (run-llama#16018) * Implement `get_nodes` on `PGVectorStore` (run-llama#16026) * Implement `get_nodes` on `PGVectorStore` * Bump version num in pyproject.toml * Update docstring in base.py in MilvusVectorStore adding COSINE as available similarity metric (run-llama#16031) Update docstring in base.py adding COSINE as similarity metric available According to Milvus Documentation, **COSINE** as similarity metric is supported (Both Milvus and Milvus Lite) but in Llama-Index docs was missing. [Link to Milvus official docs](https://milvus.io/docs/metric.md?tab=floating#Similarity-Metrics) I've checked in the [code](https://github.com/run-llama/llama_index/blob/723c2533ed4b7b43b7d814c89af1838f0f1994c2/llama-index-integrations/vector_stores/llama-index-vector-stores-milvus/llama_index/vector_stores/milvus/base.py#L256) , so indeed COSINE is supported, so no more further changes are needed. * Fix: unnecessary warning issue in HuggingFace LLM when tokenizer is provided as argument(run-llama#16035) (run-llama#16037) * Attempt #3 of context/result refactor (run-llama#16036) * temporarily limit lancedb version (run-llama#16045) * fix: new Data Connector adaption for DashVector (run-llama#16028) * v0.11.10 (run-llama#16046) * Fix serde issue for huggingface inference API embedding (run-llama#16053) * wip * wip * fix: fix regression in OctoAI llm provider after 0.11 (run-llama#16002) * fix OctoAI llm provider * adjust code to the latest client * resolve conflicts * fix message format conversion * do not pass max_tokens if None * add chat test * bump version * update LanceDB integration (run-llama#16057) * Adding docstring inside preprocess base code. (run-llama#16060) * Add default to optional args for BedrockEmbedding (run-llama#16067) * wip * wip * Fix optional type for Cohere embedding (run-llama#16068) wip * fix vertex pydantic arguments (run-llama#16069) * Fix result order (run-llama#16078) * Fix result order * Bump version * fix elasticsearch embedding async function (run-llama#16083) * docs: add decorators to the api reference (run-llama#16081) * fix incorrect parameters in VertexAIIndex (run-llama#16080) * feat: update JinaEmbedding for v3 release (run-llama#15971) * Mistralai enable custom endpoint from env (run-llama#16084) * Implement async for multi modal ollama (run-llama#16091) * Remove circular package dep (run-llama#16070) * [chore] fix incorrect `handler.context` for `handler.ctx` in docs (run-llama#16101) fix * fix bug missing import (run-llama#16096) * Add more workflow references to docs (run-llama#16102) * fix cohere tests (run-llama#16104) * Use response synthesizer in context chat engines (run-llama#16017) * Fix mongodb hybrid search, also pass hybrid_top_k in vector retriever (run-llama#16105) * bump openai agent deps (run-llama#16112) * Fixed up test_vectorstore. (run-llama#16113) * Issue 16071: wordpress requires username, password (run-llama#16072) * Issue 16071: wordpress requires username, password * Adding changes suggested in PR template * Use Optional typing keyword * feat: add configurable base_url field in rerank (run-llama#16050) * add base_url * version bump * add default --------- Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> Co-authored-by: Logan <logan.markewich@live.com> * Enhance Pandas Query Engine Output Processor (run-llama#16052) * Enhance output processor to temporarily adjust display options. * Make format changes. * Update pyproject.toml --------- Co-authored-by: Logan <logan.markewich@live.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> * fix workflow docs (run-llama#16117) cr * Update OpenVINO LLM pyproject.toml (run-llama#16130) * Wordpress: Allow control of whether Pages and/or Posts are retrieved (run-llama#16128) * Async achat put operation (run-llama#16127) * [fix] handler.stream_events() doesn't yield `StopEvent` (run-llama#16115) * Improved TLM Rag cookbook (run-llama#16109) * Update chat message class for multi-modal (run-llama#15969) * Add support for Path for SimpleDirectoryReader (run-llama#16108) * Add TopicNodeParser based on MedGraphRAG paper (run-llama#16131) * Sql markdown response (run-llama#16103) * v0.11.11 (run-llama#16134) * Correct Pydantic warning(s) issed for llama-index-llms-ibm (run-llama#16141) Fix Pydantic warnings in llam-index-llms-ibm * feat: add drive link to google drive reader (run-llama#16156) * Introducing new VoyageAI models (run-llama#16150) * Add `required_exts` option to SharePoint reader (run-llama#16152) * User-defined schema in MilvusVectorStore (run-llama#16151) * safe format prompt variables in strings with JSON (run-llama#15734) * account for tools in prompt helper (run-llama#16157) * v0.11.12 (run-llama#16159) --------- Co-authored-by: Logan <logan.markewich@live.com> Co-authored-by: Ravi Theja <ravi03071991@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Yannic Spreen-Ledebur <35889034+spreeni@users.noreply.github.com> Co-authored-by: Adnan Alkattan <Adnankattan9@gmail.com> Co-authored-by: Laurie Voss <github@seldo.com> Co-authored-by: saipjkai <84132316+saipjkai@users.noreply.github.com> Co-authored-by: ScriptShi <xunjian.sl@alibaba-inc.com> Co-authored-by: Bryce Freshcorn <26725654+brycecf@users.noreply.github.com> Co-authored-by: Graham Tibbitts <grahamtt@users.noreply.github.com> Co-authored-by: Rashmi Pawar <168514198+raspawar@users.noreply.github.com> Co-authored-by: Jerry Liu <jerryjliu98@gmail.com> Co-authored-by: Caroline Binley <39920563+carolinebinley@users.noreply.github.com> Co-authored-by: Prashanth Rao <35005448+prrao87@users.noreply.github.com> Co-authored-by: Asi Greenholts <88270351+TupleType@users.noreply.github.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> Co-authored-by: Facundo Santiago <fasantia@microsoft.com> Co-authored-by: gsa9989 <117786401+gsa9989@users.noreply.github.com> Co-authored-by: Aayush Kataria <aayushkataria3011@gmail.com> Co-authored-by: Ryan Nguyen <96593302+xpbowler@users.noreply.github.com> Co-authored-by: David Riccitelli <david@wordlift.io> Co-authored-by: GICodeWarrior <GICodeWarrior@gmail.com> Co-authored-by: Javier Torres <javierandrestorresreyes@gmail.com> Co-authored-by: 才胜 <1392197444@qq.com> Co-authored-by: George Dittmar <georgedittmar@gmail.com> Co-authored-by: Tarun Jain <jaintarun.abd17@gmail.com> Co-authored-by: miri-bar <160584887+miri-bar@users.noreply.github.com> Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com> Co-authored-by: kobiche <56874660+kobiche@users.noreply.github.com> Co-authored-by: Arthur Moura Carvalho <141850116+armoucar-neon@users.noreply.github.com> Co-authored-by: Avi Avni <avi.avni@gmail.com> Co-authored-by: Cheese <11363971+cheese-git@users.noreply.github.com> Co-authored-by: Zac Wellmer <9603276+zacwellmer@users.noreply.github.com> Co-authored-by: Ragul Kachiappan <ragul.kachiappan@techjays.com> Co-authored-by: Vinicius <53495782+Vractos@users.noreply.github.com> Co-authored-by: Bidimpata-Kerim Aramyan-Tshimanga <bk.tshimanga@gmail.com> Co-authored-by: Laura Ceconi <laura.cec@hotmail.com> Co-authored-by: N1eo <zzhsaga@gmail.com> Co-authored-by: Chirag Agrawal <chirag.agrawal93@gmail.com> Co-authored-by: Andrei Fajardo <92402603+nerdai@users.noreply.github.com> Co-authored-by: David Oplatka <david.oplatka@vectara.com> Co-authored-by: Jacques Verré <jverre@gmail.com> Co-authored-by: Harpinder <harpinderjot36@gmail.com> Co-authored-by: Richard Liu <richardliu7896@gmail.com> Co-authored-by: Jorge Barrachina Gutiérrez <1333901+ntkog@users.noreply.github.com> Co-authored-by: Sourabh <Sourabh72101@gmail.com> Co-authored-by: OceanPresent <oceanpresent@163.com> Co-authored-by: Simon Suo <simonsdsuo@gmail.com> Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com> Co-authored-by: preprocess-co <137915090+preprocess-co@users.noreply.github.com> Co-authored-by: guodong <songoodong@163.com> Co-authored-by: polarbear567 <269739606@qq.com> Co-authored-by: Aaron Ji <127167174+DresAaron@users.noreply.github.com> Co-authored-by: enrico-stauss <73635664+enrico-stauss@users.noreply.github.com> Co-authored-by: Selim Çavaş <92586913+selimcavas@users.noreply.github.com> Co-authored-by: Casey Clements <caseyclements@users.noreply.github.com> Co-authored-by: Jonathan Springer <jonpspri@gmail.com> Co-authored-by: Anirudh31415926535 <anirudh@cohere.com> Co-authored-by: Matin Khajavi <58955268+MatinKhajavi@users.noreply.github.com> Co-authored-by: Ethan Yang <ethan.yang@intel.com> Co-authored-by: Matthew Turk <mturk24@users.noreply.github.com> Co-authored-by: Andrew Kim <59037923+andrewwkimm@users.noreply.github.com> Co-authored-by: José Henrique Luckmann <133380513+JoseLuckmann@users.noreply.github.com> Co-authored-by: Emanuel Ferreira <contatoferreirads@gmail.com> Co-authored-by: fzowl <160063452+fzowl@users.noreply.github.com> Co-authored-by: João Martins <11438285+jl-martins@users.noreply.github.com> Co-authored-by: Petros Mitseas <petros_94@icloud.com>
barduinor
added a commit
to box-community/llama_index
that referenced
this pull request
Sep 23, 2024
* v0.11.5 (run-llama#15834) * Box bug fix 202409 (run-llama#15836) * fix document matadata for box file * fix BoxSearchOptions class initialization * bump versions to 0.2.1 * Add oreilly course cookbooks (run-llama#15845) * correct course name (run-llama#15859) * clone llama-deploy docs during docs builds (run-llama#15794) * chore(deps-dev): bump cryptography from 43.0.0 to 43.0.1 in /llama-index-core (run-llama#15840) * Refresh Opensearch index after delete operation (run-llama#15854) * Update ImageReader file loading logic (run-llama#15848) * Minor bug in SQQE (run-llama#15861) * v0.11.6 (run-llama#15863) * remove widgets from recent notebooks (run-llama#15864) * Fix image document deserialization issue (run-llama#15857) * Bugfix: Remove warnings during data insertion for Hybrid Search due to duplicated columns in the schema (run-llama#15846) * Add TablestoreVectorStore. (run-llama#15657) * Removed unused `llama-index-llms-anthropic` dependency from Bedrock Converse (run-llama#15869) Removed unused `llama-index-llms-anthropic` dependency. Incremented to `0.3.0`. * Update bedrock.py (run-llama#15879) Fix minor issue in error message * Add tool calling example in NVIDIA notebook (run-llama#15842) * NVIDIA: Completion fixes (run-llama#15820) * Fix PGVectorStore with latest pydantic, update pydantic imports (run-llama#15886) * add type ignore for streaming agents (run-llama#15887) * [wip] force openai structured output (run-llama#15706) * feature: Make SentenceSplitter's secondary_chunking_regex optional (run-llama#15882) * Bug fix for KuzuPropertyGraphStore: Allow upserting relations even when chunks are absent (run-llama#15889) * Missing tablestore (run-llama#15890) * v0.11.7 (run-llama#15891) * nit: extend workflow tutorial (run-llama#15901) * Modify generate_qa_embedding_pairs to use LLM from Settings (run-llama#15904) * docs: document how to disable global timeout along with more docs (run-llama#15912) document how to disable global timeout along with more docs * fix: model_name property and pydantic v2 in Azure Inference package (run-llama#15907) * fix: model_name property and pydantic v2 * fix: tests * Add InternalServerError to retry decorator (run-llama#15921) * Add InternalServerError to retry decorator * Bump version * docs: fix broken link (run-llama#15924) * Adding vector store for Azure Cosmos DB NoSql (run-llama#14158) * Initial changes * initial changes fixed with example * Initial commit with all the code and test changes * fixing test cases * adding jupyter notebook * cleaning files * resolving comments * fix linting * more linting * add a basic readme --------- Co-authored-by: Aayush Kataria <aayushkataria3011@gmail.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> * update docs for custom embeddings (run-llama#15929) * Add doc.id to Langchain format conversions (run-llama#15928) * Update RankLLM with new rerankers (run-llama#15892) * Feature Request run-llama#15810 :: Add DynamoDBChatStore (run-llama#15917) * Adding support for `MetadataFilters` to WordLift Vector Store (run-llama#15905) * Repair and route colab links to official repo (run-llama#15900) * feat: Add a retry policy to steps (run-llama#15757) * Fix error handling in sharepoint reader (run-llama#15868) * feat: add llama-index llms alibabacloud_aisearch integration (run-llama#15850) * Opensearch Serverless filtered query support using knn_score script (run-llama#15899) * Mistral AI LLM Integration fixes (run-llama#15906) * Fix RagCLI (run-llama#15931) * v0.11.8 (run-llama#15933) * docs: document retry policy (run-llama#15938) * docs: update AI21 docs and readme (run-llama#15937) * docs: update ai21 docs and readme with jamba 1.5 and tool calling * docs: update ai21 docs and readme with jamba 1.5 and tool calling * docs: update ai21 docs and readme with jamba 1.5 and tool calling * Retry retriable errors in neo4j integrations (run-llama#15915) * Add four alibabacloud-aisearch llama-index integrations: rerank, node_parser, readers, embeddings (run-llama#15934) * Differentiate sync and async calls in OpenSearchVectorClient (run-llama#15945) * feat(postgres): add support for engine parameters (run-llama#15951) * feat(postgres): add support for engine parameters - Introduced engine_params to support passing parameters to create_engine. - Updated create_engine and create_async_engine calls to include engine_params. - Initialized engine_params in the constructor. * style(lint): reformat for readability * refactor(postgres): rename engine_params to create_engine_kwargs * refactor(postgres): rename engine_params to create_engine_kwargs * chore: bump version to 0.2.3 * fix(postgres): rename engine_params to create_engine_kwargs * update falkordb client (run-llama#15940) * update falkordb client * bump version * update version * fix * fix: Error when parsing output if tool name contains non-English characters (run-llama#15956) * fix attribute error in PGVectorStore (run-llama#15961) * Catch nest_asyncio errors (run-llama#15975) * NUDGE (run-llama#15954) * Add support for o1 openai models (run-llama#15979) * force temp to 1.0 for o1 (run-llama#15983) * Update concepts.md - fix link for Structured Data Extraction page (run-llama#15982) * Fix the import path example for SimpleMongoReader (run-llama#15988) * Do not pass system prompt from fn calling runner to fn calling worker (run-llama#15986) * Add callback manager to retriever query engine from args (run-llama#15990) * v0.11.9 (run-llama#15992) * Fix: get all documents from Elasticsearch KVStore (run-llama#16006) * Fix Pydantic numeric validation in openai/base.py (run-llama#15993) * feat: add quip reader (run-llama#16000) * [docs/example] Human in loop workflow example (run-llama#16011) * start choose own adventure hitl nb * hitl example * note on alternative implementation * add module guides and run prepare_for_build * fix: removed author info from quip reader (run-llama#16012) fix: removed author info * Fix Pydantic models definition (run-llama#16008) * chore(deps): bump litellm from 1.43.7 to 1.44.8 in /llama-index-integrations/embeddings/llama-index-embeddings-litellm (run-llama#16013) * Hotfix: Fix Citations Text (run-llama#16015) * Jacques/opik integration (run-llama#16007) * update llamacloud index with image nodes (run-llama#15996) * chore: add o1 models pinned versions (run-llama#16025) * add sparse embedding abstraction (run-llama#16018) * Implement `get_nodes` on `PGVectorStore` (run-llama#16026) * Implement `get_nodes` on `PGVectorStore` * Bump version num in pyproject.toml * Update docstring in base.py in MilvusVectorStore adding COSINE as available similarity metric (run-llama#16031) Update docstring in base.py adding COSINE as similarity metric available According to Milvus Documentation, **COSINE** as similarity metric is supported (Both Milvus and Milvus Lite) but in Llama-Index docs was missing. [Link to Milvus official docs](https://milvus.io/docs/metric.md?tab=floating#Similarity-Metrics) I've checked in the [code](https://github.com/run-llama/llama_index/blob/723c2533ed4b7b43b7d814c89af1838f0f1994c2/llama-index-integrations/vector_stores/llama-index-vector-stores-milvus/llama_index/vector_stores/milvus/base.py#L256) , so indeed COSINE is supported, so no more further changes are needed. * Fix: unnecessary warning issue in HuggingFace LLM when tokenizer is provided as argument(run-llama#16035) (run-llama#16037) * Attempt #3 of context/result refactor (run-llama#16036) * temporarily limit lancedb version (run-llama#16045) * fix: new Data Connector adaption for DashVector (run-llama#16028) * v0.11.10 (run-llama#16046) * Fix serde issue for huggingface inference API embedding (run-llama#16053) * wip * wip * fix: fix regression in OctoAI llm provider after 0.11 (run-llama#16002) * fix OctoAI llm provider * adjust code to the latest client * resolve conflicts * fix message format conversion * do not pass max_tokens if None * add chat test * bump version * update LanceDB integration (run-llama#16057) * Adding docstring inside preprocess base code. (run-llama#16060) * Add default to optional args for BedrockEmbedding (run-llama#16067) * wip * wip * Fix optional type for Cohere embedding (run-llama#16068) wip * fix vertex pydantic arguments (run-llama#16069) * Fix result order (run-llama#16078) * Fix result order * Bump version * fix elasticsearch embedding async function (run-llama#16083) * docs: add decorators to the api reference (run-llama#16081) * fix incorrect parameters in VertexAIIndex (run-llama#16080) * feat: update JinaEmbedding for v3 release (run-llama#15971) * Mistralai enable custom endpoint from env (run-llama#16084) * Implement async for multi modal ollama (run-llama#16091) * Remove circular package dep (run-llama#16070) * [chore] fix incorrect `handler.context` for `handler.ctx` in docs (run-llama#16101) fix * fix bug missing import (run-llama#16096) * Add more workflow references to docs (run-llama#16102) * fix cohere tests (run-llama#16104) * Use response synthesizer in context chat engines (run-llama#16017) * Fix mongodb hybrid search, also pass hybrid_top_k in vector retriever (run-llama#16105) * bump openai agent deps (run-llama#16112) * Fixed up test_vectorstore. (run-llama#16113) * Issue 16071: wordpress requires username, password (run-llama#16072) * Issue 16071: wordpress requires username, password * Adding changes suggested in PR template * Use Optional typing keyword * feat: add configurable base_url field in rerank (run-llama#16050) * add base_url * version bump * add default --------- Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> Co-authored-by: Logan <logan.markewich@live.com> * Enhance Pandas Query Engine Output Processor (run-llama#16052) * Enhance output processor to temporarily adjust display options. * Make format changes. * Update pyproject.toml --------- Co-authored-by: Logan <logan.markewich@live.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> * fix workflow docs (run-llama#16117) cr * Update OpenVINO LLM pyproject.toml (run-llama#16130) * Wordpress: Allow control of whether Pages and/or Posts are retrieved (run-llama#16128) * Async achat put operation (run-llama#16127) * [fix] handler.stream_events() doesn't yield `StopEvent` (run-llama#16115) * Improved TLM Rag cookbook (run-llama#16109) * Update chat message class for multi-modal (run-llama#15969) * Add support for Path for SimpleDirectoryReader (run-llama#16108) * Add TopicNodeParser based on MedGraphRAG paper (run-llama#16131) * Sql markdown response (run-llama#16103) * v0.11.11 (run-llama#16134) * Correct Pydantic warning(s) issed for llama-index-llms-ibm (run-llama#16141) Fix Pydantic warnings in llam-index-llms-ibm * feat: add drive link to google drive reader (run-llama#16156) * Introducing new VoyageAI models (run-llama#16150) * Add `required_exts` option to SharePoint reader (run-llama#16152) * User-defined schema in MilvusVectorStore (run-llama#16151) * safe format prompt variables in strings with JSON (run-llama#15734) * account for tools in prompt helper (run-llama#16157) * v0.11.12 (run-llama#16159) --------- Co-authored-by: Logan <logan.markewich@live.com> Co-authored-by: Ravi Theja <ravi03071991@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Yannic Spreen-Ledebur <35889034+spreeni@users.noreply.github.com> Co-authored-by: Adnan Alkattan <Adnankattan9@gmail.com> Co-authored-by: Laurie Voss <github@seldo.com> Co-authored-by: saipjkai <84132316+saipjkai@users.noreply.github.com> Co-authored-by: ScriptShi <xunjian.sl@alibaba-inc.com> Co-authored-by: Bryce Freshcorn <26725654+brycecf@users.noreply.github.com> Co-authored-by: Graham Tibbitts <grahamtt@users.noreply.github.com> Co-authored-by: Rashmi Pawar <168514198+raspawar@users.noreply.github.com> Co-authored-by: Jerry Liu <jerryjliu98@gmail.com> Co-authored-by: Caroline Binley <39920563+carolinebinley@users.noreply.github.com> Co-authored-by: Prashanth Rao <35005448+prrao87@users.noreply.github.com> Co-authored-by: Asi Greenholts <88270351+TupleType@users.noreply.github.com> Co-authored-by: Massimiliano Pippi <mpippi@gmail.com> Co-authored-by: Facundo Santiago <fasantia@microsoft.com> Co-authored-by: gsa9989 <117786401+gsa9989@users.noreply.github.com> Co-authored-by: Aayush Kataria <aayushkataria3011@gmail.com> Co-authored-by: Ryan Nguyen <96593302+xpbowler@users.noreply.github.com> Co-authored-by: David Riccitelli <david@wordlift.io> Co-authored-by: GICodeWarrior <GICodeWarrior@gmail.com> Co-authored-by: Javier Torres <javierandrestorresreyes@gmail.com> Co-authored-by: 才胜 <1392197444@qq.com> Co-authored-by: George Dittmar <georgedittmar@gmail.com> Co-authored-by: Tarun Jain <jaintarun.abd17@gmail.com> Co-authored-by: miri-bar <160584887+miri-bar@users.noreply.github.com> Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com> Co-authored-by: kobiche <56874660+kobiche@users.noreply.github.com> Co-authored-by: Arthur Moura Carvalho <141850116+armoucar-neon@users.noreply.github.com> Co-authored-by: Avi Avni <avi.avni@gmail.com> Co-authored-by: Cheese <11363971+cheese-git@users.noreply.github.com> Co-authored-by: Zac Wellmer <9603276+zacwellmer@users.noreply.github.com> Co-authored-by: Ragul Kachiappan <ragul.kachiappan@techjays.com> Co-authored-by: Vinicius <53495782+Vractos@users.noreply.github.com> Co-authored-by: Bidimpata-Kerim Aramyan-Tshimanga <bk.tshimanga@gmail.com> Co-authored-by: Laura Ceconi <laura.cec@hotmail.com> Co-authored-by: N1eo <zzhsaga@gmail.com> Co-authored-by: Chirag Agrawal <chirag.agrawal93@gmail.com> Co-authored-by: Andrei Fajardo <92402603+nerdai@users.noreply.github.com> Co-authored-by: David Oplatka <david.oplatka@vectara.com> Co-authored-by: Jacques Verré <jverre@gmail.com> Co-authored-by: Harpinder <harpinderjot36@gmail.com> Co-authored-by: Richard Liu <richardliu7896@gmail.com> Co-authored-by: Jorge Barrachina Gutiérrez <1333901+ntkog@users.noreply.github.com> Co-authored-by: Sourabh <Sourabh72101@gmail.com> Co-authored-by: OceanPresent <oceanpresent@163.com> Co-authored-by: Simon Suo <simonsdsuo@gmail.com> Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com> Co-authored-by: preprocess-co <137915090+preprocess-co@users.noreply.github.com> Co-authored-by: guodong <songoodong@163.com> Co-authored-by: polarbear567 <269739606@qq.com> Co-authored-by: Aaron Ji <127167174+DresAaron@users.noreply.github.com> Co-authored-by: enrico-stauss <73635664+enrico-stauss@users.noreply.github.com> Co-authored-by: Selim Çavaş <92586913+selimcavas@users.noreply.github.com> Co-authored-by: Casey Clements <caseyclements@users.noreply.github.com> Co-authored-by: Jonathan Springer <jonpspri@gmail.com> Co-authored-by: Anirudh31415926535 <anirudh@cohere.com> Co-authored-by: Matin Khajavi <58955268+MatinKhajavi@users.noreply.github.com> Co-authored-by: Ethan Yang <ethan.yang@intel.com> Co-authored-by: Matthew Turk <mturk24@users.noreply.github.com> Co-authored-by: Andrew Kim <59037923+andrewwkimm@users.noreply.github.com> Co-authored-by: José Henrique Luckmann <133380513+JoseLuckmann@users.noreply.github.com> Co-authored-by: Emanuel Ferreira <contatoferreirads@gmail.com> Co-authored-by: fzowl <160063452+fzowl@users.noreply.github.com> Co-authored-by: João Martins <11438285+jl-martins@users.noreply.github.com> Co-authored-by: Petros Mitseas <petros_94@icloud.com>
jerryjliu
added a commit
to run-llama/llamacloud-demo
that referenced
this pull request
Sep 23, 2024
- do chunk-level retrieval and document-level retrival to fetch relevant bits for apple/tesla - do custom LLM prompt to insert chunks to generate report - use structured output abstractions to generate report depends on this PR: run-llama/llama_index#15734
raspawar
pushed a commit
to raspawar/llama_index
that referenced
this pull request
Oct 7, 2024
raspawar
pushed a commit
to raspawar/llama_index
that referenced
this pull request
Oct 7, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This fixes the edge case where the prompt template also contains json, and you don't want to treat the JSON string as template variables
Thanks @erik-megarad