Knowledge Search Retrieval

“Disclosure up front: I build Grunz, a hosted chat + coding agent on open-weight models. Not pitching anything — this is a retrieval-sizing problem I keep hitting and I suspect it silently affects more Haystack pipelines than people realise. Your retrieval budget is probably based on a number you are not actually being served Splitter length, top_k, and reranking are all tuned against an assumed context budget.…”

“Disclosure up front: I build Grunz, a hosted chat + coding agent on open-weight models. Nothing to sell here — this is a retrieval-sizing problem I keep hitting and I suspect it affects more LlamaIndex users than realise it. The number your retrieval budget is based on is probably wrong Chunk size, top-k and reranking all get tuned against an assumed context budget. That budget is normally taken from the model…”

“the real missing skill isn’t RAG or agents. it’s knowing when to use neither. most “AI engineer” failures are a RAG pipeline on a problem a SQL query would’ve solved in 50ms.”

Comment, author, and video data come from YouTube API Services. NeedRadar generated the classification, summary, AI path, counterevidence, and unknowns; YouTube did not provide or endorse them.

“Context: I operate a compliance-sensitive local evidence pipeline that consumes Codex session records. I need an authoritative, version-bound statement of what Codex guarantees for its local session storage. I have read the docs at developers.openai.com/codex (app-server, noninteractive, cli/reference, config-reference, sdk) and could not find these guarantees stated. Current environment: ChatGPT desktop app…”

“### Feature Description Add the new capabilities of autoEmbed from vector search and the reranker native stage to MongoDBAtlasVectorSearch ### Reason The current version of MongoDBAtlasVectorSearch does not allow for autoEmbed or add the native reranker stage ### Value of Feature _No response_”

“### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community…”

“### Description `InMemoryStore.search()` and `asearch()` ignore the remaining pagination offset when semantic search fills a page with items saved using `index=False`. Later pages repeat the first unindexed items, and an offset beyond the result count still returns items. With both indexed and unindexed items, the offset is applied to scored items but the scoreless fallback always starts at the beginning of its…”

“### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community…”

“### Description In `mem0/vector_stores/azure_ai_search.py`, `insert()`, `delete()`, and `update()` have a broken response validation condition: ```python if not hasattr(doc, "status_code") and doc.get("status_code") != 201: ``` On real Azure SDK `IndexingResult` objects, `hasattr(doc, "status_code")` is `True`. Because of the `and`, the condition short-circuits to `False`, skipping the error check entirely.…”

“## Summary Codex can call an Amazon Bedrock AgentCore Gateway's semantic-search tool and receive valid MCP tool definitions, but those discovered tools are not added to the current session's callable tool surface. The search response includes the target tool name, description, and input schema. Attempting to call the returned name from the same Codex session fails because no callable function was registered. A…”

“### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community…”

“### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community…”

“### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community…”

“### Feature Description When building RAG pipelines with LlamaIndex, web pages are often the primary data source — but the existing readers in llama-index-readers-web (including TrafilaturaWebReader, ReadabilityWebReader, MainContentExtractorReader) return the full extracted content regardless of what the user is actually asking. For a typical large documentation page, this means: - 15,000+ tokens returned per…”

“### Component Python SDK ### Description ### Use Case **What problem are you trying to solve?** Currently, `mem0` supports multiple embedding providers such as OpenAI and HuggingFace, but it does not have native support for Cohere's embedding models. Many developers use Cohere's embedding models, such as `embed-english-v3.0` and `embed-multilingual-v3.0`, for vector representations and RAG workflows. Adding…”